Operations & systems

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Land and deploy workflow. Merges the PR, waits for CI and deploy, verifies production health via canary checks. Takes over after /ship creates the PR. Use when: "merge", "land", "deploy", "merge and verify", "land it", "ship it to production". (gstack)

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is ready, asks about deploying, wants to push code up, or asks to create a PR. (gstack)

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

This skill should be used when generating comprehensive test cases from PRD documents or user requirements. Triggers when users request test case generation, QA planning, test scenario creation, or need structured test documentation. Produces detailed test cases covering functional, edge case, error handling, and state transition scenarios.

Interactive Product Owner skill for requirements gathering, analysis, and PRD generation. Triggers when users request product requirements, feature specification, PRD creation, or need help understanding and documenting project requirements. Uses quality scoring and iterative dialogue to ensure comprehensive requirements before generating professional PRD documents.

This skill should be used for browser automation tasks using Chrome DevTools Protocol (CDP). Triggers when users need to launch Chrome with remote debugging, navigate pages, execute JavaScript in browser context, capture screenshots, or interactively select DOM elements. No MCP server required.

Install Claude skills from GitHub repositories with automated security scanning. Triggers when users want to install skills from a GitHub URL, need to browse available skills in a repository, or want to safely add new skills to their Claude environment.

Extreme lightweight end-to-end development workflow with requirements clarification, intelligent backend selection, parallel codeagent execution, and mandatory 90% test coverage

This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成", "AI视频", "短剧", "广告视频", "视频延长", or discusses video prompt engineering, AI video generation, or Seedance 2.0 workflows.

Efficiently extract and convert the contents of any local file—such as PDF, DOCX, DOC, ODT, RTF, XLSX, XLS, or HTML—into clean, well-formatted markdown saved to disk. Use this skill whenever the user requests to parse, read, or extract information from a file on their computer, including phrases like “parse this PDF”, “convert this document”, “read this file”, “extract text from”, or when a local file path (not a URL) is provided. This skill offers advanced options like generating AI-powered summaries and answering questions based on the file's content. Prefer this tool over `scrape` when handling local files to deliver precise, structured outputs for downstream tasks.

Create Vue 3 components with Composition API — composables, Pinia store integration, TypeScript, and unit tests.

Craft Stable Diffusion prompts — SDXL, LoRA triggers, ControlNet hints, and ComfyUI workflow design.

Write high-converting copy — landing pages, ads, product descriptions, taglines, and brand narratives.

Build data-rich infographics as SVG or HTML — timelines, process flows, comparison charts, and statistical summaries.

Analyze competitors — feature matrices, pricing comparisons, positioning maps, and SWOT analysis.

Design Google Cloud architectures — GKE, Cloud Run, BigQuery, Pub/Sub, and Cloud Spanner solutions.

Generate pure CSS art and illustrations — portraits, landscapes, UI elements, and interactive CSS-only animations.

Build end-to-end ETL pipelines — extract from APIs/databases, transform, validate, and load into data warehouses.

Write compelling grant applications — needs statements, project narratives, budgets, and evaluation plans.

Design full online courses — learning objectives, module outlines, lesson scripts, quizzes, and assessment rubrics.

Generate database migrations with up/down scripts — Alembic, Flyway, Liquibase, and framework-native migrations.

Design alert configurations — thresholds, severity levels, routing, de-duplication, and escalation policies.

Design click-worthy thumbnails — layout compositions, text overlays, color psychology, and A/B test variants.

Build polished command-line tools — argument parsing, help text, interactive prompts, progress bars, and shell completions.

Compile data-driven reports with charts, tables, and narrative sections — business reports, research summaries, and dashboards.

Design and generate publication-quality charts — bar, line, pie, scatter, heatmaps, and interactive D3 visualizations.

Master pandas operations — DataFrames, Series, groupby, merge, time-series resampling, and memory optimization.

Design and track OKR frameworks — set objectives, measurable key results, check-in templates, and scoring rubrics.

Write Jenkins declarative and scripted pipelines — stages, parallel execution, credentials, and shared libraries.

Create comprehensive study guides — key concepts, mnemonics, practice problems, and exam strategies.

Detect cognitive and statistical biases — confirmation bias, survivorship bias, sampling issues, and logical fallacies.

Craft viral tweet threads — hook tweets, narrative arcs, engagement CTAs, and optimal posting strategies.

Run agile sprints — backlog refinement, story pointing, sprint planning, daily standups, and retrospective formats.

Track and manage action items — owners, deadlines, status updates, and escalation workflows.

Generate complete UI themes — color tokens, spacing scales, typography systems, and dark/light mode variants.

Transform and reshape data — pivot, melt, aggregate, join, and apply complex business rules to datasets.

Identify and analyze trends — technology signals, market shifts, sentiment tracking, and future-back scenarios.

Design and implement GraphQL schemas — types, queries, mutations, subscriptions, resolvers, and federation.

Write PySpark and Spark SQL jobs — RDDs, DataFrames, streaming, MLlib, and cluster configuration.

Optimize YouTube content — titles, descriptions, tags, thumbnails, chapters, and end screen strategies.

Package text and images into valid ePub 3 e-books — chapters, TOC, cover images, and metadata for Kindle and Apple Books.

Engineer Midjourney prompts — style references, aspect ratios, negative prompts, and v6 parameter tuning.

Build Twilio communications — SMS, voice calls, WhatsApp, video, and Verify for 2FA.

Evaluate ML models rigorously — cross-validation, confusion matrices, ROC curves, bias audits, and interpretability.

Check for OWASP Top 10 vulnerabilities — injection, broken auth, XSS, insecure deserialization, and misconfiguration.

Audit project dependencies — outdated packages, known CVEs, license conflicts, and upgrade recommendations.

Write structured meeting minutes — attendance, decisions, action items, parking lot items, and next-meeting prep.

Build webhook handlers — payload validation, signature verification, retry logic, and event routing.

Build n8n automation workflows — nodes, expressions, error handling, and self-hosted deployment.

Collaborate on long-form documents — track changes, merge edits, maintain consistent voice, and manage review cycles.

Write performance reviews — self-assessments, manager evaluations, 360 feedback synthesis, and development plans.

Generate consistent icon sets in SVG — line icons, filled icons, duotone, and multi-size PNG exports for apps and websites.

Design and create ML features — encoding, scaling, interaction terms, embeddings, and feature selection.

Integrate Stripe payments — Checkout, Payment Intents, subscriptions, webhooks, and billing portal.

Generate professional PDF invoices with line items, taxes, discounts, payment terms, and company branding.

Prepare for exams — practice tests, weak-area drills, timed quizzes, and performance feedback.

Create effective meeting agendas — objectives, time boxes, pre-read materials, and decision frameworks.

Write LinkedIn posts that build personal brand — thought leadership, storytelling, and algorithm-friendly formatting.

Build interactive data dashboards — Streamlit, Dash, Grafana, and Power BI reports with live data sources.

Create GitLab CI/CD pipelines — stages, jobs, caching, artifacts, environments, and Auto DevOps customization.

Generate structured interview guides — behavioral, technical, and situational questions with scoring rubrics.

Auto-generate documentation from code — docstrings, API references, README files, and changelog entries.

Perform threat modeling — STRIDE, attack trees, data flow diagrams, and mitigation recommendations.

Integrate with Notion — database queries, page creation, property updates, and content sync.

Build apps with the Anthropic Claude API — chat completions, tool use, streaming, vision, and multi-turn conversations.

Select and pair typefaces, set type scales, and generate CSS typography systems for web and print.

Build Chrome/Edge extensions — manifest v3, content scripts, service workers, popup UIs, and Chrome API integrations.

Build assessment rubrics — criteria, performance levels, point values, and qualitative descriptors.

Build cohort analyses — retention curves, LTV by cohort, churn funnels, and behavioral segmentation.

Design RESTful and RPC APIs — OpenAPI specs, request/response schemas, error codes, versioning, and documentation.

Write compelling video scripts — YouTube tutorials, explainers, ads, and documentary-style narratives with B-roll notes.

Compose professional emails for any context — outreach, follow-ups, apologies, negotiations, and announcements.

Create, read, edit, and fix spreadsheets — add columns, compute formulas, format cells, generate charts, and clean messy tabular data.

Refactor codebases with confidence — extract methods, reduce complexity, apply SOLID principles, and modernize legacy code.

Process, generate, and manipulate PDF files — extract text, merge, split, rotate, watermark, fill forms, and OCR scanned PDFs.

Design personalized learning paths — skill assessment, resource curation, milestones, and progress tracking.

Conduct market research — survey design, interview scripts, secondary research synthesis, and insight reports.

Write optimized Dockerfiles — multi-stage builds, layer caching, security hardening, and minimal image sizes.

Review academic literature — summarize papers, extract key findings, identify gaps, and synthesize research themes.

Research keywords — intent mapping, competition analysis, long-tail opportunities, and cluster groupings.

Generate creative algorithmic and generative art using code — fractals, parametric patterns, noise fields, and procedural imagery.

Plan and conduct UX research — usability tests, journey maps, affinity diagrams, and design recommendations.

Perform SQL-based data analysis — exploratory queries, aggregations, funnels, cohorts, and insight narratives.

Build Slack bots and apps — Bolt framework, slash commands, modals, Block Kit UI, and event subscriptions.

Detect hardcoded secrets and credentials in codebases — API keys, tokens, passwords, and remediation steps.

Convert any UI to a polished dark mode — semantic color tokens, system preference detection, and smooth transitions.

Write Dockerfiles and docker-compose files — multi-stage builds, health checks, volumes, networks, and production configurations.

Prepare for SOC 2 audits — control mapping, evidence collection, gap analysis, and audit narrative writing.

Explain complex topics simply — analogies, Feynman technique breakdowns, and layered explanations for any audience.

Build detailed project plans — WBS, Gantt charts, resource allocation, risk registers, and milestone tracking.

Create Anki-compatible flashcard decks — spaced repetition, cloze deletions, images, and export to CSV/APKG.

Design Azure architectures — AKS, Functions, Cosmos DB, Service Bus, and Azure AD integration patterns.

Create Discord bots — slash commands, embeds, voice, roles, threads, and Discord.js/Pycord implementations.

Build harmonious color palettes — complementary, analogous, triadic schemes with WCAG contrast checks and CSS variable exports.

Write and optimize complex SQL queries — JOINs, CTEs, window functions, query plans, and dialect-specific syntax.

Parse, transform, validate, and convert XML documents — XPath queries, XSLT transforms, schema validation, and XML-to-JSON conversion.

Write internal communications — all-hands updates, policy announcements, team memos, and executive briefings.

Identify security vulnerabilities in code and configurations — CVE lookup, SAST findings, and remediation guides.

Build new Claude skills from scratch — SKILL.md authoring, instruction design, example writing, and testing.

Author Kubernetes manifests — Deployments, Services, Ingress, ConfigMaps, Secrets, HPA, and Helm charts.

Design and render graphics on HTML5 Canvas — illustrations, diagrams, UI mockups, and interactive visual elements.

Design SVG logos with multiple variants — primary, monochrome, favicon, and animated versions with brand alignment.

Build financial models — P&L projections, cash flow forecasts, unit economics, DCF valuations, and scenario analysis.

Scaffold production-ready REST APIs with authentication, rate limiting, validation, and OpenAPI docs.

Build step-by-step tutorials — prerequisites, numbered steps, screenshots, troubleshooting, and next-steps.

Craft ATS-optimized resumes and cover letters tailored to specific job descriptions — formats for multiple industries.

Profile and optimize application performance — algorithmic complexity, caching strategies, database queries, and bundle size.

Create, edit, and extract content from .pptx presentations — slide decks, pitch decks, speaker notes, animations, and templates.

Facilitate cohort-based learning — weekly prompts, peer challenges, group projects, and community engagement.

Generate, format, and convert Markdown documents — README files, wikis, changelogs, and full documentation sites.

Plan content calendars — themes, publishing schedules, platform mix, repurposing strategies, and campaign alignment.

Analyze application and infrastructure logs — pattern detection, error clustering, and anomaly identification.

Build end-to-end ML pipelines — data prep, feature engineering, model training, evaluation, and MLflow tracking.

Write information security policies — acceptable-use, incident response, data classification, and access control.

Create standard operating procedures — step-by-step workflows, decision trees, safety notes, and version control.

Build, render, and manage document templates with dynamic variables, conditionals, and loops using Jinja2 or Handlebars.

Plan podcast episodes — show structure, interview questions, segment timing, and show notes.

Create CI/CD pipelines — GitHub Actions, GitLab CI, Jenkins, and CircleCI with test, build, and deploy stages.

Transform raw data into compelling interactive visualizations — dashboards, maps, network graphs, and Sankey diagrams.

Generate personalized documents from templates and data sources — bulk letters, certificates, invoices, and email campaigns.

Turn data into compelling narratives — executive summaries, annotated charts, and data-driven presentations.

Develop Angular components — services, pipes, directives, reactive forms, RxJS, and Angular Material.

Design effective surveys — question types, Likert scales, skip logic, pilot testing, and analysis plans.

Build Microsoft Teams apps — bots, message extensions, tabs, adaptive cards, and Graph API integration.

Build Svelte 5 components — runes, stores, SvelteKit routing, and server-side rendering.

Build customer success playbooks — onboarding flows, health scoring, QBR templates, and churn intervention plans.

Create custom animated GIFs optimized for Slack — reactions, celebrations, status indicators, and team mascots.

Analyze markets — TAM/SAM/SOM sizing, Porter's Five Forces, SWOT analysis, and customer segmentation.

Summarize meetings from transcripts — key decisions, action items, owners, deadlines, and follow-up emails.

Check compliance with standards — ISO 27001, SOC 2, PCI-DSS, HIPAA, and NIST frameworks.

Assist authorized penetration testing — recon methodology, vulnerability identification, and report writing.

Clean messy datasets — handle missing values, fix dtypes, remove duplicates, normalize formats, and flag anomalies.

Draft organizational policies — HR policies, data governance, acceptable-use, and regulatory compliance documents.

Design pixel art sprites, tilesets, and animations — game assets, retro icons, and character sheets.

Integrate with GitHub — Actions, Apps, webhooks, Octokit, and repository automation workflows.

Write speeches for any occasion — keynotes, toasts, eulogies, commencements, and investor pitches.

Format and manage citations — APA, MLA, Chicago, IEEE, and Vancouver styles with BibTeX export.

Perform thorough code reviews — bugs, security issues, performance bottlenecks, style violations, and architectural concerns.

Run statistical analyses — hypothesis tests, regressions, ANOVA, confidence intervals, and power calculations.

Write and run comprehensive web app tests — unit, integration, E2E with Playwright/Cypress, and visual regression.

Build production-ready React components — hooks, context, accessibility, TypeScript types, and Storybook stories.

Create Make (Integromat) scenarios — modules, routers, aggregators, and error handlers.

Author and compile LaTeX documents — academic papers, theses, mathematical equations, bibliographies, and Beamer presentations.

Analyze, clean, transform, and summarize CSV files — detect anomalies, compute statistics, and produce actionable insights.

Configure observability stacks — Prometheus, Grafana, alerting rules, SLOs, error budgets, and on-call runbooks.

Generate alt text, captions, and metadata for images — accessibility compliance, social media, and SEO.

Design and analyze A/B tests — sample sizes, significance testing, multiple comparisons, and results interpretation.

Format, validate, transform, and query JSON data — pretty-print, minify, diff two JSON objects, and extract fields with JSONPath.

Audit and fix accessibility issues — WCAG 2.2 compliance, ARIA labels, color contrast, keyboard navigation, and screen-reader compatibility.

Write inclusive, compelling job descriptions — role summaries, requirements, benefits, and bias-free language.

Create animated SVGs with GSAP or CSS — loaders, illustrations, icon animations, and micro-interactions.

Design pixel-perfect frontend UIs with HTML/CSS/Tailwind — responsive layouts, component libraries, and design-to-code workflows.

Build concept maps and knowledge graphs — nodes, relationships, hierarchies, and Mermaid/Graphviz exports.

Craft investor pitch narratives — problem/solution framing, market sizing, traction slides, and Q&A preparation.

Create Helm charts — templates, values, helpers, hooks, tests, and OCI chart publishing.

Write Terraform infrastructure-as-code — providers, modules, state management, and cloud resource definitions.

Audit code for security vulnerabilities — OWASP Top 10, injection flaws, auth issues, secrets exposure, and dependency risks.

Create technical documentation — API docs, user guides, runbooks, architecture decision records, and onboarding guides.

Create VS Code extensions — commands, language servers, tree views, webview panels, and marketplace publishing.

Draft professional press releases — headline, dateline, lead, boilerplate, and media contact formatting.

Evaluate information sources — CRAAP test, lateral reading, domain authority, and bias assessment.

Analyze customer feedback — sentiment analysis, theme clustering, NPS interpretation, and improvement roadmaps.

Design Zapier automations — triggers, actions, filters, formatters, and multi-step Zap architectures.

Generate quizzes from any content — multiple choice, true/false, short answer, and fill-in-the-blank with answer keys.

Plan engaging lessons — objectives, warm-ups, instruction, guided practice, assessments, and differentiation strategies.

Automatically fill PDF and HTML forms from structured data — applications, registrations, and government forms.

Design normalized relational database schemas — ERDs, indexes, constraints, migrations, and performance optimization.

Design KPI frameworks — define metrics, set targets, build tracking templates, and generate progress reports.

Create high-fidelity UI mockups in HTML/CSS — dashboards, mobile screens, landing pages, and component previews.

Scaffold and implement Model Context Protocol servers — tools, resources, prompts, and sampling handlers.

Diagnose and fix bugs systematically — error analysis, stack trace interpretation, root cause identification, and fix suggestions.

Optimize content for search — keyword research, on-page SEO, meta tags, structured data, and content briefs.

Generate low-fidelity wireframes and user-flow diagrams — screens, navigation maps, and interaction annotations.

Design AWS architectures — VPCs, EC2, ECS, Lambda, RDS, S3, CloudFront, and Well-Architected Framework reviews.

Build complete design systems — component tokens, Storybook stories, Figma variables, and living style guides.

Design curricula — scope and sequence, standards alignment, unit plans, and pacing guides.

Write winning proposals — RFP responses, project proposals, business cases, and partnership agreements.

Create, read, edit, and manipulate Word .docx files with full formatting — tables of contents, headings, page numbers, letterheads, tracked changes.

Write support responses — ticket triage, empathetic replies, escalation paths, and macro templates.

Create docker-compose configurations — service definitions, networks, volumes, health checks, and environment management.

Verify claims and sources — cross-reference facts, assess source credibility, and flag misinformation.

Summarize research papers and reports — abstracts, key findings, methodology critique, and practical implications.

Automate Jira — issue creation, sprint management, JQL queries, and project reporting via REST API.

Write comprehensive business plans — executive summary, market analysis, financial projections, and competitive positioning.

Create qualitative interview guides — discussion guides, probing questions, thematic analysis, and synthesis frameworks.

Build interactive HTML/CSS/JS artifacts — widgets, calculators, games, and mini-apps that run directly in Claude.

Build GitHub Actions workflows — CI, CD, automated releases, dependency updates, and custom composite actions.

Use when deploying changes to staging across relay, relay-dashboard, and relay-cloud repos - coordinates multi-repo branch syncing using git worktrees, automatically triggers staging deployments via GitHub Actions

Use when building multi-agent workflows with the relay broker-sdk - covers the WorkflowBuilder API, DAG step dependencies, agent definitions, step output chaining via {{steps.X.output}}, verification gates, evidence-based completion, owner decisions, dedicated channels, dynamic channel management (subscribe/unsubscribe/mute/unmute), swarm patterns, error handling, event listeners, step sizing rules, authoring best practices, and the lead+workers team pattern for complex steps

Use when building Cmd+K command palettes in React - covers keyboard navigation with arrow keys, keeping selected items in view with scrollIntoView, filtering with shortcut matching, and preventing infinite re-renders from reference instability

Use when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool access, model selection, and validation against schema.

Use when creating or publishing Claude Code hooks - covers executable format, event types, JSON I/O, exit codes, security requirements, and PRPM package structure

Detect documentation drift and propose updates to docs/ai/, AGENTS.md, and CLAUDE.md. Use when session-start warnings flag stale docs, after significant code changes, or periodically to keep context current.

Audit citations in LaTeX files -- check all \cite keys exist in .bib and verify via Perplexity

Creates new Claude Code skills, auto-apply skills, or auto-trigger rules, or audits existing ones for quality and effectiveness.

Fix for NATS JetStream consumer losing position after restart. Use when consumer stops receiving messages after process restart. Implements durable consumer name for persistent subscription state.

Autonomous agent execution mode

Guided workflow navigation showing current state and next steps

Deploy and archive the development cycle

Security audit of deployment infrastructure. Reviews server setup, configs, hardening, secrets management.

Build the current sprint

Security and quality audit of sprint implementation. Final gate before sprint completion. Creates COMPLETED marker on approval. Resolves local sprint IDs to global IDs via Sprint Ledger.

Plan your project — requirements, architecture, and sprints

View and manage Sprint Ledger status. Provides global sprint numbering and cycle management.

Review and audit your work

Run all remaining phases autonomously — discuss→plan→execute per phase

Retroactively audit and fill Nyquist validation gaps for a completed phase

Display project statistics — phases, plans, requirements, git metrics, and timeline

Retroactive 6-pillar visual audit of implemented frontend code

Route freeform text to the right GSD command automatically

Configure GSD workflow toggles and model profile

Remove a future phase from roadmap and renumber subsequent phases

Archive completed milestone and prepare for next version

Remove a GSD workspace and clean up worktrees

Create context handoff when pausing work mid-phase

Zero-friction idea capture. Append, list, or promote notes to todos.

Capture idea or task as todo from current conversation context

Create phases to close all gaps identified by milestone audit

Automatically advance to the next logical step in the GSD workflow

Generate a session report with token usage estimates, work summary, and outcomes

Resume work from previous session with full context restoration

Check project progress, show context, and route to next action (execute or plan)

Audit milestone completion against original intent before archiving

Show available GSD commands and usage guide

Add phase to end of current milestone in roadmap

Generate developer behavioral profile and create Claude-discoverable artifacts

Insert urgent work as decimal phase (e.g., 72.1) between existing phases

Start a new milestone cycle — update PROJECT.md and route to requirements

Initialize a new project with deep context gathering and PROJECT.md

Update GSD to latest version with changelog display

Generate tests for a completed phase based on UAT criteria and implementation

Validate built features through conversational UAT

Create an isolated workspace with repo copies and independent .planning/

Request cross-AI peer review of phase plans from external AI CLIs

Archive accumulated phase directories from completed milestones

Execute a trivial task inline — no subagents, no planning overhead

Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents

Diagnose planning directory health and optionally repair issues

List active GSD workspaces and their status

Create a clean PR branch by filtering out .planning/ commits — ready for code review

Run all remaining phases autonomously — discuss→plan→execute per phase

Retroactively audit and fill Nyquist validation gaps for a completed phase

Display project statistics — phases, plans, requirements, git metrics, and timeline

Retroactive 6-pillar visual audit of implemented frontend code

Route freeform text to the right GSD command automatically

Configure GSD workflow toggles and model profile

Archive completed milestone and prepare for next version

Research how to implement a phase (standalone - usually use /gsd:plan-phase instead)

Remove a GSD workspace and clean up worktrees

Zero-friction idea capture. Append, list, or promote notes to todos.

Generate a session report with token usage estimates, work summary, and outcomes

Resume work from previous session with full context restoration

Check project progress, show context, and route to next action (execute or plan)

Show available GSD commands and usage guide

Add phase to end of current milestone in roadmap

Generate developer behavioral profile and create Claude-discoverable artifacts

Insert urgent work as decimal phase (e.g., 72.1) between existing phases

Start a new milestone cycle — update PROJECT.md and route to requirements

Initialize a new project with deep context gathering and PROJECT.md

Update GSD to latest version with changelog display

Generate tests for a completed phase based on UAT criteria and implementation

Validate built features through conversational UAT

Create an isolated workspace with repo copies and independent .planning/

Generate UI design contract (UI-SPEC.md) for frontend phases

Request cross-AI peer review of phase plans from external AI CLIs

Gather phase context through adaptive questioning before planning. Use --auto to skip interactive questions (Claude picks recommended defaults).

Archive accumulated phase directories from completed milestones

Execute a trivial task inline — no subagents, no planning overhead

Post-mortem investigation for failed GSD workflows — analyzes git history, artifacts, and state to diagnose what went wrong

Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents

Diagnose planning directory health and optionally repair issues

List active GSD workspaces and their status

Create a clean PR branch by filtering out .planning/ commits — ready for code review

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

用于加载状态、错误处理和数据获取的现代React UI模式。在构建UI组件、处理异步数据或管理UI状态时使用。

Build automated billing systems for recurring payments, invoicing, subscription lifecycle, and dunning management. Use when implementing subscription billing, automating invoicing, or managing recurring payment systems.

This skill should be used when enhancing the visual design and aesthetics of Next.js web applications. It provides modern UI components, design patterns, color palettes, animations, and layout templates. Use this skill for tasks like improving styling, creating responsive designs, implementing modern UI patterns, adding animations, selecting color schemes, or building aesthetically pleasing frontend interfaces.

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

Configure Static Application Security Testing (SAST) tools for automated vulnerability detection in application code. Use when setting up security scanning, implementing DevSecOps practices, or automating code vulnerability detection.

Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks, or improving application performance.

Master Python asyncio, concurrent programming, and async/await patterns for high-performance applications. Use when building async APIs, concurrent systems, or I/O-bound applications requiring non-blocking operations.

Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

This skill should be used whenever users need help with resume creation, updating professional profiles, tracking career experiences, managing projects portfolio, or generating tailored resumes for job applications. On first use, extracts data from user's existing resume and maintains a structured database of experiences, projects, education, and skills. Generates professionally styled one-page PDF resumes customized for specific job roles by selecting only the most relevant information from the database.

This skill should be used whenever users ask food-related questions, meal suggestions, nutrition advice, recipe recommendations, or dietary planning. On first use, the skill collects comprehensive user preferences (allergies, dietary restrictions, goals, likes/dislikes) and stores them in a persistent database. All subsequent food-related responses are personalized based on these stored preferences.

Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.

Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment.

Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration. Use when architecting deployment workflows, setting up continuous delivery, or implementing GitOps practices.

This skill should be used when analyzing CSV datasets, handling missing values through intelligent imputation, and creating interactive dashboards to visualize data trends. Use this skill for tasks involving data quality assessment, automated missing value detection and filling, statistical analysis, and generating Plotly Dash dashboards for exploratory data analysis.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossible

Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

This skill should be used when analyzing technical debt in a codebase, documenting code quality issues, creating technical debt registers, or assessing code maintainability. Use this for identifying code smells, architectural issues, dependency problems, missing documentation, security vulnerabilities, and creating comprehensive technical debt documentation.

Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists

Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository

Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Implement GitOps workflows with ArgoCD and Flux for automated, declarative Kubernetes deployments with continuous reconciliation. Use when implementing GitOps practices, automating Kubernetes deployments, or setting up declarative infrastructure management.

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Build automated billing systems for recurring payments, invoicing, subscription lifecycle, and dunning management. Use when implementing subscription billing, automating invoicing, or managing recurring payment systems.

Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.

This skill should be used when enhancing the visual design and aesthetics of Next.js web applications. It provides modern UI components, design patterns, color palettes, animations, and layout templates. Use this skill for tasks like improving styling, creating responsive designs, implementing modern UI patterns, adding animations, selecting color schemes, or building aesthetically pleasing frontend interfaces.

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

Configure Static Application Security Testing (SAST) tools for automated vulnerability detection in application code. Use when setting up security scanning, implementing DevSecOps practices, or automating code vulnerability detection.

Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks, or improving application performance.

Master Python asyncio, concurrent programming, and async/await patterns for high-performance applications. Use when building async APIs, concurrent systems, or I/O-bound applications requiring non-blocking operations.

Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.

Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

This skill should be used whenever users need help with resume creation, updating professional profiles, tracking career experiences, managing projects portfolio, or generating tailored resumes for job applications. On first use, extracts data from user's existing resume and maintains a structured database of experiences, projects, education, and skills. Generates professionally styled one-page PDF resumes customized for specific job roles by selecting only the most relevant information from the database.

This skill should be used whenever users ask food-related questions, meal suggestions, nutrition advice, recipe recommendations, or dietary planning. On first use, the skill collects comprehensive user preferences (allergies, dietary restrictions, goals, likes/dislikes) and stores them in a persistent database. All subsequent food-related responses are personalized based on these stored preferences.

Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.

Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment.