The bottleneck on a solo founder is not code. It is everything that surrounds the code — the idea that has not been pressure-tested yet, the PRD that lives in your head, the runway spreadsheet you keep meaning to update, the first ten customer-discovery emails you never sent, the onboarding flow that loses every other signup, and the support inbox that piles up the week you ship. The skills below cover that surface area. They are the ones a one-person company should install before writing a line of product code: a YC-style brainstorm partner, a founder-mode plan reviewer, a PRD generator, a spreadsheet co-pilot for the runway and pricing math, a cold-email writer for customer discovery, a customer-success playbook builder for onboarding and churn, and a support-handler skill so the first ten tickets do not eat a Tuesday. All from verified plugins with real commit history and real star counts on GitHub.
From the gstack plugin (101,054 stars). Two modes: Startup mode runs six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode is a design-thinking brainstorm for side projects, hackathons, and open source. Either mode ends with a saved design doc. The skill is invoked proactively any time you describe a new product idea or ask whether something is worth building, which is the exact moment a solo founder needs a second brain in the room and does not have one.
When to use: before any code is written, the first time you can articulate the idea in a paragraph, and any time you catch yourself defending the idea instead of stress-testing it. Run it before plan-ceo-review below — office hours frames the problem, the CEO review pressure-tests the solution. Pair it with the Founders persona collection for the rest of the early-stage stack.
Also from gstack. Founder-mode plan review: rethink the problem, find the 10-star product, challenge premises, expand scope when expansion makes the product better and contract when it does not. Four modes — SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope and cherry-pick expansions), HOLD SCOPE (maximum rigor on what is already in), SCOPE REDUCTION (strip to essentials). For a solo founder the most common failure mode is shipping the obvious product instead of the right one; this skill makes you sit with the alternatives long enough to notice.
When to use: after a first draft of any product plan, before committing to a sprint, and the next time you catch yourself saying "good enough for v1" about a feature that defines the product. Run it after office-hours has clarified the problem and before you open a PRD. Pair it with the lightweight backend-engineer skill stack for when the v1 implementation begins — the same skills work, the reviewer just becomes the team.
From the myclaude plugin (2,669 stars). An interactive Product Owner skill for requirements gathering, analysis, and PRD generation. It uses quality scoring and iterative dialogue to make sure the requirements are actually comprehensive before it writes the PRD — the failure mode it prevents is the one-page PRD that looks complete and turns into a four-week build because nothing about state, errors, or empty states was specified. For a solo founder who is going to implement the PRD themselves the next morning, that gap is the difference between a clean week and a rewrite.
When to use: the moment plan-ceo-review says the scope is right, before you open the editor, and again whenever you find yourself re-deciding a requirement mid-implementation (a signal the PRD was incomplete). The skill is also worth running over an existing feature you are about to extend, as a forcing function to write down the requirements that were always implicit.
From the flagship skills plugin (139,553 stars). Opens, reads, edits, and creates spreadsheets — adding columns, computing formulas, formatting, charting, cleaning messy data, converting between tabular formats. For a solo founder the spreadsheet is the operating system: runway model, pricing scenarios, cohort retention, ad-spend tracker, the contact list of every investor you have ever emailed. The skill removes the friction of opening Excel for the tenth small change of the week and lets the spreadsheet stay an asset rather than a chore.
When to use: any time the runway model is more than two weeks stale, when you need to model three pricing options before a customer call, when ad-platform CSVs need to be reconciled with Stripe payouts, and when investor outreach has outgrown a Notion page. Pair it with the Data category for the rest of the founder analytics stack, and with the plan-ceo-review above so the scenarios in the spreadsheet feed back into the plan instead of living in a parallel universe.
From the agent-skills plugin (21 stars). Writes cold emails that get replies using proven frameworks (AIDA, PAS, BAB), and enforces best practices like the 50-125 word limit and a personalized opener. For a solo founder doing customer discovery, the cold email is the single highest-leverage atom of work: ten good emails will tell you more about the market than ten weeks of building. The skill removes the excuse — there is no longer a 30-minute warm-up cost to write the first one, so you actually send them.
When to use: the week after office-hours when you have a wedge and need to talk to ten people in it, before any landing page or product is built, and on the recurring cadence (five outbound a day, every day) that turns customer discovery into a habit instead of a project. Pair it with a tracking sheet built via the xlsx skill above so reply rates by opener and by segment become signal you can act on.
From the claude-skills plugin (12 stars). Builds customer-success playbooks — onboarding flows, health scoring, QBR templates, churn intervention plans. The skill is sized for a solo founder: it produces the artifact you would otherwise hire a CS lead to build, and it produces it in a form you can run yourself for the first hundred customers without dedicated tooling. The onboarding flow alone — the email sequence, the in-product checkpoints, the day-three check-in — is where most solo founders leak the customers they spent a month acquiring.
When to use: the day after the first paying customer, before activation rates settle into a number you cannot move, and any time churn starts climbing without an obvious cause (the health-scoring playbook will usually find the cause faster than your gut will). Pair it with the support-handler skill below so the support tickets feed back into onboarding improvements instead of disappearing into the inbox.
Also from claude-skills. Writes support responses — ticket triage, empathetic replies, escalation paths, and macro templates. The reason this matters for a solo founder is not the time saved on any one ticket; it is the difference between a support inbox that compounds (every ticket becomes a macro, every macro covers the next ten tickets, the inbox quietly empties on its own) and one that drowns you (every ticket is bespoke, every Tuesday is gone). The skill enforces the macro habit by default.
When to use: from the first ticket, before patterns have set in, and as a one-time retrofit over the last 30 days of tickets to extract the macros you should have been writing all along. Pair it with the customer-success skill above (recurring ticket categories are usually onboarding gaps) and with the content-creator stack when you start turning the macros into public help-center articles.
How to install
Each skill lives inside a plugin. Add the plugin marketplace once, then install with a single command. The skill detail page on Skill Index has the exact install string and a copy button.
If you are starting a one-person company in 2026, the highest-ROI first install is the gstack plugin (you get office-hours and plan-ceo-review together — the brainstorm partner and the plan reviewer that replace a co-founder on the strategic side), then myclaude/product-requirements so every feature has a PRD before the editor opens, then the skills plugin for xlsx (runway, pricing, every spreadsheet you keep meaning to update) and the rest of the Anthropic-maintained set, then agent-skills/cold-email the week customer discovery starts, and finally claude-skills/customer-success and claude-skills/support-handler the day the first paying customer lands. Pair the output with the rest of the thicket toolkit — quick reference screenshots via capture.thicket.sh, QR codes on launch-day landing pages via qr.thicket.sh, and timeboxed deep-work blocks via focus.thicket.sh — and the gap between "I had an idea" and "I have ten paying customers" stops being the founder bottleneck and starts being a week-by-week sequence you can actually run.