write-readme
Write or critique a README for an open-source project (library or CLI tool) using the inverted-pyramid structure — concrete value first, install second, explanation third, reference last. Use when the user asks to "write a README", "draft a README", "review my README", "improve my README", or starts a new lib/tool and needs documentation. Do NOT use for internal service docs, monorepo root READMEs, or non-public projects.
What this skill does
# write-readme
Produce a README that answers the reader's questions in the order they actually ask them: *why care → how to install → what it does → how it works → what if it breaks.*
## Quick start
Ask one question, then draft:
> "Is this a **library** (imported as a dependency) or a **tool/CLI** (run directly)?"
The answer changes the lead section and the template. See [REFERENCE.md](REFERENCE.md) for full templates.
## Steps
1. **Classify** — lib or tool? When unclear, ask. This determines the reader's first question and the README's opening frame.
2. **Find the lead metric** — one line of concrete numbers before any prose description. If the project has no benchmark yet, use the sharpest qualitative differentiator ("zero dependencies", "100% local", "single binary"). Never lead with "A library that…"
Then find the **domain trust signal**: the one anxiety your tool's category triggers in readers. Data tools: "does this phone home?" → answer with "100% local". Build tools: "will this break my pipeline?" → answer with "reproducible, hermetic". Hot-path libs: "does this allocate?" → answer with "zero alloc". Surface the trust signal in the opening, not in a footnote.
3. **Draft in inverted-pyramid order** — most newsworthy first, reference material last. A reader who stops after two sections should still have a complete, useful picture.
4. **Apply the matching template** from [REFERENCE.md](REFERENCE.md). Fill every section; delete a section only if it truly has nothing to say (not to save space).
5. **Run the checklist** at the bottom of [REFERENCE.md](REFERENCE.md) before handing off.
## Non-negotiables
- Install/quickstart comes **before** the explanation of why it works.
- Benchmarks and capability claims need a methodology note — even one sentence. Claims without method are marketing.
- Admit where the tool **doesn't** help — and give it a **heading**, not a parenthetical. A named limitation ("Estimate Accuracy", "Not for X") reads as honest engineering; a buried caveat reads as defensive marketing.
- When claiming broad support (platforms, formats, languages), **name the things**: list them explicitly. "Supports 15+ tools" is a count; "Claude Code, Codex, Cursor…" is evidence.
- Troubleshooting lives in the README, not "open an issue".
- `<details>` for depth: advanced config, raw data, alternative setup. The happy path must be scannable without expanding anything.
See [REFERENCE.md](REFERENCE.md) for templates, badge patterns, and the full checklist.
Related in Code Review
gstack
IncludedFast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
startup-due-diligence
IncludedLegal due diligence review for seed-stage and Series A startups (US, Delaware C-Corp focus). Supports both investor and founder perspectives. Capabilities include: (1) Interactive document review and issue spotting; (2) Document request list generation; (3) Cap table and SAFE/convertible note analysis; (4) Red flag identification with severity ratings; (5) Diligence report generation. TRIGGERS: due diligence, DD, startup investment, cap table review, Series A, seed round, investor diligence, legal review startup, SAFE analysis, convertible note, 409A, founder vesting.
interview-master
IncludedThis skill should be used when the user asks to "generate interview questions", "prepare for interview", "optimize resume", "conduct mock interview", "analyze git commits for resume", "generate resume from code", "review my resume", or mentions interview preparation, career assistance, or extracting project experience from git history. Provides comprehensive interview and career development guidance for both job seekers and interviewers.
fix-issue
IncludedFixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.
sf-apex
IncludedGenerates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.
swift-development
IncludedComprehensive Swift development for building, testing, and deploying iOS/macOS applications. Use when Claude needs to: (1) Build Swift packages or Xcode projects from command line, (2) Run tests with XCTest or Swift Testing framework, (3) Manage iOS simulators with simctl, (4) Handle code signing, provisioning profiles, and app distribution, (5) Format or lint Swift code with SwiftFormat/SwiftLint, (6) Work with Swift Package Manager (SPM), (7) Implement Swift 6 concurrency patterns (async/await, actors, Sendable), (8) Create SwiftUI views with MVVM architecture, (9) Set up Core Data or SwiftData persistence, or any other Swift/iOS/macOS development tasks.