agentsclimarketplace

Docs & writing

16,621 rows, by stacks then stars

3,030 of these skill files have been read, by 1,951 distinct authors, and what they tell an agent counted. What Docs & writing authors agree on, and what they forbid

  • Release notes automation

    almasumdev/awesome-mobile-release-agent-skills/.github/skills/versioning/release-notes-automation Skill

    no license1★ repo

    Generate release notes from Conventional Commits with git-cliff, conventional-changelog, or release-please. Use this when automating the changelog and store release notes.

  • Adlc docs

    davidvictor/adlc-skills/skills/adlc/adlc-docs Skill

    1★ repo

    Audit and update documentation artifacts that explain shipped ADLC-relevant behavior.

  • Design system docs

    almasumdev/awesome-mobile-design-system-agent-skills/.github/skills/docs_and_tooling/design-system-docs Skill

    no license1★ repo

    Docs-as-code for design systems — Zeroheight, Storybook, DocC/DokkaHtml/dartdoc, and API reference. Use this when establishing or revising the documentation site.

  • Write prd

    niftymonkey/skills/skills/write-prd Skill

    1★ repo

    Create a PRD through user interview, codebase exploration, and module design, saved as a local markdown file with optional GitHub issue submission. Works for new projects, features, or refactors. Use when user wants to write a PRD, create a product requirements document, plan a new feature, or spec out a new project.

  • Refresh readme

    agentjido/jido-skills/source/skills/refresh-readme Skill

    1★ repo

    Refresh a repository README so it matches current package metadata, public APIs, examples, configuration, workflows, and validation commands. Use when README content is stale, incomplete, or inconsistent with code.

  • Sync docs to code

    agentjido/jido-skills/source/skills/sync-docs-to-code Skill

    1★ repo

    Audit and reconcile repository docs with current code, examples, module docs, configuration, Mix aliases, telemetry, workflows, and public APIs. Use when docs may be stale after code changes or before release.

  • One item per file

    pjankiewicz/skills/skills/one-item-per-file Skill

    1★ repo

    Use when writing or restructuring a non-trivial chunk of code (a module, a subsystem, an algorithm) and you want it precise, parallelizable, and maintainable — treat code as data. Enforces a three-phase authoring workflow — (1) define the data structures, (2) define the function signatures in terms of those structures so the skeleton compiles, (3) implement the functions — with strict one-item-per-file decomposition: every data structure in its own file, every free function in its own file, a module is a directory of those files. Because each item is isolated, implementations parallelize cleanly and related ones can be batched. Triggers on "scaffold this module", "write this subsystem", "one function per file", "split this big file", "types then functions", "make this parallelizable / maintainable", planning a feature with many functions. Skip for a one-line fix or a single cohesive 50-line function.

  • Grill with docs

    fbarrento/laravel-agent-kit/.agents/skills/grill-with-docs Skill

    no license1★ repo

    Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

    The same file is in 11 other repositories

  • Setup matt pocock skills

    fbarrento/laravel-agent-kit/.agents/skills/setup-matt-pocock-skills Skill

    no license1★ repo

    Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.

    The same file is in 15 other repositories

  • Write a skill

    fbarrento/laravel-agent-kit/.agents/skills/write-a-skill Skill

    no license1★ repo

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

    The same file is in 20 other repositories

  • Git conventions

    fbarrento/laravel-agent-kit/skills/git-conventions Skill

    no license1★ repo

    Canonical naming + message rules for commits, pull request titles, and branch names using Conventional Commits. Defines the shared type vocabulary (feat, fix, refactor, chore, docs, test, perf, build, ci, style, revert), subject grammar, body/footer format, co-author trailer, breaking-change marking, and issue references. Use when writing or reviewing a commit message, naming a PR, or naming a branch. Framework-agnostic — applies to any repo.

    The same file is in 1 other repository

  • Paper writer

    nianbaizy/grad-agent-kit/skills/paper-writer Skill

    1★ repo

    Reusable AI agent skills for research writing, experiment analysis, academic presentation, reviewer simulation, and project delivery.

  • Readme style

    coreline-ai/codex-devflow-plugin/skills/readme-style Skill

    1★ repo

    Redesign README.md files with modern GitHub styling — badges, icons, tables, ASCII diagrams, and anchor navigation. Use when asked to restyle, modernize, or redesign a README with shields.io badges, section icons, or visual improvements.

  • Unicorn testing

    andrey-learning-machines/swe-harness/plugins/swe-harness/skills/unicorn-testing Skill

    1★ repo

    Guides the user through test-first development and test strategy decisions. ALWAYS trigger on "write tests", "TDD", "test coverage", "mock", "test fails", "flaky test", "how to test", "unit test", "integration test", "e2e test", "test structure", "what to test", "test organization", "coverage report", "testing strategy", "arrange act assert". Use when writing new tests, choosing test types, setting up mocking, debugging flaky tests, improving coverage, or designing testable code. Different from qa-security agent which focuses on code review and security audits rather than test authoring.

  • Perfect docs

    scwlkr/skillsies/skills/perfect-docs Skill

    no license1★ repo

    Upgrade an existing software project into a mature, compact, modular, verified documentation system for humans and AI agents.

  • Docs audit

    scwlkr/skillsies/skills/perfect-docs/template/.agents/skills/docs-audit Skill

    no license1★ repo

    Reusable agent skills for docs, design, and repo cleanup.

    The same file is in 6 other repositories

  • Spring cleaning

    scwlkr/skillsies/skills/spring-cleaning Skill

    no license1★ repo

    Ruthlessly clean, consolidate, and standardize project documentation into a coherent user-manual path with canonical language, structure, formatting, and a verified active-docs audit.

  • Write a skill

    scwlkr/skillsies/skills/write-a-skill Skill

    no license1★ repo

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

    The same file is in 1 other repository

  • Create docs

    pavelsimo/skills/skills/create-docs Skill

    no license1★ repo

    Analyzes a codebase and generates LLM-optimized documentation covering project overview, architecture, build system, testing, development patterns, deployment, and a file catalog. Use when the user wants to document a codebase or refresh existing project documentation.

  • Markdown

    pavelsimo/skills/skills/markdown Skill

    no license1★ repo

    Converts files to Markdown using uvx markitdown, supporting PDF, Word, PowerPoint, Excel, HTML, images with OCR, audio with transcription, ZIP archives, and YouTube URLs. Use when the user wants to convert a file or URL to Markdown.

  • Grill with docs

    Soham407/studio-kickstart/architecture/grill-with-docs Skill

    1★ repo

    Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

    The same file is in 8 other repositories

  • Setup matt pocock skills

    Soham407/studio-kickstart/architecture/setup-matt-pocock-skills Skill

    1★ repo

    Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.

    The same file is in 15 other repositories

  • Write a skill

    Soham407/studio-kickstart/architecture/write-a-skill Skill

    1★ repo

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

    The same file is in 20 other repositories

  • Project docs cleanup

    mo-hawary/hawary-workflow-skills/skills/project-docs-cleanup Skill

    1★ repo

    Audit project docs for stale, duplicate, contradictory, or missing workflow artifacts before cleanup or handoff.

  • Release publisher

    skills-lock/example-claude-code-skills/.claude/skills/release-publisher Skill

    1★ repo

    Cut a new git tag, generate release notes from CHANGELOG.md, and publish via the GitHub API. Uses git, gh; calls api.github.com. Use when preparing a tagged release of this repository.

  • Cto weekly review

    hiteshbandhu/skills-i-use/skills/cto-weekly-review Skill

    1★ repo

    Generate a deep CTO self-review report: working hours, productivity patterns, focus sessions, AI collaboration depth, cognitive load signals, sustainability health, and codebase velocity — not just commit counts. Triggers on "weekly review", "CTO report", "week summary", "what did I build", "productivity report", "show me my week", "engineer report", "weekly digest". Scans git across repos, AI agent session logs, shell history, file timestamps, and produces markdown + HTML reports. Always trigger this skill for any weekly or periodic review of engineering or product work.

  • Spec grounded design

    hiteshbandhu/skills-i-use/skills/spec-grounded-design Skill

    1★ repo

    Before implementing against any protocol, SDK, or external API, ground the design in reality — pull the actual spec, probe the live endpoint to capture how it really behaves, reconcile spec-vs-reality (reality wins), and extract a design contract of verified facts, edge cases, and invariants to build against. Encodes "read the protocol" + "test live before assuming the spec is correct," because reverse-engineered or stale docs lag the real API. Triggers on "integrate with X", "design against this API", "read the protocol first", "before we build this integration", "is the spec right", "how does this API actually behave", "ground this in the docs", "verify before coding". Use before writing integration code against an external system, not for internal logic.

  • Skill creator

    zrosenbauer/skills/skills/skill-creator Skill

    1★ repo

    This skill should be used when the user wants to create a new agent skill, scaffold a SKILL.md, validate an existing skill against repo rules, or refactor a skill to match this monorepo's conventions. Common triggers include "build a skill for X", "create a new skill", "scaffold a skill", "add a skill that does Y", "make me a skill", "audit this skill against our rules", and "refactor this skill to match repo conventions". Enforces kebab-case naming, verbatim trigger phrases, and selective XML for example boundaries. Skip when modifying source code, debugging an existing skill, or writing non-skill markdown.

  • Ts best practices

    zrosenbauer/skills/skills/ts-best-practices Skill

    1★ repo

    This skill should be used when the user wants to write, review, or refactor TypeScript code to follow industry best practices. Common triggers include "follow ts best practices", "review this typescript", "fix the typescript style", "make this idiomatic typescript", "apply typescript conventions", and "audit this ts file". Bakes in branded types, discriminated unions, ts-pattern for multi-branch logic, JSDoc on exports, kebab-case file naming, and *Params/*Options object-arg conventions. Skip when the user wants pure functional refactors (use ts-best-practices-functional) or is writing framework components (React/Vue/Svelte have different conventions).

  • Humanizer

    mattdweigand-sketch/agent-skills/skills/humanizer Skill

    1★ repo

    Remove signs of AI-generated writing and fix clarity failures in text. Use when editing or reviewing any prose to make it sound natural and human-written: emails, posts, docs, READMEs, specs, reports. Detects AI tells (inflated significance, promotional language, -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary, copula avoidance, negative parallelism, filler, hedging) and runs a clarity pass for problems that survive a clean scan: redundant structure, abstract claims with no example, wrong framing, backwards information order.

  • Crash reporting strategy

    almasumdev/awesome-mobile-agent-skills/.github/skills/operations/crash-reporting-strategy Skill

    no license1★ repo

    Crash reporting for mobile - symbolication, SLOs, tagging, triage workflow, and comparing Crashlytics, Sentry, Bugsnag, Firebase, and native (APM) reporters. Use when setting up or improving crash reporting.

  • Grill with docs

    merllinsbeard/merlin-skills/skills/grill-with-docs Skill

    1★ repo

    Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

    The same file is in 11 other repositories

  • Project tracking

    Yesterday-AI/skills/plugins/personal-agent/skills/project-tracking Skill

    1★ repo

    Standardisiertes Projekt-Tracking für Yesterday KI-Agenten. Use when: setting up a new agent workspace, responding to a status request from another agent or a human team member, or aggregating fleet-wide project status. Covers: PROJECTS_TRACKING.md structure, YAML frontmatter, responsibility matrix, status definitions, and the Project Status Report format.

  • Decision memo

    stephenrogan/leadership-skills/skills/decision-memo Skill

    1★ repo

    Creates a concise decision memo with context, decision required, options, tradeoffs, assumptions, dissent, recommendation, owner, and revisit criteria. Use when a leadership decision has ambiguity, cross-functional impact, material risk, or is likely to be reopened later.

  • Commit message

    kin0992/dev-toolkit/packages/skills/src/git/commit-message Skill

    1★ repo

    **UTILITY SKILL** - Generate a classic Git commit message from a staged diff. USE FOR: write commit message, generate commit message from diff, summarize staged changes, create commit text, compose git commit. DO NOT USE FOR: generating PR descriptions (use pr-title-description), writing changelog entries, conventional commits format. INVOKES: git diff --staged for reading staged changes. FOR SINGLE OPERATIONS: Use git commit -m directly for trivial one-liners.

  • Pr title description

    kin0992/dev-toolkit/packages/skills/src/git/pr-title-description Skill

    1★ repo

    **UTILITY SKILL** - Generate a pull request title and description from a branch diff. USE FOR: write PR description, generate pull request title, summarize branch for reviewers, create PR body from commits, draft pull request. DO NOT USE FOR: writing commit messages (use commit-message skill), code review feedback, changelog generation. INVOKES: git log and git diff for reading branch changes, file reading for PR templates. FOR SINGLE OPERATIONS: Use git log --oneline directly for a quick branch summary.

  • Flutter localization

    almasumdev/awesome-flutter-agent-skills/.github/skills/ui/flutter-localization Skill

    no license1★ repo

    Setup Flutter localization with flutter_localizations, ARB files, intl plurals/genders/dates, RTL support, and dynamic locale switching. Use this when adding or auditing i18n.

  • Update documentation

    barseghyanartur/dot-agents/skills/update-documentation Skill

    1★ repo

    Keep project documentation aligned with code by detecting and auto-fixing mismatches using agent-based analysis.

  • Human ai research

    imnotdev25/skills/human-ai-research Skill

    no license1★ repo

    Drives a HUMAN-LED, multi-stage research workflow (ideation -> literature review -> problem framing & novelty -> hypothesis & planning -> experimentation -> validation -> reporting) in which Claude acts strictly as an implementation engine while the researcher does the thinking. Use this whenever the user wants to start, structure, or advance a research project, paper, thesis chapter, or study. Trigger it for things like "I have a research idea", "help me frame this", "find / screen papers on X", "write a problem statement", "is this novel?", "help me design an experiment", or "let's write a paper" -- and especially when the user wants a rigorous, fully provenance-tracked process rather than a quick answer. The skill keeps a workspace where every link, term, assumption, inference, and decision is written down as it happens, and it counter-questions the user instead of thinking for them. This is the opposite of an autonomous "AI scientist": the human owns every intellectual commitment; Claude owns retrieval, structuring, bookkeeping, drafting scaffolds, and running tools.

  • Documentation and adrs

    Xrenya/safe-agent-skills/skills/documentation-and-adrs Skill

    1★ repo

    Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

    The same file is in 11 other repositories

  • Audit docs

    bmaltais/skills/audit-docs Skill

    no license1★ repo

    Audit a codebase's documentation (README, SKILL.md, AGENTS.md, etc.) for gaps against the actual implementation. Finds undocumented commands, flags, config fields, and behaviors. Use when a feature has landed but docs weren't updated, after a session where docs drift was discovered, or as a pre-release check.

  • Grill with docs

    bmaltais/skills/grill-with-docs Skill

    no license1★ repo

    A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

    The same file is in 19 other repositories

  • Markdown

    bmaltais/skills/markdown Skill

    no license1★ repo

    Comprehensive Markdown best practices and formatting rules, aligned with markdownguide.org, markdownlint, and CommonMark spec 0.31.2. Use when writing or reviewing Markdown files. Trigger on phrases like "format this markdown", "markdown best practices", "fix my markdown", "lint markdown", "markdown style".

  • Plan

    bmaltais/skills/plan Skill

    no license1★ repo

    Plan mode for Hermes — inspect context, write a markdown plan into the active workspace's `.hermes/plans/` directory, and do not execute the work.

  • Powershell

    bmaltais/skills/powershell Skill

    no license1★ repo

    PowerShell cmdlet and scripting best practices based on Microsoft guidelines. Use when writing or reviewing PowerShell scripts (.ps1, .psm1). Trigger on phrases like "write a PowerShell function", "review my script", "PowerShell best practices", "cmdlet design", "PS1 style".

  • Terraform module change

    bmaltais/skills/terraform-module-change Skill

    no license1★ repo

    End-to-end workflow for making a change to an existing Terraform module resource: fetch provider docs, implement the change, write a pure-logic tftest fixture (no provider credentials needed), wire test discovery via Makefile, run the full validation cycle (terraform test → fmt → tflint), and update RELEASE_NOTES.md. Use when the user asks to add, update, or fix an argument on an existing Terraform resource, add a new behaviour to an existing resource block, ensure a resource re-syncs on upstream changes, or "update X to use the new Y argument". Trigger on phrases like "update this resource to use", "add X to my terraform resource", "ensure sync when", "how do I make terraform detect changes in", "update my tf code for provider version X", "write tests for this tf change". DO NOT use for: scaffolding new modules (use terraform-caf-azurerm-module), full provider version upgrades across a module (use eslz-module-upgrade), or pure validation runs without code changes (use terraform-validation-workflow).

  • Writing plans

    NjoyimPeguy/augments/plugins/augments/skills/writing-plans Skill

    1★ repo

    Use when approved requirements or a clearly multi-step task need an executable per-task plan before implementation. High-risk target-work planning requires current approved migration and assurance contracts. A plan limited to explicitly authorized gate-enabling prerequisites may consume the exact proposed owning gate contract, but cannot include target work. Skip single-step or trivial work.

  • Writing skills

    NjoyimPeguy/augments/plugins/augments/skills/writing-skills Skill

    1★ repo

    Use when creating or editing a skill in this library — the lean format, progressive disclosure, and how to prove a skill works. For AUTHORING skills, not using them.

  • Writing skills

    NjoyimPeguy/augments/skills/common/writing-skills Skill

    1★ repo

    Use when creating or editing a skill in this library — the lean format, progressive disclosure, and how to prove a skill works. For AUTHORING skills, not using them.

  • Writing plans

    NjoyimPeguy/augments/skills/design/writing-plans Skill

    1★ repo

    Use when approved requirements or a clearly multi-step task need an executable per-task plan before implementation. High-risk target-work planning requires current approved migration and assurance contracts. A plan limited to explicitly authorized gate-enabling prerequisites may consume the exact proposed owning gate contract, but cannot include target work. Skip single-step or trivial work.

  • Migrate docs

    RubenGlez/harness/skills/migrate-docs Skill

    1★ repo

    Discover all documentation in the repo, classify each file, transform content to match harness templates, and migrate everything to the correct location. Also adopts doctier encrypted tracking for .harness/ on pre-doctier harness projects. Use on any existing project to adopt the harness workflow without starting from scratch.

  • Qa

    RubenGlez/harness/skills/qa Skill

    1★ repo

    Test implemented features against their acceptance criteria, fix simple failures, and write a QA report. Use after implement has finished a phase, or when you want to verify that implemented features work as specified.

  • Update docs

    RubenGlez/harness/skills/update-docs Skill

    1★ repo

    Update all project documentation to reflect the current state of the codebase. Use after finishing a feature, refactor, or any meaningful change — or whenever docs feel stale.

  • Write a skill

    RubenGlez/harness/skills/write-a-skill Skill

    1★ repo

    Create new harness skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

  • Readme polish

    montgomeryunpopular607/anywhere-agents/packages/pypi/anywhere_agents/composer/skills/readme-polish Skill

    1★ repo

    Audit a GitHub README and rewrite it using modern 2025-2026 patterns — centered header, badges, hero image, GitHub alert callouts, emoji-prefixed features, expandable details, Mermaid diagrams, tables over dense prose. Produces a scannable README that works for a 10-second skim and a deep dive.

    The same file is in 1 other repository

  • Readme polish

    montgomeryunpopular607/anywhere-agents/skills/readme-polish Skill

    1★ repo

    Audit a GitHub README and rewrite it using modern 2025-2026 patterns — centered header, badges, hero image, GitHub alert callouts, emoji-prefixed features, expandable details, Mermaid diagrams, tables over dense prose. Produces a scannable README that works for a 10-second skim and a deep dive.

    The same file is in 1 other repository

  • Skill writer

    wenjiazhu1980/deepcode-macos/packages/core/templates/skills/bundled/skill-writer Skill

    1★ repo

    Guide users through creating, updating, debugging, and validating Agent Skills for AI agents. Use when the user wants to create, write, author, design, troubleshoot, validate, or improve a Skill, or needs help with SKILL.md, frontmatter, or skill structure.

  • Engineering paper coach

    169884902hzl/engineering-paper-skills/skills/engineering-paper-coach Skill

    1★ repo

    Use for a lightweight, conservative first pass on engineering paper writing, manuscript audit, paragraph repair, claim-bound polishing, reviewer-response planning, or readiness triage when the user wants practical Markdown guidance rather than a structured JSON benchmark. Best for robotics, machine learning, control, and systems papers with partial author evidence.

  • Engineering writing

    169884902hzl/engineering-paper-skills/skills/engineering-writing Skill

    1★ repo

    Draft, restructure, or plan English engineering research paper sections from author-provided claims, methods, results, figures, notes, outlines, LaTeX files, or manuscript drafts. Use for section logic, contribution-evidence mapping, abstract/introduction/related-work/methods/experiments/discussion/conclusion drafting, and evidence-bounded manuscript prose. Do not use for pure language polishing, figure/table-only work, reviewer responses, or final build/readiness validation unless the user explicitly asks for those workflows.

  • Pitch deck evaluator

    thevibethinker/vibe-thinker-skills/pitch-deck-evaluator Skill

    no license1★ repo

    Evaluate early-stage pitch decks across four investor credulity frames, stage-aware substantive rubric dimensions, optional named-POV reads, and markdown/JSON report rendering.