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

  • Google style javascript

    sanjeevafk/agent-skills/skills/google-style-javascript Skill

    0★ repo

    Apply Google's official JavaScript style guide when writing, reviewing, formatting, or linting JavaScript code. Use this skill whenever the user asks to review JavaScript for style, asks about JS naming conventions, module syntax, var vs let vs const, string formatting, JSDoc comments, or whether code follows Google JS conventions. Also triggers on: "clean up this JavaScript", "is this good JS?", "how do I format this JS function?", "should I use arrow functions here?", "how do I write JSDoc?", "what's the Google way to handle this in JS?". Note: for TypeScript (.ts/.tsx files) use google-style-typescript instead — this skill covers .js and .mjs files.

  • Google style python

    sanjeevafk/agent-skills/skills/google-style-python Skill

    0★ repo

    Apply Google's official Python style guide when writing, reviewing, formatting, or linting Python code. Use this skill whenever the user asks to review Python code for style, wants to know how Google formats Python, asks about docstring format, import ordering, type annotations, naming conventions, or whether something is idiomatic Python by Google standards. Also triggers on: "is this good Python?", "clean up this Python file", "how should I name this variable/function/class in Python?", "does this follow PEP 8 / Google style?", "how do I write a docstring?", or any request involving pylint, pyink, or Black in a Google-style context.

  • Interview style doc building

    sanjeevafk/agent-skills/skills/interview-style-doc-building Skill

    0★ repo

    Use when the user wants to build a structured strategic document by answering questions (life priorities, goals docs, framework files, ranked lists, principles, reviews). Interview one question at a time, patch the file after each answer, then re-ask. Not for day planning (use day-plan).

  • Grill with docs

    sanjeevafk/agent-skills/skills/mattpocock/grill-with-docs Skill

    0★ 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

    sanjeevafk/agent-skills/skills/mattpocock/setup-matt-pocock-skills Skill

    0★ 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

  • Documentation

    mj-deving/pai-skills/skills/Documentation Skill

    no license0★ repo

    Documentation practices — comment guidelines, ADR conventions, API documentation, inline docs philosophy, doc health scanning and maintenance. USE WHEN documentation, write docs, comment guidelines, ADR, architecture decision, API docs, JSDoc, OpenAPI, document code, when to comment, how to document, self-documenting code, README, doc health, doc drift, stale docs, fix docs, doc maintenance, check docs.

  • GitWorkflow

    mj-deving/pai-skills/skills/GitWorkflow Skill

    no license0★ repo

    Git workflow and versioning — atomic commits, save point pattern, worktrees for parallel agents, commit conventions, change summaries. USE WHEN git workflow, commit strategy, branching, git conventions, commit message, worktree, parallel work, save point, git bisect, version control, how to commit, when to commit, split commits, act, local actions, test workflow, git-cliff, changelog, release notes.

  • ProjectTelos

    mj-deving/pai-skills/skills/ProjectTelos Skill

    no license0★ repo

    Project-only Telos context mapping for goals, constraints, stakeholders, decisions, dependencies, risks, and narrative reports. Use when analyzing a project, building a project context pack, mapping dependencies, writing an executive project brief, or creating a non-personal project dashboard/report.

  • TDD

    mj-deving/pai-skills/skills/TDD Skill

    no license0★ repo

    Test-driven development — RED/GREEN/REFACTOR cycle, Prove-It Pattern for bugs, test pyramid, coverage strategy. USE WHEN writing tests, TDD, test strategy, prove-it pattern, test pyramid, bug fix testing, test coverage, test-first, write tests, add tests, test plan, testing approach, regression test, coverage checklist.

  • Documents

    mj-deving/pai-skills/skills/Utilities/Documents Skill

    no license0★ repo

    Read, write, convert, and analyze documents — routes to PDF, DOCX, XLSX, PPTX sub-skills for creation, editing, extraction, and format conversion. USE WHEN document, process file, create document, convert format, extract text, PDF, DOCX, XLSX, PPTX, Word, Excel, spreadsheet, PowerPoint, presentation, slides, consulting report, large PDF, merge PDF, fill form, tracked changes, redlining.

  • Typst

    mj-deving/pai-skills/skills/Utilities/Typst Skill

    no license0★ repo

    Professional PDF document creation via Typst — CVs, cover letters, reports, proposals, invoices, technical docs, academic papers, flyers, posters, brochures. USE WHEN create PDF, generate PDF, make PDF, CV, resume, cover letter, application letter, report PDF, proposal, invoice, technical document, academic paper, typst, format as PDF, export PDF, professional document, letter, letterhead, flyer, poster, brochure, handout, leaflet, marketing print, print design.

  • N8n code javascript

    mj-deving/pai-skills/skills/Utilities/n8n/n8n-code-javascript Skill

    no license0★ repo

    Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, choosing between Code node modes, or doing any custom data transformation in n8n. Always use this skill when a workflow needs a Code node — whether for data aggregation, filtering, API calls, format conversion, batch processing logic, or any custom JavaScript. Covers SplitInBatches loop patterns, cross-iteration data, pairedItem, and real-world production patterns.

    The same file is in 1 other repository

  • N8n code python

    mj-deving/pai-skills/skills/Utilities/n8n/n8n-code-python Skill

    no license0★ repo

    Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes. Use this skill when the user specifically requests Python for an n8n Code node. Note — JavaScript is recommended for 95% of use cases — only use Python when the user explicitly prefers it or the task requires Python-specific standard library capabilities (regex, hashlib, statistics).

    The same file is in 2 other repositories

  • Graphify

    mj-deving/pai-skills/skills/graphify Skill

    no license0★ repo

    any input (code, docs, papers, images) - knowledge graph - clustered communities - HTML + JSON + audit report

  • Session closer

    fbsmna-coder/karpathy-pro-max/skills/session-closer Skill

    0★ repo

    End every work session with an honest status report — what shipped, what didn't, what's blocked. Use at the end of any non-trivial work session to prevent silent loss of context, false claims of completion, and undocumented blockers.

  • Conventional commits

    narenaryan/agent-skills/skills/git/conventional-commits Skill

    0★ repo

    Use when writing or validating Conventional Commits v1.0.0 messages — choosing between `!` and `BREAKING CHANGE:` footer, formatting git-trailer footers (Token-with-dashes vs `BREAKING CHANGE`), scope syntax, mapping types to SemVer bumps, prepending gender-neutral gitmoji-style icons (feat ⚡ / fix 🐛 / refactor ♻️ / docs 📝), or handling revert/multi-paragraph body rules

  • Field report

    frodo2647/triptych/.claude/skills/field-report Skill

    0★ repo

    User-controlled feedback to the Triptych maintainer. Mines the current session for context, sanitizes locally, drafts a GitHub issue body, asks the user to review the full draft, and only on explicit approval submits via gh issue create. Use when the user says "/field-report", "send feedback", "report a bug to maintainer", "tell the team about this," or wants to share a missing-skill / new-use-case observation. NEVER auto-invoked; user-only trigger.

  • Peer review

    frodo2647/triptych/.claude/skills/peer-review Skill

    0★ repo

    Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.

    The same file is in 4 other repositories

  • Scientific writing

    frodo2647/triptych/.claude/skills/scientific-writing Skill

    0★ repo

    Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.

    The same file is in 3 other repositories

  • Spec writer

    antonioshaman/aura-companion/.agents/skills/spec-writer Skill

    0★ repo

    Generate structured software specifications for features, bug fixes, and products. Use when the user wants to create a spec, PRD, feature brief, requirements document, or when starting any new implementation that needs a specification first. Invoke via /spec-writer or when the user says "write a spec", "spec this out", "create a spec", "I need a spec for...", or describes a feature they want to build. Produces adaptive-complexity specs with Job Stories, Gherkin acceptance criteria, and three-tier boundaries. Output is a markdown file ready for agent execution or human review.

  • Create readme

    scikrikci/skills/skills/create-readme Skill

    no license0★ repo

    Create a README.md file for the project

    The same file is in 3 other repositories

  • Readme blueprint generator

    scikrikci/skills/skills/readme-blueprint-generator Skill

    no license0★ repo

    Intelligent README.md generation prompt that analyzes project documentation structure and creates comprehensive repository documentation. Scans .github/copilot directory files and copilot-instructions.md to extract project information, technology stack, architecture, development workflow, coding standards, and testing approaches while generating well-structured markdown documentation with proper formatting, cross-references, and developer-focused content.

    The same file is in 1 other repository

  • Research pruning pre prune

    stevennitesh/programming-agent-skills/docs/validation/evals/research-pruning-pre-prune Skill

    0★ repo

    Research or investigate one bounded source question using primary or governing sources and return a citation-verified answer, conflict, or blocker. Use for an explicit source-research request, an authorized repo-local research note, explicit `$research`, or a complete caller packet. Write at most one repo-local Markdown note; otherwise return cited inline evidence without changing tracked state. Ordinary lookup stays outside this skill.

  • Writing great skills pruning pre prune

    stevennitesh/programming-agent-skills/docs/validation/evals/writing-great-skills-pruning-pre-prune Skill

    0★ repo

    Create or edit canonical Codex skill behavior; audit or review skill semantics; or test whether skill wording changes behavior. Use when the request turns on invocation, ownership, context loading, leading words, pruning, or completion; exclude general prompt rewriting, ordinary code review, plugin scaffolding, and post-edit delivery.

  • Grill with docs

    stevennitesh/programming-agent-skills/skills/custom/grill-with-docs Skill

    0★ repo

    Use when a request combines grilling one repo-backed decision with keeping its domain language, invariants, or relationships current; exclude conversation-only grilling and settled-domain-only work.

  • Writing great skills

    stevennitesh/programming-agent-skills/skills/custom/writing-great-skills Skill

    0★ repo

    Create or edit canonical Codex skill behavior; audit or review skill semantics; or test whether skill wording changes behavior. Use when the request turns on invocation, ownership, context loading, leading words, pruning, or completion; exclude general prompt rewriting, ordinary code review, plugin scaffolding, and post-edit delivery.

  • Skill writing best practices

    lazuee/agent-skills/skills/skill-writing-best-practices Skill

    0★ repo

    Guidelines for creating AI agent skills. Use when writing new skills, documenting coding patterns, or reviewing skill files. Triggers when creating or modifying files in the skills/ directory.

  • Translation editorial

    dzhokhov/markdown-agent-vault/skills/translation-editorial Skill

    0★ repo
  • Bumpversion changelog stamp release

    kjuhwa/skills-hub/skills/agents/bumpversion-changelog-stamp-release Skill

    0★ repo

    Finalize a release by stamping the changelog, running bumpversion across all tracked files, and creating a signed tag — without pushing.

  • Draft release notes from git log

    kjuhwa/skills-hub/skills/agents/draft-release-notes-from-git-log Skill

    0★ repo

    Keep a non-destructive [Unreleased] changelog draft in sync with the actual diff since the last tag, using git log + GitHub's generate-notes API.

  • Llm json extraction

    kjuhwa/skills-hub/skills/ai/llm-json-extraction Skill

    0★ repo

    Robustly extract a JSON object from free-form LLM text output — strip markdown fences, locate outermost braces, tolerate prelude/postlude prose.

  • Openapi to mcp tag grouping

    kjuhwa/skills-hub/skills/ai/openapi-to-mcp-tag-grouping Skill

    0★ repo

    Convert OpenAPI specs into MCP tools by grouping operations under their OpenAPI tag, exposing one tool per tag with an operation selector and per-operation arguments.

  • Document converter priority registry

    kjuhwa/skills-hub/skills/architecture/document-converter-priority-registry Skill

    0★ repo

    Pluggable converter registry where each candidate declares a numeric priority, registrations are prepended, and dispatch re-sorts stably per call so the most recently registered converter at a priority wins.

  • Changelog compaction tombstone retention

    kjuhwa/skills-hub/skills/backend/changelog-compaction-tombstone-retention Skill

    0★ repo

    State-backend changelog topics need tombstone retention longer than compaction interval to survive consumer rebalance gaps.

  • Dry run confirm retry write flow

    kjuhwa/skills-hub/skills/backend/dry-run-confirm-retry-write-flow Skill

    0★ repo

    [Backend] 트래커/외부 API 쓰기 작업에 적용하는 공통 플로우: 미리보기 → 사용자 확인 → 쓰기 → 재시도.

  • Springdoc yaml externalization

    kjuhwa/skills-hub/skills/backend/springdoc-yaml-externalization Skill

    0★ repo

    Move long `@Operation description` and `@RequestBody examples` text out of Spring controllers into per-controller YAML files under `resources/api-docs/`, injected at runtime via a single `OperationCustomizer` bean. Swagger UI output unchanged.

  • Readme auto toc with markers

    kjuhwa/skills-hub/skills/build-tooling/readme-auto-toc-with-markers Skill

    0★ repo

    Use HTML comment markers (`<!-- BEGIN AUTO GENERATED X -->`/`<!-- END AUTO GENERATED X -->`) to carve mutable regions inside README.md and regenerate them idempotently from source of truth.

  • Document release

    kjuhwa/skills-hub/skills/cli/gstack/document-release Skill

    0★ repo

    Post-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when asked to "update the docs", "sync documentation", or "post-ship docs". Proactively suggest after a PR is merged or code is shipped. (gstack)

  • Ipynb cells to markdown

    kjuhwa/skills-hub/skills/data-pipeline/ipynb-cells-to-markdown Skill

    0★ repo

    Convert a Jupyter notebook JSON (.ipynb) into a single markdown document — markdown cells passed through, code cells wrapped in ```python fences, raw cells in bare fences, title auto-detected from first H1 or notebook metadata.

  • Zip recursive subdocument conversion

    kjuhwa/skills-hub/skills/data-pipeline/zip-recursive-subdocument-conversion Skill

    0★ repo

    Convert a ZIP archive to a single combined markdown document by iterating entries, constructing per-entry StreamInfo from filename+extension, and recursing through the same converter registry for each entry.

  • Reverse document

    kjuhwa/skills-hub/skills/design/reverse-document Skill

    0★ repo

    Generate design or architecture documents from existing implementation. Works backwards from code/prototypes to create missing planning docs.

  • Dual jre docker oz report

    kjuhwa/skills-hub/skills/devops/dual-jre-docker-oz-report Skill

    0★ repo

    Package a Java 21 Spring Boot app that bundles a legacy JRE 8 + sidecar Tomcat (OZ Report engine) in one Alpine container

  • Document release

    kjuhwa/skills-hub/skills/docs/document-release Skill

    0★ repo

    Post-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when asked to "update the docs", "sync documentation", or "post-ship docs". Proactively suggest after a PR is merged or code is shipped. (gstack)

  • Inline i18n dictionary with dropdown

    kjuhwa/skills-hub/skills/gradio/inline-i18n-dictionary-with-dropdown Skill

    0★ repo

    Inline i18n via Python dict keyed by language code, swapped live via Gradio dropdown callback

  • I18n module registry pattern

    kjuhwa/skills-hub/skills/i18n/i18n-module-registry-pattern Skill

    0★ repo

    Compile-time language module registration with lazy_static registry — no runtime file IO.

  • Atomic file write with fsync

    kjuhwa/skills-hub/skills/jit-compilation/atomic-file-write-with-fsync Skill

    0★ repo

    Wrap every cache write with a `put(path, data)` helper that calls `ofstream.write`, closes, then `fsync(open(path))` so other processes on distributed filesystems see the full file before it's read.

  • First occurrence config print with set memo

    kjuhwa/skills-hub/skills/jit-compilation/first-occurrence-config-print-with-set-memo Skill

    0★ repo

    Print a JIT-selected config the first time a given shape/desc is encountered, memoizing with `std::unordered_set<std::string>` keyed on the stringified descriptor — so each unique workload prints exactly once.

  • Writing skills

    kjuhwa/skills-hub/skills/meta/writing-skills Skill

    0★ repo

    Use when creating new skills, editing existing skills, or verifying skills work before deployment

  • Write a skill

    kjuhwa/skills-hub/skills/misc/write-a-skill Skill

    0★ 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.

  • Failure streak cooldown auto issue report

    kjuhwa/skills-hub/skills/observability/failure-streak-cooldown-auto-issue-report Skill

    0★ repo

    When a long-running agent hits a repeating failure, file one GitHub issue — not ten — by combining a minimum-streak threshold, a per-error-signature cooldown, an open-issue search for de-duplication, and sanitized logs, then persist the decision in a local state file so the next run resumes the throttle.

  • Personality report generation with percentiles

    kjuhwa/skills-hub/skills/observability/personality-report-generation-with-percentiles Skill

    0★ repo

    Generate human-readable personality report with success rates, velocity, and trait analysis

  • Html to markdown markdownify subclass

    kjuhwa/skills-hub/skills/preprocessing/html-to-markdown-markdownify-subclass Skill

    0★ repo

    Subclass markdownify.MarkdownConverter to customize link escape, drop javascript/data URIs, convert input[type=checkbox] to GFM task syntax, and fall back to plain text on deeply-nested HTML.

  • Writing plans

    kjuhwa/skills-hub/skills/process/writing-plans Skill

    0★ repo

    Use when you have a spec or requirements for a multi-step task, before touching code

  • Bug report

    kjuhwa/skills-hub/skills/production/bug-report Skill

    0★ repo

    Creates a structured bug report from a description, or analyzes code to identify potential bugs. Ensures every bug report has full reproduction steps, severity assessment, and context.

  • Changelog

    kjuhwa/skills-hub/skills/production/changelog Skill

    0★ repo

    Auto-generates a changelog from git commits, sprint data, and design documents. Produces both internal and player-facing versions.

  • Team qa

    kjuhwa/skills-hub/skills/production/team-qa Skill

    0★ repo

    Orchestrate the QA team through a full testing cycle. Coordinates qa-lead (strategy + test plan) and qa-tester (test case writing + bug reporting) to produce a complete QA package for a sprint or feature. Covers: test plan generation, test case writing, smoke check gate, manual QA execution, and sign-off report.

  • Playtest report

    kjuhwa/skills-hub/skills/qa/playtest-report Skill

    0★ repo

    Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

  • Multilingual tts text normalize and split

    kjuhwa/skills-hub/skills/text-normalization/multilingual-tts-text-normalize-and-split Skill

    0★ repo

    Multilingual TTS text normalization via wetext + inflect with budget-aware paragraph splitting

  • Model onnx file versioning and staging

    kjuhwa/skills-hub/skills/versioning/model-onnx-file-versioning-and-staging Skill

    0★ repo

    Version model assets under assets/models/<name>_v<major>_<minor>/ with per-version README and a top-level CHANGELOG.md, and a 'default' pointer (file or symlink).

  • Md corpus l1 l2 index with auto regen

    kjuhwa/skills-hub/skills/workflow/md-corpus-l1-l2-index-with-auto-regen Skill

    0★ repo

    Build a two-tier markdown index over a large MD corpus (skills, notes, docs) so LLMs can discover entries without reading every file. L1 compact + L1 full + per-category L2, regenerated via git hooks after every mutation so the index never goes stale.