All categories
Documentation
Docs, README files, API references, tutorials, specs, and changelogs
- 15,627
- 652
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse documentation skills
Showing 4,153–4,176 of 15,627 skills
- Samanthaci Stormstack .Claude CommandsRun all review skills (self, SOLID, test coverage, security, docs), merge findings, apply auto-fixes, generate unified summary. Triggers: 'premerge', 'pre-merge', 'full review', 'review everything', 'pre-push', 'check all'.Votes: 0GitHub stars: 4
- Overflow65537 Maa Snowbreak Skill> 目标:让 AI Agent 在本仓库中稳定、可复现地完成“分析、文档、脚本与轻量维护”类任务。Votes: 0GitHub stars: 4
- Markes76 Claude Code Gui Linkedin Cli DocsYou have access to `linkedin-cli`, an unofficial LinkedIn CLI tool. Use it to read information from the user's LinkedIn account.Votes: 0GitHub stars: 4
- Majiayu000 Claude Skill Registry Skills Other Changelog GuideWrite and maintain CHANGELOG.md following Keep a Changelog format. Use when: creating changelog entries, preparing releases, documenting changes. Keywords: changelog, release notes, CHANGELOG.md, keep a changelog, 變更日誌, 發布說明.Votes: 0GitHub stars: 4
- Majiayu000 Claude Skill Registry Skills Documents CoreCore development principles and guidelines covering security, QA, performance, documentation, and coding standards. Used by all agents to ensure consistent quality across the Orchestra system.Votes: 0GitHub stars: 4
- Genecyber Loadout PromptsThis guide provides a structured approach for analyzing skill security and identifying potential vulnerabilities.Votes: 0GitHub stars: 4
- Flashpoint493 Vibecollab .You are helping a user set up VibeCollab in their project. Execute the following steps in order. Stop and report if any step fails.Votes: 0GitHub stars: 4
- Codermakers Interview Questions Git- git clone --mirror (镜像): 主要用于仓库迁移(常见不同托管平台):实现仓库一比一完整迁移: 保留所有分支,提交历史、标签等Votes: 0GitHub stars: 4
- Ceetity Her Skill .将一个真实的人蒸馏为 AI Skill —— 她的声音、她的记忆、她的温度。 通过聊天记录、照片、文字叙述等原材料,构建一个完整的数字副本。Votes: 0GitHub stars: 4
- 4797pnkkx5 Gif Ai Augmented Re Skills Elicit**Purpose:** Synthesise all available input documents into the Elicitation Document. Every run reads all inputs — new and existing — and updates the document to reflect the best current understanding. New information can refine existing requirements, resolve open questions, and improve architecture diagrams. **Invocation:** - Claude Code: `/elicit` - GitHub Copilot: "Run the elicit skill" or "Follow `skills/elicit/skill.md`" **Inputs:** - All files in `inputs/` and sub-folders (Markdown, PDF,...Votes: 0GitHub stars: 4
- Youtube DownloaderDownload YouTube videos and HLS streams (m3u8) from platforms like Mux, Vimeo, etc. using yt-dlp and ffmpeg. Use this skill when users request downloading videos, extracting audio, handling protected streams with authentication headers, or troubleshooting download issues like nsig extraction failures, 403 errors, or cookie extraction problems.Votes: 0GitHub stars: 4
- Writing Prose Like A HumanProduces prose that reads as authentically human by avoiding statistical patterns common to LLM output. Use when writing or editing prose, documentation, READMEs, PR descriptions, or any text where the output must not read like AI-generated content.Votes: 0GitHub stars: 4
- Writing Hive SkillsAuthor a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, or package a new skill for a Hive agent.Votes: 0GitHub stars: 4
- Write DocsCollaborative document authoring workflow for proposals, technical specs, decision docs, README sections, ADRs, and long-form prose that must work for fresh readers. Use when asked to "write the docs", "draft a proposal", "write a spec", "write an RFC", "write the README", or when a document needs to be understandable by someone without this session's context. Three stages: gather context, iterate on structure, reader-test for a stranger.Votes: 0GitHub stars: 4
- Write Clear ReadmeAuthor, audit, or polish a project README — clarity, structure (Pattern A grouped collapse / Pattern B per-entry collapse), wording concision, anchor integrity. Reads the repo first, proposes diffs, applies on approval.Votes: 0GitHub stars: 4
- Wjs Auditing ProjectUse when the user asks to audit what's wrong with a project, "make it right", "看看项目出了什么问题", "为什么用户的需求还没上线", "为什么没提交App Store", "为什么没新build", or wants a holistic state-of-the-project check covering unmerged branches, stalled PRs, failed GitHub Actions, stale builds, plan drift (TODOS.md / ROADMAP), unreleased commits, and log errors. Runs read-only investigation, presents a grouped checklist, fixes only after explicit user confirmation. Aware of the Cathier iOS app workflow (Xcode + fastlane +...Votes: 0GitHub stars: 4
- Windsurf Code PrivacyConfigure code privacy and data retention policies. Activate when users mention "code privacy", "data retention", "privacy settings", "data governance", or "gdpr compliance". Handles privacy and data protection configuration. Use when working with windsurf code privacy functionality. Trigger with phrases like "windsurf code privacy", "windsurf privacy", "windsurf".Votes: 0GitHub stars: 4
- VulgariserThis skill should be used when the user invokes /vulgariser, asks to "expliquer simplement", "comment dire ça à mon client", "vulgarise [concept]", "explique [terme financier] à quelqu'un qui n'y connaît rien", "comment expliquer le PER à un retraité", "prépare une explication sur [sujet] pour un client", or needs any financial or regulatory concept translated into plain language for non-expert clients. Always use cgp-persona tone (clear, reassuring, no jargon).Votes: 0GitHub stars: 4
- Vrc Udon Heavy RuntimeVRChat UdonSharp で重い再構築処理、replay、reset、段階実行、分割適用が必要な runtime を設計・実装するときに使う。大量オブジェクト更新、操作列の再適用、1 フレームで終わらない処理を安全に扱いたい場合に使う。Votes: 0GitHub stars: 4
- Validate MechanismsPeriodic smoke test for behavioral mechanism compliance. Scans the workspace for statically-detectable violations of rules in mechanism-registry.md. Use when: (1) user says "validate mechanisms", "檢查機制", "/validate-mechanisms", (2) as part of a periodic health check, (3) after major framework changes.Votes: 0GitHub stars: 4
- Validate IntegrationAudit an existing Sim integration against the service API docs and repository conventions, then report and fix issues across tools, blocks, outputs, OAuth scopes, triggers, and registry entries. Use when validating or repairing a service integration under `apps/sim/tools`, `apps/sim/blocks`, or `apps/sim/triggers`.Votes: 0GitHub stars: 4
- Validate Genie Learning CourseValida artefatos gerados pelo Genie Learning após uma execução manual da skill `/genie-learn` no Claude Code, verificando estrutura, idioma, conteúdo, podcast, quizzes, segurança de secrets e sinais de falha de orquestração.Votes: 0GitHub stars: 4
- Validate ContributionValidate geographic data contributions against the CSC database schema. Use this skill whenever you encounter a PR that adds, modifies, or deletes data in the contributions/ directory. Trigger on: validate, check, review, verify, audit, inspect, or assess any data contribution, PR review requests, schema compliance checks, field validation, or when someone says "is this correct", "check my data", "validate this", or "review my PR". Also use when asked about required fields, allowed values, or...Votes: 0GitHub stars: 4
- UpfetchLoad this skill for any up-fetch task: `up(fetch, getDefaultOptions?)`, `upfetch(url, options?)`. Covers dynamic defaults, auth, request shaping, validation, error handling, lifecycle timing, and runtime caveats.Votes: 0GitHub stars: 4