All categories
Documentation
Docs, README files, API references, tutorials, specs, and changelogs
- 15,591
- 650
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 2,449–2,472 of 15,591 skills
- Engineering StandardApply shared engineering standards when implementing, reviewing, or documenting software. Covers evidence-based verification, iterative delivery of large changes, project contribution rules, development tooling, formatting, Rust conventions, and Git/GitHub workflows.Votes: 0GitHub stars: 212
- Array ApiConventions that MUST be followed when implementing array API compatible functions and their tests.Votes: 0GitHub stars: 212
- P ImageGenerate images with Pruna P-Image models via inference.sh CLI. Models: P-Image, P-Image-LoRA, P-Image-Edit, P-Image-Edit-LoRA. Capabilities: text-to-image, image editing, LoRA styles, multi-image compositing, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna, p-image, pruna image, fast image generation, optimized flux, pruna ai, p image, fast ai image, economic image generation, cheap image generationVotes: 0GitHub stars: 212
- Gpt ImageGenerate and edit images with OpenAI GPT-Image-2 via inference.sh CLI. Models: GPT-Image-2. Capabilities: text-to-image, image editing, inpainting, mask-based editing, multi-image reference, batch generation. Use for: product mockups, marketing visuals, image editing, concept art, inpainting, photo manipulation. Triggers: gpt image, gpt-image-2, openai image, chatgpt image, dall-e, dalle, openai image generation, gpt image edit, gpt inpainting, openai dall-e, gpt 4o imageVotes: 0GitHub stars: 212
- Regelrecht Scenario TracesMaakt regelrecht-scenario's vindbaar en hun norm-ketens leesbaar/geassert. Aan de invoerkant — vertaal een platte lijst leaf-parameters naar benoemde casus-assen + een herbruikbare persona-bibliotheek, met een reverse-lookup casus-matrix. Aan de uitvoerkant — maak de norm-keten zichtbaar via keten-checkpoints (assert elke knoop op het kritieke pad, niet alleen de endpoint) en golden-trace-snapshots + branch-coverage. Gebruik dit bij het schrijven of opschonen van scenario-/feature-files, het ...Votes: 0GitHub stars: 23
- Law DownloadDownloads Dutch official legal publications including national laws, local regulations, and implementation policies from government sources (wetten.overheid.nl, lokaleregelgeving.overheid.nl). Use this skill proactively when: user mentions downloading, fetching, or importing a Dutch law by name or BWB/CVDR identifier, when a source.regulation reference points to a law not in the corpus, or when user provides a wetten.overheid.nl URL. Activate automatically when user mentions a specific Dutch ...Votes: 0GitHub stars: 23
- DependabotProcesses all open Dependabot PRs sequentially — rebases if needed, analyzes for breaking changes and security issues, then merges or requests changes. Use when you want to handle pending Dependabot dependency updates.Votes: 0GitHub stars: 23
- Port Daddy Expository WriterVoice and structure guide for Port Daddy expository writing — the kind of essay that takes a hard technical claim (formal verification, mechanism design, cryptographic protocol) and turns it into something an educated reader can follow with pleasure. Use when authoring docs/concepts/* or docs/tutorials/* pieces that explain how the Port Daddy whitepapers' formal proofs actually work. NOT for landing-page marketing (use port-daddy-marketing-copy), NOT for ADR bodies (those stay internal), NOT ...Votes: 0GitHub stars: 2
- Agent SkillsAuthoring Agent Skills — SKILL.md format and frontmatter, progressive disclosure and token budgeting, Anthropic's authoring best practices, bundling references/scripts, and packaging skills for Claude Code, claude.ai, and the Skills API. WHEN: \"write a SKILL.md\", \"create an Agent Skill\", \"skill frontmatter\", \"skill description isn't triggering\", \"progressive disclosure\", \"disable-model-invocation\", \"allowed-tools in a skill\", \"context: fork\", \"upload a custom skill\", \"conta...Votes: 0GitHub stars: 4
- Skill BuilderMulti-agent research-and-curation pipeline that builds or refreshes a technology skill for the domain-expert marketplace. The invoking session becomes a pure orchestrator: parallel Sonnet research agents WebFetch official documentation into a source-cited corpus under research/<skill>/, a gap audit closes coverage holes, then a single Opus curator distills the corpus into the skill (200–500 line SKILL.md, trigger-tuned frontmatter description, at least one references/ file, scripts/ when they...Votes: 0GitHub stars: 4
- Plugin BuilderInteractive orchestration pipeline that remodels an existing skills repo (or a pile of .claude/ assets) into a well-architected Claude Code plugin or marketplace repo, and plans greenfield plugins. Interviews the user on intent before acting, inventories existing skills/commands/agents/hooks, strategizes which components each plugin should ship (skill vs agent vs hook vs command vs MCP server), proposes an architecture for sign-off, scaffolds manifests and migrations, then delegates per-skill...Votes: 0GitHub stars: 4
- Deep ExplainerUse this skill whenever the user asks a question they want genuinely explained — especially while learning an unfamiliar codebase, repository, library, or technical concept. Trigger it for any question ending in a "?", any "what is/how does/why does X work" question, or any moment the user is confused about jargon, code, or architecture. Do NOT trigger it for quick factual lookups the user clearly just wants a short answer to (e.g. "what's the syntax for X", "what year was Go released"), for ...Votes: 0GitHub stars: 16
- Demo GifRecord and optimize reproducible README demo GIFs. Use when asked to record a demo or add a README GIF.Votes: 0GitHub stars: 7
- DocumentationCreates, structures, and reviews technical documentation following the Diátaxis framework (tutorials, how-to guides, reference, and explanation pages). Use when a user needs to write or reorganize docs, structure a tutorial vs. a how-to guide, build reference docs or API documentation, create explanation pages, choose between Diátaxis documentation types, or improve existing documentation structure. Trigger terms include: documentation structure, Diátaxis, tutorials vs how-to guides, organize...Votes: 0GitHub stars: 18
- Minimap Spec ReviewUse when reviewing or commenting on one specific markdown file (spec, design, RFC, idea, roadmap item) with anchored comments and proposed edits. Works from any repo, including repos without minimap.Votes: 0GitHub stars: 2
- Minimap RoadmapUse when showing or updating roadmap state in a repo with the minimap roadmap convention (board.md, scope.md, features/, ideas/). Not for arbitrary spec review.Votes: 0GitHub stars: 2
- MinimapTop-level entry point for minimap. Use this to choose between the two minimap capabilities. For roadmap planning and roadmap file updates use `minimap-roadmap`. For collaborative review of one specific spec/design/idea file use `minimap-spec-review`.Votes: 0GitHub stars: 2
- Google DocsAuthor and edit Google Docs with the google-docs tools - structured writing, character and paragraph styling, lists, tables, images, headers/footers. Use when creating a formatted document, editing document content, or applying styles.Votes: 0GitHub stars: 9,086
- Cli OrcaRoute Orca CLI work: worktrees, terminals, browser, automations, handoffs, artifacts, and the eight official Orca skills.Votes: 0GitHub stars: 36
- Cli JevTypeSafe Jev CLI transport for typed judgments: noul probabilities, choice selections, ordered scores, and batched run requests.Votes: 0GitHub stars: 36
- Mintlify DocsBuild and maintain documentation sites with Mintlify. Use when creating docs pages, configuring navigation, adding components, or setting up API references.Votes: 0GitHub stars: 450
- Writing Plan計画を作成し、依頼された実装の各ステップと実測結果を記録する親向けスキル。計画だけの依頼では実装へ進まず、既存計画は決定事項と完了項目を保って増分更新する。ユーザーが /writing-plan と入力したら使う。Votes: 0GitHub stars: 8
- Walkthrough差分または既存コードを実コードに基づいて説明し、入口・経路・状態・設計上の注意を整理する。必要な場合だけ詳細化・保存・HTML化を行う。ユーザーが /walkthrough と入力したときに使う。Votes: 0GitHub stars: 8
- Retro実際の作業結果からパターンを汎化し、次回に役立つ改善を提案する。振り返り・ふりかえり・retrospective・改善サイクル・エージェント定義の見直し・パターン分析に使う。`--meta` と `--dream` はユーザーが明示した場合の追加モード。ユーザーが /retro と入力したら使う。Votes: 0GitHub stars: 8