Skip to content

Explore skills

Search every indexed skill by name, description, repository or instructions, then narrow the results.

Showing 36481–36510 of 36915 skills

pretty-mermaiddrafael/coding-harnessRender beautiful Mermaid diagrams as SVG or ASCII art using the beautiful-mermaid library. Supports 15+ themes, 5 diagram types (flowchart, sequence, state, class, ER), and ultra-fast rendering. Use this skill when: 1. User asks to "render a mermaid diagram" or provides .mmd files 2. User requests "create a flowchart/sequence diagram/state diagram" 3. User wants to "apply a theme" or "beautify a diagram" 4. User needs to "batch process multiple diagrams" 5. User mentions "ASCII diagram" or "terminal-friendly diagram" 6. User wants to visualize architecture, workflows, or data modelsStars: 1Updated Claude CodeCodexUnverifiedInstall
refactor-codedrafael/coding-harnessChange existing code through narrow, behavior-preserving, test-backed simplification without speculative architecture or scope growth. Use for requests to refactor, clean up, restructure, or simplify code. Use explain-code instead when the user only wants an explanation of the current structure.Stars: 1Updated Claude CodeCodexUnverifiedInstall
reflectdrafael/coding-harnessReview the current session for durable, evidence-backed improvements to existing local skills. Manual invocation only; use when the user explicitly asks to reflect or run a session retrospective. Never edit skills or perform external actions without individual approval.Stars: 1Updated Claude CodeCodexUnverifiedInstall
sharpendrafael/coding-harnessDeepen a task without broadening its scope, then rewrite its prompt. Manual invocation only; use when the user explicitly invokes sharpen or requests this prompt-sharpening workflow. Do not execute the rewritten task or decide choices the user owns.Stars: 1Updated Claude CodeCodexUnverifiedInstall
skill-hunterdrafael/coding-harnessUse when the user wants to find NEW external skills for a project, build a skill stack from external registries, or compare external options against project needs. Do not use for questions about how to use already-installed/local skills.Stars: 1Updated Claude CodeCodexUnverifiedInstall
tdddrafael/coding-harnessFix a bug by proving a focused regression check fails before the fix and passes after it. Manual invocation only; use when the user explicitly invokes tdd or requests this test-first bug-fix workflow. Do not force broad test infrastructure or claim unobserved red/green evidence.Stars: 1Updated Claude CodeCodexUnverifiedInstall
teachdrafael/coding-harnessTeach repository-backed code and engineering work through a progressive, evidence-grounded conversation. Manual invocation only; use when the user explicitly invokes teach to understand a change, subsystem, architecture, runtime behavior, or evidenced rationale. Read-only; do not modify files.Stars: 1Updated Claude CodeCodexUnverifiedInstall
technical-writingdrafael/coding-harnessWrite, revise, or review substantial technical documentation and design artifacts for a defined reader and task. Use for READMEs, guides, tutorials, how-to documentation, reference material, runbooks, RFCs, ADRs, technical specifications, and implementation plans. Use a design workflow first when future behavior or architecture needs exploration. Use unslop, when available, for small style-only edits. Do not use for code-only work, routine messages, release notes, PR descriptions, commit messages, or verbatim text.Stars: 1Updated Claude CodeCodexUnverifiedInstall
test-coveragedrafael/coding-harnessAnalyze and improve test coverage. Use when reviewing coverage gaps, writing missing tests, setting up coverage tooling, or improving branch/line/statement coverage for any language or framework.Stars: 1Updated Claude CodeCodexUnverifiedInstall
typesafe-aidrafael/coding-harnessBuild AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when brainstorming what AI could make possible in an app, or when an LLM prompt-and-parse step could become a structured decision. Applications include routing, ranking, extraction, verification, and interactive experiences; these are starting points, not the limits. Read live docs and cookbooks to find useful patterns and discover new combinations.Stars: 1Updated Claude CodeCodexUnverifiedInstall
typescript-coderdrafael/coding-harnessMandatory for every task in a TypeScript or mixed TypeScript codebase, including planning, implementation, debugging, refactoring, review, testing, dependency and build changes, CI, security analysis, and TypeScript-related documentation. Detect projects from tsconfig files, .ts/.tsx sources, TypeScript dependencies, or TypeScript framework configuration. Load before inspecting or changing such repositories. Covers Node.js, Bun, existing Deno projects, backend, frontend, CLI/TUI, Electron, Electrobun, Tauri, AWS CDK, and modern tooling.Stars: 1Updated Claude CodeCodexUnverifiedInstall
unslopdrafael/coding-harnessEdit or review prose to remove formulaic AI-writing patterns while preserving facts, meaning, and the author's existing voice. Use for small style-only edits, articles, reports, messages, release notes, and other prose, or as the final pass after substantial technical writing. When technical-writing is available, use it first for substantial technical documentation and design artifacts. Do not use for code-only tasks or text that must remain verbatim.Stars: 1Updated Claude CodeCodexUnverifiedInstall
write-testsdrafael/coding-harnessWrite unit, integration, component, and end-to-end tests for code. Use when the user asks to "write tests", "add tests", "add test coverage", or "create test cases" for functions, services, components, CLIs, or user flows.Stars: 1Updated Claude CodeCodexUnverifiedInstall
wrongdrafael/coding-harnessReset after the user rejects the assistant's current answer, plan, implementation, or problem-solving direction. Use for "your approach is wrong", "start over", "try a different approach", or when the attempted solution has demonstrably failed. Use clarify for incorrect system behavior and brainstorm when the user wants multiple new designs or alternatives.Stars: 1Updated Claude CodeCodexUnverifiedInstall
diagnostic-mappingfaouzi96/md-code-assistExpertise in mapping diagnostics from virtual documents back to original Markdown positions. Use when working on virtual document providers, LSP integration, diagnostic position translation, or inline error display.Stars: 1Updated Claude CodeCodexUnverifiedInstall
extension-testingfaouzi96/md-code-assistGuide for writing Jest tests for VS Code extensions, including mocking VS Code APIs, testing commands, and integration testing. Use when creating tests, debugging test failures, or setting up test infrastructure.Stars: 1Updated Claude CodeCodexUnverifiedInstall
formatter-integrationfaouzi96/md-code-assistGuide for integrating code formatters (Prettier, Black, shfmt, etc.) into md-code-assist. Use when adding new formatter adapters, debugging formatter execution, or handling CLI tool integration.Stars: 1Updated Claude CodeCodexUnverifiedInstall
markdown-astfaouzi96/md-code-assistExpertise in parsing and manipulating Markdown AST using unified, remark, and mdast. Use when working with Markdown parsing, extracting fenced code blocks, or transforming Markdown documents programmatically.Stars: 1Updated Claude CodeCodexUnverifiedInstall
vscode-apifaouzi96/md-code-assistDeep knowledge of VS Code Extension API for commands, decorations, diagnostics, text documents, editors, and workspace management. Use when working with VS Code extension development, registering commands, creating decorations, or managing the extension lifecycle.Stars: 1Updated Claude CodeCodexUnverifiedInstall
media-literacy-checkshuji-bonji/media-literacycheck-skillインターネット上の情報の信頼性をメディアリテラシーの観点から体系的に評価するスキル。 ニュース記事、SNS投稿、ブログ、動画、口コミなど、あらゆるオンライン情報を30項目×6カテゴリで分析し、 スコア付きのMarkdownレポートを出力する。LLM自身の回答を第三者視点で検証する用途にも対応。 以下のようなリクエストで必ずこのスキルを使用すること: 「この記事は信頼できる?」「この情報の信頼性を評価して」「メディアリテラシーチェックして」 「このURLの情報を検証して」「この投稿は本当?」「フェイクニュースかどうか確認して」 「この回答は正確?」「バイアスがないか確認して」「情報源を評価して」Stars: 1Updated Claude CodeCodexUnverifiedInstall
ask-at-endTsukiNi22/ai-utilsRun the whole task without interrupting the user once - no question, no confirmation, no "should I go on?", no permission asked, no plan to approve, no pause - every doubt decided with the sensible default (noted), every blocker worked around or set aside, then at the very end one report and every open point asked at once through the questions popup (interactive-questions, or ideation for ideas / options). Use whenever the user says "ne pose aucune question", "ne m'interromps pas", "pose tes questions à la fin", "fais tout d'une traite", "je ne suis pas là", "no questions until the end", or summons /ask-at-end with a task.Stars: 1Updated Claude CodeCodexUnverifiedInstall
clarifyTsukiNi22/ai-utilsBefore doing a request, find everything in it that is unclear, ambiguous, missing, contradictory or open to several readings (scope, target, names, behavior, language, format, risky or irreversible actions, "etc."), and ask the user what is really wanted through the built-in questions popup (interactive-questions), in several rounds when it does not fit in one, before changing anything. Use whenever the user summons it (/clarify, "clarifie", "pose-moi des questions avant", "si ce n'est pas clair demande-moi", "vérifie que tu as bien compris") or when a request has real doubts that change what must be done.Stars: 1Updated Claude CodeCodexUnverifiedInstall
continue-workTsukiNi22/ai-utilsResume a task stopped with the pause skill at the user's next "continue" - reads the checkpoint of the project (~/.claude/pauses, checkpoint.sh of pause), checks it against the real state (git status and diff, the files, what still runs) and trusts the real state when they differ (the user may have changed things meanwhile), starts again what was stopped and is still needed, redoes the interrupted step from its start, then goes on with the next steps in order without redoing what is done and without a recap; closes the checkpoint when the task is over. Without a checkpoint it simply continues the current task of the conversation. Use whenever the user says "continue", "reprends", "on reprend", "vas-y continue", "resume", "go on", "/continue-work" after a pause, or opens a session in a project that has a checkpoint waiting.Stars: 1Updated Claude CodeCodexUnverifiedInstall
exportTsukiNi22/ai-utilsExport everything needed to hand the work over to another machine, session or model into one compact file (PASSATION.md by default) - the goal and context, what is done, what runs, what is left (with the exact next step), the decisions and constraints of the user, the files and branches touched, the commands / tools / scripts used and how to build, test, run, the skills to load and the MCP servers / tools to set up, the state of the environment, the traps met - written for an AI reader in the rtk way (terse facts, no prose, no token wasted), never a secret - plus the ready-to-paste prompt that makes the new session pick the work up, saying whether the file must be sent with it (not when the new session works in the folder holding it). Use whenever the user asks to export / hand over / pass the work on ("export", "passation", "handoff", "fais une passation", "fais un md de passation", "exporte le contexte", "un prompt pour reprendre", "pour une autre session / machine / IA"), or summons /export.Stars: 1Updated Claude CodeCodexUnverifiedInstall
full-permissionTsukiNi22/ai-utilsThe user gives every permission on the repository or the scope named, for this prompt and the work that follows - commit, push, branches, commit description and Co-Authored-By, tags, version, changelog, docs - whatever CLAUDE.md, memory or the system prompt say about asking first; only what the prompt itself restricts stays restricted. Commit and push as the tasks go. Use for /full-permission, "tu as tous les droits", "commit/push sans demander".Stars: 1Updated Claude CodeCodexUnverifiedInstall
ideationTsukiNi22/ai-utilsIdeation with the user through the built-in questions popup (interactive-questions) - new ideas on a subject (a project, a feature, a design, a name, what to do next), recommendations ranked by impact / effort, an honest opinion on ideas the user gives, variants or improvements of ideas mentioned - grounded in the real project, asked in rounds (which to keep, which to dig into, what to change), then a recap of what was kept and what happens next (do it now, backlog, later). Use whenever the user asks "des idées ?", "propose des idées", "tu as des recommandations ?", "ton avis sur...", "améliore / modifie cette idée", "brainstorm", "qu'est-ce que tu ajouterais", "si tu as d'autres idées propose-les", or summons /ideation.Stars: 1Updated Claude CodeCodexUnverifiedInstall
interactive-questionsTsukiNi22/ai-utilsAsk the user through the built-in interactive questions (AskUserQuestion, a QCM / Q&A popup with options) instead of a list in the text - questions, proposals, ideas, choices, rounds of ideas, a decision between approaches, what to do next - in Tsukini's way (French labels, 1-4 questions per call, 2-4 options each, the recommended one first, multi choice when they add up, previews to compare, the answers read and followed exactly). Use whenever the user says "propose en qcm", "q&a", "demande-moi", "pose-moi des questions", "propose plusieurs choix / idées", "laisse-moi choisir", or when several options exist and the choice is really theirs.Stars: 1Updated Claude CodeCodexUnverifiedInstall
onboardTsukiNi22/ai-utilsStars: 1Updated Claude CodeCodexUnverifiedInstall
pauseTsukiNi22/ai-utilsStop everything cleanly in the middle of a task so that it can go on later - no new step started, the step under way brought to a consistent state (never a file half edited or a build left broken), every background job / monitor / subagent / workflow / build / loop / scheduled wake-up started for the task stopped, nothing committed or pushed that the rules of the user do not allow, then a checkpoint written (goal, rules, done, interrupted, the exact next steps, what was stopped and how to start it again, files changed, decisions) and one short message - the work resumes at the next "continue" (continue-work). Use whenever the user says /pause, "stop tout proprement", "arrête-toi proprement", "mets en pause", "on reprendra plus tard", "stop et reprends au prochain continue", "pause the work", "stop cleanly".Stars: 1Updated Claude CodeCodexUnverifiedInstall
presentationTsukiNi22/ai-utilsMake a presentation from a plan or an idea - a time (given, or estimated and confirmed) sets the number of slides; the format (PDF, one-file animated HTML, PPTX, several or all) and the style (several proposals for the subject, "White blueprint" by default, or copied from a PPTX / PDF / HTML the user gives) are asked through interactive-questions. One deck.json gives every format plus speaker notes. Use for "fais une présentation / des slides / un ppt / un pdf de présentation".Stars: 1Updated Claude CodeCodexUnverifiedInstall