Explore skills
Search every indexed skill by name, description, repository or instructions, then narrow the results.
Showing 42901–42930 of 50352 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| onboardTsukiNi22/ai-utils | Stars: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| 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: 1 | Updated | Claude CodeCodex | Unverified | Install |
| rtkTsukiNi22/ai-utilsReduce to the minimum the tokens of a text, a command output, a report, a log or a program's output so it costs the least in an AI context - every human-readable part dropped (colors, ANSI, tables, rulers, banners, prose, repeated fields, absolute paths), only the signal kept in a compact machine-oriented form (legend once, one record per line, shared values written once, counters on one line), even if unreadable for a human - and design / implement an --rtk mode (flag + env var) on a program or script, like xstyle --rtk. Use whenever the user asks to compact / minify / compress a text or an output for an AI, to save tokens or context, for an "rtk" / "AI" / "token-optimized" output or mode, to add such a flag to a binary or a script, or to write a file only an AI will read. | Stars: 1 | Updated | Claude CodeCodex | Unverified | Install |
| setup-contextTsukiNi22/ai-utilsSet up everything this conversation needs before the work starts - read the current repository (tree, docs, rules files, build, code, git state), search the earlier and archived sessions on this computer (Claude Code transcripts and memory, claude-cluster sessions and their trash, Codex / Qwen / opencode, handover files) for what was asked, done, left and decided, then load the skills that fit the project (style, language, build, tests, docs, git) and check the MCP servers / tools it would use (configured, connected, missing), and hold it all as the working context; the questions only at the end. Use whenever the user says "setup le contexte", "prépare-toi", "charge tout ce qu'il faut", "lis le repo et les anciennes sessions", "setup les skills / mcp utiles", or summons /setup-context before a task. | Stars: 1 | Updated | Claude CodeCodex | Unverified | Install |
| write-like-meTsukiNi22/ai-utils | Stars: 1 | Updated | Claude CodeCodex | Unverified | Install |
| audit-bugsTsukiNi22/ai-utilsAudit a project for bugs in a loop - undefined behaviour, memory errors and leaks, data races, error handling, logic and security bugs - with sanitizer builds (ASan/LSan/UBSan/TSan), unit tests, compiler warnings, static analysers and code review, alone or with parallel subagents (asked to the user), every finding verified with evidence, then reported (optionally fixed after confirmation). Use whenever the user asks for an audit, bug hunt, UB / memory error / crash / race search, a sanitizer run, or a correctness review of a project, module or diff. | Stars: 1 | Updated | Claude CodeCodex | Unverified | Install |
| audit-depsTsukiNi22/ai-utilsCheck the dependencies of a project (direct and transitive - CMake packages, pkg-config, FetchContent, submodules, vendored code, prebuilt binaries, includes, pip/npm/cargo) for their licenses - what must be credited, copyleft constraints, non-commercial / source-available / paid / proprietary terms, dependencies without license or of unknown origin - generate the third-party notices, and check their known vulnerabilities / compromised versions; result delivered as a PDF report. Use whenever the user asks what the dependencies allow, what to credit, if a dependency is legal/paid/restrictive, a THIRD_PARTY_NOTICES file, or a dependency security check. | Stars: 1 | Updated | Claude CodeCodex | Unverified | Install |
| audit-qualityTsukiNi22/ai-utils | Stars: 1 | Updated | Claude CodeCodex | Unverified | Install |
| audit-securityTsukiNi22/ai-utilsSecurity and memory-safety audit of the whole project in passes run back to back - memory errors that can crash it or be exploited (overflows, use after free, leaks a client can trigger, races), injection (shell, SQL, path, format strings), authentication / authorization holes, secrets, crypto, network exposure, files and permissions, untrusted input, known vulnerable dependencies - each finding verified with evidence and fixed at once, then a new full pass, again and again while the last pass still found something; ends with a PDF report (report skill) of everything found and fixed. Use whenever the user asks for a security audit, a vulnerability / flaw / exploit hunt, a hacking-proof check, a memory-error audit that must be fixed until clean, or "passe sur tout le projet pour les failles". | Stars: 1 | Updated | Claude CodeCodex | Unverified | Install |
| benchmarkTsukiNi22/ai-utilsBenchmark and profile the current program (C / C++ first, also Rust and Python) with the tools available (perf stat / record / report, hyperfine, valgrind callgrind / massif, heaptrack, flame graphs), asking before installing a missing tool - optimized build with symbols in a copy, wall time, hardware counters, hot functions (self and inclusive), hot lines, memory - then the analysis of what is slow and why, each finding classified as a quick win or a complex change with its estimated gain, delivered as a PDF / Markdown report (report skill), and optionally the optimizations with a before / after comparison. Use whenever the user asks for a benchmark, a profiling, a performance analysis, what is slow, which function takes the time, or how to optimize a program. | Stars: 1 | Updated | Claude CodeCodex | Unverified | Install |
| cmake-styleTsukiNi22/ai-utilsWrite or edit CMakeLists.txt in Tsukini's style (from libutils, context-forge, c2dmp-hsm) - fixed section order with '# =====' banners, TARGET variable, clang++ C++20, ccache, warnings, explicit SRC list with group comments, Debug/Asan/Optimized modes, release targets, exception header generation, GTest tests/, install + find_package config, CPack RPM/DEB with stable/pre channels, Makefile wrapper. Use whenever creating, editing or reviewing a CMakeLists.txt, a tests/CMakeLists.txt, a *Config.cmake.in or the CMake packaging of one of the user's projects. | Stars: 1 | Updated | Claude CodeCodex | Unverified | Install |
| cpp-classTsukiNi22/ai-utilsGenerate C++ (C++20) .hpp/.cpp files and class architectures in Tsukini's style (Xartania header, indented include guards, INCLUDE/CLASS sections, Pre-Function/Function/Operator/Constructor/Destructor blocks, libutils attributes or standard [[...]]), with empty bodies only (never the logic), then register the .cpp in the CMakeLists.txt. Also creates the main.cpp entry point in the same style. Use whenever the user asks to create, scaffold or add a C++ class, a main / entry point, interface (I*), abstract class (A*), template, struct/Type or Define header, module or set of .hpp/.cpp files. | Stars: 1 | Updated | Claude CodeCodex | Unverified | Install |