Explore skills
Showing 33091–33120 of 33445 skills
TsukiNi22/ai-utils
Stars: 1Claude CodeCodexHow Tsukini writes comments and file headers in any language - C, C++, CMake, Makefile, shell, Python, Lua, YAML (GitHub workflows), Markdown/HTML docs, and a fallback for any other language - section separators/banners, trailing vs above comments, notations, tone. Use whenever writing, adding, rewriting or reviewing comments or file headers in any file of the user (for C++ details also see cpp-comments).
TsukiNi22/ai-utils
Stars: 1Claude CodeCodexFree as much space as possible on the user's computer and in the data of Claude Code / claude-cluster - a deep scan of every ~/.cache folder, the caches of the language tools and of the Chromium / Electron / flatpak apps, build outputs and envs of old projects (never a git-tracked file), the trash, downloads (installers, archives already extracted), duplicated or big old files, core dumps, Docker / Podman (images, orphan volumes), flatpak (unused runtimes, SDKs, data of removed apps), dnf (cache, updates not installed), journals, old kernels, old Claude Code conversations, finished jobs, clean worktrees, claude-cluster leftovers - each with its size (real gain on btrfs), what it is for and what deleting it does, chosen in a QCM, then deleted for good. Use whenever the user wants to clean / free space / tidy their computer, their disk, their caches, Docker, or the leftovers of Claude Code / claude-cluster (old sessions, jobs, worktrees).
TsukiNi22/ai-utils
Stars: 1Claude CodeCodexMeasure and raise the test coverage of a C / C++ project built the cpp-tests way (GoogleTest, tests/ + BUILD_TESTS, unit_tests) - instrumented build in a copy (clang source based coverage, llvm-profdata / llvm-cov), lines / functions / branches per file, the functions never called and the line ranges never run, then new tests written module by module (cpp-tests rules) and re-measured until the coverage stops growing, and at the end always the question of a report (report skill) on what is still missing and why. Use whenever the user asks for the coverage, what is not tested, to fill / raise / maximize the coverage, or for a coverage report.
TsukiNi22/ai-utils
Stars: 1Claude CodeCodexTsukiNi22/ai-utils
Stars: 1Claude CodeCodexSet up and write unit tests for a project in any language - detects the languages and build system, reuses the test framework already in place or asks the user which framework/method to use (GTest, Catch2, doctest, Criterion, pytest, vitest/jest, cargo test, go test, bats...), then sets it up, inventories what to test, writes test files mirroring the source tree, runs them and adds the CI step. For C++ it follows cpp-tests. Use whenever the user wants unit tests, a test setup, more coverage or "test the whole project" and the project is not (only) C++.
TsukiNi22/ai-utils
Stars: 1Claude CodeCodexTsukiNi22/ai-utils
Stars: 1Claude CodeCodexTsukiNi22/ai-utils
Stars: 1Claude CodeCodexTsukiNi22/ai-utils
Stars: 1Claude CodeCodexMake a website or web app multilingual - on top of the common rules of multilingual-project (languages asked through the interactive questions, catalogs, placeholders, plurals, Intl formats, RTL, review flags) - the web part - the framework's i18n library (i18next / react-i18next, next-intl, vue-i18n, Angular i18n, SvelteKit, Astro, Django / Flask-Babel, Rails, Laravel, plain JS with Intl and JSON catalogs), URLs per language (/fr/ prefix, subdomains or domains), translated slugs, hreflang + x-default, sitemaps, html lang and dir, the language switcher (names in their own language, no flags, accessible), the first choice from Accept-Language without forced redirects, the choice remembered, SEO and social meta per language, emails and notifications in the user's language, server rendering and caching (Vary), lazy-loaded catalogs, and the legal pages in each language. Use whenever a site / web app must exist in several languages, "site multilingue", "traduire le site", hreflang, a language switcher.
TsukiNi22/ai-utils
Stars: 1Claude CodeCodexakhilvarier2000/youtube-summarizer
Stars: 0Claude CodeCodexKizuno18/dora-explores-binaries
Stars: 0Claude CodeCodexСоздание новых навыков, улучшение существующих и проверка их качества. Используй, когда пользователь хочет создать навык с нуля, отредактировать или оптимизировать существующий навык, проверить качество навыка или адаптировать его под другой кодовый агент.
diana-AI-coder/ai-skill-creator
Stars: 0Claude CodeCodexGenerate interactive HTML forms from natural language. Use when the user wants to create a form, survey, questionnaire, registration page, or feedback form. Also use when mentioning Formant, form schemas, or form building.
chriscooning/formant
Stars: 0Claude CodeCodexGenerate interactive HTML forms from natural language. Use when the user wants to create a form, survey, questionnaire, registration page, or feedback form. Also use when mentioning Formant, form schemas, or form building.
chriscooning/formant
Stars: 0Claude CodeCodexchriscooning/formant
Stars: 0Claude CodeCodexBaut aus einem einzigen Satz ein fertiges, beeindruckendes 3D-Erlebnis als eine HTML-Datei, mit Licht, Kamerafahrt, Bewegung und eigenem Ton. Drei Modi. Welt (interaktive 3D-Szene, z. B. „Cyberpunk-Straße in Tokio“), Film (animierter Kurzfilm mit Untertiteln und Musik) und Zeitreise (animierte Zeitleiste von früher bis in die Zukunft). Benutze diesen Skill immer, wenn jemand eine 3D-Szene, eine 3D-Welt, eine interaktive Szene, einen animierten Kurzfilm, eine Animation, eine Zeitreise, eine Zeitleiste zum Durchfahren, eine Visualisierung der Geschichte von etwas oder „etwas Beeindruckendes zum Zeigen oder Posten“ möchte, auch wenn das Wort 3D nicht fällt und auch bei „build an interactive 3D scene“, „make a short film about“, „visualize the history of“.
Ultra-Smashed/fable-studio
Stars: 0Claude CodeCodexTurn a script into podcast-style audio with distinct neural voices. Use whenever the user wants to convert dialogue, a conversation, an interview, notes, or any script into spoken audio / an audio file / a podcast episode. Accepts a raw script in ANY format — the user does not need to structure it. Triggers: 'make this a podcast', 'turn this into audio', 'read this as a conversation', 'generate an episode', 'text to speech for two hosts', mentions of podcast/audio/voices/narration from a script. Produces an mp3 with British hosts by default. Runs fully offline on CPU, no API keys.
jhdgeai/clodcaster
Stars: 0Claude CodeCodexRead web pages and search the web as plain text with `tbrowse` (lynx). Faster and cheaper than WebFetch for docs, articles, search results and link lists, and subagents can use it directly. Use when you need page text, a list of links on a page, or a quick search, and the page does not need JavaScript.
NubleX/atelier
Stars: 0Claude CodeCodexGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
edisonzerolam/qclaw-skill-creator
Stars: 0Claude CodeCodexWrites or optimizes prompts: asks for the rules it cannot infer, then attacks the draft against its spec. Use when asked for a new or better prompt, system prompt, agent instructions or CLAUDE.md.
HighMarck17/prompt-engineer
Stars: 0Claude CodeCodexMaps a woman's menstrual cycle onto her Google Calendar as six named windows, then keeps them accurate through a daily check-in. Use when the user wants to see her cycle in her calendar, plan around how she actually feels, set up cycle windows, report that her period started, log how she is feeling, ask which windows are coming up, or check whether something on her calendar lands in a hard week. Also use for "put my cycle in my calendar", "when should I schedule this", "my period is late", "recalibrate my phases".
michiamoalena/burning-girl
Stars: 0Claude CodeCodexWrites a production-quality README.md for any code repository, grounded entirely in the repo's real contents. Give it a repo link to clone, or paste/upload the repo's files, and it inventories manifests, CI config, build files, and code, works out what kind of project it actually is, and drafts a README using only the sections that project needs — no placeholder text, no invented badges or benchmarks, no boilerplate sections that don't apply. Works the same way regardless of language, stack, or project category. Use whenever asked to write, generate, or improve a README for a repo, or for a specific named project, in whatever wording that request takes.
Zeyad-101/Readme-writer-skill
Stars: 0Claude CodeCodexCreate and modify PowerPoint presentations (PPTX) through direct XML manipulation. Use this skill when: (1) Creating presentations from scratch, (2) Adding/editing/deleting slides, (3) Inserting images or custom shapes, (4) Applying POTX templates for consistent branding, (5) Editing existing PPTX files, (6) Working with slide layouts and placeholders, (7) User asks to make a "presentation", "slides", "deck", or mentions ".pptx". Supports all 11 standard Office slide layouts.
24111999/claude-skills
Stars: 0Claude CodeCodexProduction Stage 10 — on-demand rollup report of eng-flow/analytics.jsonl (time/token log) and eng-flow/findings.jsonl (bug counts), both incrementally written by other eng-flow skills. Reports per-story and per-stage totals, tokens by category, cycle time (elapsed vs. active), stage-transition gaps, review/QA rework cycles, and bug rate. Read-only; doesn't instrument itself.
m3dcodie/eng-flow
Stars: 0Claude CodeCodexProduction Stage 3 — takes a saved eng-flow spec and domain model and produces the technical design — tech stack, a tech-labeled system diagram, API contracts, quantified non-functional requirements, deployment topology, and ADRs. This is where technical decisions actually get made; Stages 1 and 2 deliberately deferred all of them here.
m3dcodie/eng-flow
Stars: 0Claude CodeCodexGeneral-purpose visual-verification tool wrapping the plugin-bundled Playwright MCP server — navigate a URL, screenshot, check console errors, verify a page/component renders correctly. Usable standalone by any agent/skill in this plugin, any time — not tied to a production-track stage.
m3dcodie/eng-flow
Stars: 0Claude CodeCodexProduction Stage 6 — reviews an implemented diff (branch vs. base, or a specific story's commits) across five axes before it ships. Post-implementation counterpart to Stage 3.5's pre-implementation architecture review — this one reviews actual code, not a design doc.
m3dcodie/eng-flow
Stars: 0Claude CodeCodexProduction Stage 2 — takes a saved eng-flow spec and turns its named domains into a domain model, data flows, and a conceptual system diagram. No tech stack, no deployment, no API shape — that's Stage 3. Run by an "architect" persona, after eng-flow-spec, before eng-flow-architecture.
m3dcodie/eng-flow
Stars: 0Claude CodeCodexProduction Stage 3.5 — reviews a saved architecture.md against engineering-leadership judgment before it becomes epics/stories/tasks. Catches architecture problems while they're still cheap to fix (before backlog breakdown, before implementation), not a code review — no code exists yet at this point in the track.
m3dcodie/eng-flow
Stars: 0Claude CodeCodex