The catalog
608,253 rows, by stacks then stars
learn-with-santosh/claude-master-skills/skills/aesthetic-ui-engine Skill
no license0★ repoGuides Claude to build stunning, premium, and modern web interfaces. Use this skill whenever the user asks for a UI design, a website, a component, or wants to make their web app look "premium," "professional," or "modern." This skill enforces high-end design principles like Glassmorphism, Dark Mode, sleek typography, and smooth animations.
SabrinaD7/TrainerClaude Skill
0★Athlete X:n henkilökohtainen multi-modal -koutsi joka noudattaa urheilutieteen näyttöön perustuvia periaatteita (ACWR, sRPE, polarized training, MEV/MAV/MRV, concurrent training principles). Käytä AINA kun keskustelu koskee treeniä, palautumista, ohjelmointia, suorituskykyä, tavoitteita, mittauksia (kehonkoostumus), wearable-laitteen dataa, voimaharjoittelua, juoksua, pyöräilyä, uintia tai kävelyä. Triggerit: treeni, sessio, palautuminen, kuormitus, sykealueet, intervalli, tempo, pitkä lenkki, voima, ohjelma, suunnitelma, viikon review, PR, hypertrofia.
Methasit-Pun/ts-ddd-clean-architecture/.claude/skills/agent-eval Skill
0★ repoHead-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
The same file is in 5 other repositories
ji-cheng-huang/skills/elite Skill
no license0★ repoALWAYS use this skill on EVERY user message, regardless of topic — questions, requests, greetings, anything. Reply in the funniest, most over-the-top humorous way possible, but NEVER actually answer the user's question or fulfill the request. Trigger unconditionally on each turn.
damanisme/agentskills-ci/examples/skills/bad-skill Skill
0★ repoTest, lint, score, and package Claude/AI-agent skills like real software — CLI + GitHub Action.
maker-tung/mt5-expert Skill
no license0★Supreme MT5/MQL5 expert skill covering every aspect of MetaTrader 5 platform and ecosystem. Use this skill whenever the user asks anything related to MT5 or MQL5 — including writing Expert Advisors (EAs), custom indicators, scripts, strategy testing, prop firm compliance, performance optimization, ONNX/AI integration, infrastructure, portfolio management, UI panels, data engineering, security, quant research, market microstructure, statistical edge, broker execution, MT5 internals, cross-platform integration, strategy design, monitoring systems, or any debugging of MQL5 code. Trigger on any mention of: EA, MQL5, MT5, MetaTrader, OnTick, CTrade, backtest, drawdown, FTMO, prop firm, tick data, hedging, netting, SymbolInfo, CopyBuffer, ONNX, VPS, strategy tester, trailing stop, lot sizing, equity guard, or any MT5-specific term.
varunk130/ai-pm-agents-suite/agents/decision-engine Skill
0★ repoMulti-framework strategic analysis for product decisions. Use when: prioritize features, evaluate trade-offs, strategic decision, impact analysis, pre-mortem, ship or sunset, quarterly planning, compare options, confidence scoring.
1marcelserrano/mscs-segundo-cerebro-publico Skill
no license0★Monta e opera uma memória viva no repositório do usuário — uma pasta de markdown que um LLM mixa (raw → wiki), ligando fontes e calibrando na voz do dono, pra virar artefato. Use quando alguém quiser montar um segundo cérebro, uma memória viva, uma wiki viva estilo Karpathy, ligar os pontos do material bruto, organizar conversas/pesquisa em markdown, criar um sistema que escreve na própria voz, ou instalar os comandos /mixar, /lembrar, /produzir. Dispara em "montar minha memória viva", "segundo cérebro", "wiki viva no meu repo", "mixar meu material bruto", "ligar os pontos", "sistema que escreve na minha voz", "exportei meu ChatGPT e agora". Use mesmo que o usuário cite só uma parte (captura, mixagem ou produção).
blammectrappora/baroque-art-generator Skill
no license0★any subject into dramatic baroque oil painting art with rich chiaroscuro lighting, opulent Caravaggio and Rembrandt style textures, and classical Renaissance composition. Perfect for creating baroque portraits, classical art prints, museum-style oil paintings, Renaissance-inspired wall art, old masters style portraits, and ornate historical artwork for Etsy sellers, art collectors, and classical aesthetic lovers via the Neta AI image generation API (free trial at neta.art/open).
wilson534/editorial-portfolio Skill
0★Generate a Claude-designed personal portfolio website in editorial bilingual (中/英) dark-mode style. Single-page React app with hero / methodology / timeline / awards / press / inputs / agent chat / contact sections. Trigger when the user asks to build their personal website / portfolio / 个人网站, or wants a Claude-quality "looks-like-Peng-Zhiwei's-site". Reads user context (chat, attached docs, GitHub, prior bio) and produces a deployable codebase, ideally one-shot.
aradniankou/civic-screening-skill/civic-screening-skill Skill
no license0★ repoSecurity pre-screening of applications to civil society educational programs in repressive environments. Data-source agnostic (Airtable, Google Sheets, CSV, any form tool). Triggers: "screening", "pre-screening", "скрининг", "проверка заявок", "проверить участников", "check applicants".
heichenya/heichen-skills/skills/foundry-contract-dev Skill
0★ repoComprehensive Foundry smart contract development skill with code style, naming conventions, contract structure, security guidelines, testing standards, and gas optimization. Use when working with .sol files, Foundry projects (foundry.toml), test files (.t.sol), or deployment scripts. Triggers on "smart contract", "Solidity", "Foundry", "forge", "deploy contract", "write test", "security audit".
mloki23/side-hustle-evaluator Skill
0★Stress-test any side hustle or business idea before investing time and money. Researches market size, competition, startup costs, revenue potential, time to first dollar, required skills, risks, and delivers a brutally honest go/no-go verdict with a 1-10 viability score. No API keys or paid tools required — works with web search alone. Use when asked to evaluate a business idea, validate a side hustle, assess whether something is worth pursuing, rate a startup concept, or reality-check an entrepreneurial idea.
juncoding/nextjs-trpc-prisma-starter/skills/nts-add-auth Skill
0★ repoAdd Better Auth to an existing project scaffolded with nextjs-trpc-prisma-starter that initially skipped auth. Use this when the user says 'add auth', 'add login', 'wire Better Auth', 'add user accounts', invokes /nts-add-auth, or starts asking permission/session questions in a project without auth wired. Wires up the Better Auth Prisma adapter, session helper, requirePermission helper, /login page (credentials), the auth route handler at /api/auth/[...all], and the User / Session / Account / Verification Prisma models. Updates the tRPC context to include the session and switches the example router from publicProcedure to protectedProcedure.
aksheyw/context-bridge/skill Skill
0★ repoUse when starting, continuing, or closing a Claude Code session on a multi-session project. Scaffolds a small per-project wiki (.claude/wiki/) and runs an 11-step save+sync that produces a paste-and-resume handoff prompt. Solves cross-session amnesia. Does NOT solve mid-session context bloat — use /strategic-compact for that.
DesiredPathConsulting/clear-copy/skills/clear-copy-marketing Skill
0★ repoUse when writing or revising marketing/consultant/editorial prose for human readers (landing pages, hero copy, About pages, services pages, founder letters, blog posts, newsletters, packet content, longform articles). Calibrated against a DTC-consultant corpus (shorter sentences, higher Flesch, lower abstract-noun ratio than legal prose). Skip for code, code comments, commit messages, README, CLAUDE.md, structured data, JSON-LD, developer documentation, Privacy/Terms/DMCA/legal disclaimers, bar-journal prose (use clear-copy instead).
liberastudio-mx/skill-ui-ux-Libera Skill
no license0★UI/UX checklist and decision framework for web and mobile. LIBERA Studio fork focused on accessibility, interaction, responsive layout, performance, typography, color, forms, navigation, charts, and pre-delivery review. Style, palette, and typography databases available via local scripts when installed.
indradhanush/skills/plugins/asdf-go-setup/skills/asdf-go-setup Skill
0★ repoInstall and configure gopls for a Go project that uses asdf to manage the Go version. Use this whenever gopls fails to start for a project, an editor reports "No version is set for command gopls", or a new Go project needs LSP set up with asdf. Accepts a project path as args; detects the correct Go version from .tool-versions or go.mod automatically.
AntonioTimo/skillchecker Skill
0★Audits any Claude Code skill before you install it — flags malicious patterns (data exfiltration, persistence, obfuscation, description-vs-behavior mismatch) and sloppy patterns (overbroad allowed-tools, prompt injection vulnerabilities, missing input validation, predictable temp paths). Outputs a 🔴/🟡/🟢 verdict with concrete diffs for fixable issues, or refuses installation for malicious ones. Use before adding any third-party skill to ~/.claude/skills/.
rundrill/rundrill-kazakh/skills/kazakh-coach Skill
no license0★ repoPersonal Kazakh-language coach. Subcommands: status | diagnose | practice | update | profile.
anoop04singh/scaffold-skill/.claude/skills/scaffold Skill
no license0★ repoConvert a research paper into an implementation-first engineering roadmap and starter code scaffold. Use when the user provides a CS, blockchain, cryptography, distributed systems, or ML paper and wants to build from it.
isatuncer/ClaudeCodeCTO/decisions/assets/skills/project-lifecycle Skill
no license0★ repoClaude Code'un projeyi baştan sona yönetmesini sağlayan 8 fazlı yaşam döngüsü orkestratörü. Kullanıcıyı Discovery → Planning → Design → Build → Test → Document → Ship → Maintain yolculuğunda yönlendirir, her fazda uygun agent'ları ve skill'leri çağırır.
forsonny/DG-Anvil/skills/authoring-skills Skill
0★ repoMeta-skill governing every change to any skill file. Requires a RED-then-GREEN subagent pressure transcript before a skill change is accepted.
alphilippo/alignment-os Skill
0★Système d'alignement personnel avec 4 modules — purpose clarifier (clarifier ce qui compte vraiment au-delà des récits sociaux), ethics filter (passer une décision au filtre de ses valeurs déclarées), discipline reinforcement (identifier les patterns de dérive et les corriger structurellement), life audit (audit trimestriel ou annuel sur cohérence vie/valeurs). Utilise cette skill dès que l'utilisateur dit "je sais plus pourquoi je fais ça", "qu'est-ce qui compte vraiment", "j'ai perdu le nord", "cette décision me grise mais me gêne", "je tiens pas mes engagements avec moi", "je dérive sur X depuis longtemps", "fin d'année/trimestre", "bilan de vie", "suis-je aligné", "j'ai l'impression de trahir X". Pas de développement personnel creux, pas de citations gourou, pas d'émojis 🙏. À la place des questions dures et exercices d'écriture structurés. Garde-fou obligatoire sur signaux de détresse profonde.
viktor-milev/claude-prompt-optimizer Skill
0★Rigorous mode prompt optimizer — audits a polished prompt and rewrites it to elicit state-of-the-art output from Claude. Auto-triages every input into OUT OF PURVIEW / BORDERLINE / IN PURVIEW and routes to a band-appropriate output path; rigorous optimization (9-dimension diagnostic, archetype detection, Claude-specific capability activation) is applied ONLY to IN PURVIEW prompts. Simple prompts are returned substantially unchanged with a triage note. Use whenever the user pastes a prompt and asks to optimize, improve, rewrite, restructure, sharpen, audit, score, or diagnose it. Trigger phrases include "optimize this prompt", "audit this prompt", "score this prompt", "diagnose this prompt", "PO this", "run this through the optimizer", "sharpen this prompt", "level this prompt up". Best for prompts that deserve rigorous evaluation and a full diagnostic. For messy dictated input or flow-state work, use prompt-optimizer-flow instead. Do NOT trigger when the user wants the prompt EXECUTED rather than optimized.
BohanCui/Deck-Lens Skill
no license0★Use this skill to choose the right narrative lens for a presentation based on audience, context, and goal, then generate the matching slide structure, PPTX, or speech script. Triggers include "make me a slide deck", "prepare a pitch", "help me present X", "write a speech script", "build a presentation", "帮我做个PPT", "帮我写汇报", "做个presentation", "写个演讲稿", "我要汇报", "比赛要交PPT". Also triggers when the user describes a product, feature, or project they want to present — even without saying "PPT". Always run this skill before generating any presentation content.
decebal/curated-claude-skills/skills/allsource-prime/pr-atom-reviewer Skill
no license0★ repoReview a local git branch as a pull request with a bias toward minimum disruption and minimum reviewer scope. Splits sprawling PRs into independently-mergeable atoms of work — each one a single end-to-end behaviour describable in 2-3 sentences, each shippable to the trunk on its own without any other atom in the plan being merged first — and demands a screenshot/video/recording proving the verifiable acceptance criterion. If the AllSource Prime MCP server is available (`prime_*` tools), the skill recalls prior reviews of the same repo to calibrate its judgement and records the current review for the next one. Use this skill whenever the user asks to review a PR, review a branch, prep a PR for review, check if a branch is ready to merge, or mentions "this PR is too big", "split this PR", "atomic commits", "scope creep in PR", "PR review checklist", or anything about getting a branch in shape before peers look at it. Trigger even if the user just says "look at my branch" in a code review context.
ChenxDeng/pitch-your-proj Skill
no license0★为当前项目生成一份产品介绍 pitch,像给别人安利一个好工具一样。直接输出可复制文本,支持长短两种篇幅。
jy1529098645-gif/Cat_paper_review Skill
0★Simulate a full academic peer-review panel on a draft — examine a manuscript through five independent review lenses (significance, rigor & validity, evidence, argument, clarity), with the methodological criteria adapted to the paper type (CONSORT / STROBE / PRISMA / COREQ / Toulmin), a rebuttal round, a moderator, and a chief editor, then deliver a referee letter plus a scored verdict (Accept / Minor / Major Revision / Reject). Use this skill WHENEVER the user wants critical feedback on their own academic writing: "review my paper / essay / thesis chapter", "give me peer review on this draft", "is this ready to submit?", "what would a reviewer say about my manuscript", "critique my research proposal", or pastes a draft and asks how to improve it. Trigger even when the tool isn't named. Feedback is calibrated to the draft's stage (final / working / sketch / student) so a student essay isn't judged like a journal submission.
risal-ea/code-crack/crack-seer Skill
no license0★ repoScan a project codebase, detect all security vulnerabilities, and generate SECURITY_REPORT.md with categorized risks
mccarthy606/claude-operator-stack/skills/case-study-anonymiser Skill
no license0★ repoApply the operator's redaction playbook to a draft case study, blog post, or public artefact, replacing real product names with `Discipline A/B/C` style aliases, stripping URLs and API keys, and returning a redacted draft plus a substitution diff.
brandonuttley/project-forward/skill Skill
0★ repoUse whenever the user is planning, running, recovering, or producing artifacts for any project, program, or marketing initiative — including CRM migrations, ERP rollouts, system implementations, transformations, launches, vendor/RFP selection, stalled or inherited projects, stakeholder tangles, scope changes, or anywhere they say 'I have no idea where to start,' 'where do I begin,' 'this project is a mess,' or 'I need to write up a [charter / RAID log / status report / scope memo / campaign brief / RFP scorecard / etc.].' Engage proactively when the user is wrestling with a multi-stakeholder effort, even if they don't frame it as project management. Produces real artifacts populated for the user's situation, surfaced through diagnostic conversation rather than dumped on first request. A PMP-grounded toolkit drawn from Brandon Uttley's 20+ year career across enterprise transformations, agency leadership, and startup growth.
dimayip/socratic-design Skill
0★A general-purpose Socratic facilitation framework that guides users from a vague idea to a concrete, decision-locked design document. Use this skill whenever the user says things like "帮我设计 XX"、"我有个想法但还不清楚"、"帮我把需求理清楚"、"帮我想明白"、"help me think this through"、"how should I architect this"、"帮我写个 PRD / RFC / 技术方案 / 设计文档",especially when key decisions are still fuzzy (acceptance criteria, scope boundaries, role边界, integration points, etc.). The skill runs a 4-layer workflow — Capture Context → internalized brainstorming discipline → Socratic A/B/C/D questioning with dependency ordering → deliverable schema organization — and produces whatever fits the real audience (PRD / Design Doc / RFC / Kickoff checklist / ADR / One-Pager), not a fixed format. It is subject-agnostic (product features, internal tools, platform refactors, AI systems, workflows, governance, data pipelines, anything where decisions need to be locked before writing) and fully self-contained — it internalizes Socratic brainstorming discipline and mainstream design-document schemas, so it does not delegate to other skills.
drsreekrishnan/bar-chart-race-skill/skills/bar-chart-race Skill
0★ repoCreates an AI-powered, animated Bar Chart Race visualization that lets users compare how any set of entities (companies, countries, products, technologies, sports teams, etc.) have evolved over time. Use this skill whenever the user wants to visualize rankings or relative sizes changing over time — even if they don't use the exact words "bar chart race". Trigger for requests like: "show me how X has grown compared to Y over the years", "visualize the rise of tech companies", "which countries had the biggest GDP over time", "animate the history of streaming services", "compare programming language popularity over time", "show market share changes", "who was winning the smartphone wars each year", or any request involving a time-based ranking competition between multiple entities. Always use this skill when the user wants a dynamic, animated comparison across years — don't just describe what the chart would look like, actually build it.
daniel8824-del/claude-planning-system/metis-review Skill
no license0★ repoPre-planning consultant — gap analysis and guardrail generation before the planner runs. Catches blind spots the planner (Prometheus) missed and passes them as Directives. Named after the Greek goddess of wisdom, prudence, and deep counsel. Use when: plan validation, gap analysis, complex scope clarification, ambiguous requirements before planning, quality gate before prometheus-planning. Do NOT use for: simple single-file tasks, direct implementation requests.
blammectrappora/manga-panel-generator Skill
no license0★Generate professional black-and-white manga panels and comic pages with dynamic poses, screentones, and authentic Japanese manga art style. Perfect for manga artists, doujinshi creators, webtoon storyboards, comic writers, and anime fans who want to illustrate scenes, action sequences, or character moments in classic shonen, shojo, or seinen manga aesthetics via the Neta AI image generation API (free trial at neta.art/open).
Iec61131 3 motioncontrol melsec
mokouliszt/iec61131-3-motioncontrol-skill/skills/iec61131-3-motioncontrol-melsec Skill
0★ repo三菱電機 MELSEC iQ-R シリーズの **PLCopen Motion Control FBライブラリ** を使った STコードを書くためのSkill。シンプルモーションユニット(RD77GF, RD77MS)と、 CC-Link IE フィールドネットワーク マスタユニット(RnENCPU, RJ71GF11-T2, RJ71EN71)+ MR-J4-GFサーボの構成に対応。 対象ライブラリ: - **MotionControl_RD77** (RD77GF, RD77MS 用、26FB) - **MotionControl_J4GFIO** (RJ71GF11-T2, RJ71EN71, RnENCPU, RD77GF 用、12FB) 本Skillは「STコードを書く」ところまでを担当。FBそのものは三菱公式から ダウンロードする内容保護形式のライブラリファイル(.mslm)に同梱されており、 本Skillは生成しない。STコードからエンジニアリングツール用XMLへの変換は jiecc-skill に移譲する。 ## 起動する依頼パターン ### 1. RD77 / J4GFIO のSTコード作成依頼 - 「RD77GFで軸を動かしたい」「RD77MSで原点復帰させて」 - 「シンプルモーションでPLCopen FBを使って位置決め」 - 「RJ71GF11-T2 + MR-J4-GF でサーボ制御」 - 「RnENCPU でCC-Link IE Field 経由でモータ動かす」 - 「PLCopen の MC_Power, MC_MoveAbsolute を呼び出すSTを書いて」 ### 2. PLCopen Motion Control FB の使い方の質問 - 「MC_Power と MC_MoveAbsolute の違い」「Execute型 vs Enable型」 - 「AXIS_REF と AXIS_REF_J4GF の違い」「MasterModule の値」 - 「PLCopen 状態遷移(Disabled / Standstill / DiscreteMotion 等)」 - 「軸エラーの読出しと復旧(MC_ReadAxisError, MC_Reset)」 ### 3. ユニット選定・構成相談 - 「RD77GF と RD77MS の違い」「RJ71GF11-T2 と RJ71EN71 の使い分け」 - 「シンプルモーションユニットを使うならどのライブラリ?」 - 「CC-Link IE Field マスタユニットで使えるFBは?」 - 「RD77GF + J4GFIO 併用時の注意点」 ### 4. ライブラリ取込み・設定の質問 - 「MotionControl_RD77.mslm のダウンロード先」 - 「ライブラリの登録手順」「マクロ型 / サブルーチン型」 - 「G_stLinkIEF のグローバルラベル設定」 - 「サーボパラメータ PA19 を 00ABh に設定する理由」 ### 5. エラー対応 - 「ErrorID 1100 とは」「1101 / 1200 / 1203 / 1207 のエラー」 - 「MC_Reset の使い方」「軸エラー復旧シーケンス」 - 「サーボアラームと FB エラーの違い」 ## 起動してはいけない依頼パターン - **RD78G(H) / モーションCPU の依頼** — 別ライブラリ(MotionControl_RD78)であり、 本Skillの対象外 - **MR-J4-A / MR-J4-B 系(CC-Link IE 非対応)の依頼** — SSCNETIII/H 直結や アナログ・パルス列指令は対象外(RD77MS 経由でのSSCNETIII/H は対象内) - **iQ Monozukuri 製品単独の依頼** — 本ライブラリと組み合わせる場合のみ対応 - **オムロン・キーエンス・CODESYSの PLCopen FB** — 本Skillは三菱電機専用 ## 暗黙の連携 本Skillで生成したSTコードを GX Works3 用 XMLに変換したい場合、ユーザーが 「XMLにして」「GX Works3 にインポートしたい」と依頼すれば、 [jiecc-skill](https://github.com/mokouliszt/jiecc-skill) に自然に引き継がれる。 ST言語そのものの仕様(データ型・制御構造・標準POU)に関する質問は、 [iec61131-3-st-skill](https://github.com/mokouliszt/iec61131-3-st-skill) を併用すること。
datadata-team/datadata-skills/skills/datadata-dql Skill
no license0★ repo本技能包含了 Datadata DQL 查询脚本语言的完整参考文档,当使用 Datadata DQL 脚本时,**必须先加载本技能**。 Write DQL data processing scripts for the Datadata platform — a Starlark-based extended scripting language supporting DataFrame/Series operations, SQL queries, HTTP requests, and more. Use when the user needs to write data transformation, data cleaning, data generation, or custom data processing logic.
Rockfish-Data/tacklebox/skills/generate-from-schema Skill
0★ repoGenerate synthetic datasets from a schema specification using the Rockfish SDK. Use when a user wants to create synthetic tabular or time-series data with specific structure — independent or derived columns, state machines, timeseries, entity relationships (including composite foreign keys), or realistic PII-like values (names, emails, addresses, SSNs) via NamedEntityProvider. Trigger on phrases like "generate synthetic data", "fake data from a schema", "create a test dataset", "GenerateFromDataSchema", or mentions of entity/foreign-key/state-machine data.
caojia321/mifi-skills/skills/mi-car-trial Skill
0★ repo根据用户描述(车型名、总车价、首付金额或首付比例、期数),调用小米天星金融 af-portal-api 的免登录聚合试算接口,返回所有可选产品方案及每个方案的试算结果。 本技能仅适用于小米汽车(小米 SU7 / SU7 Pro / SU7 Max / SU7 Ultra / YU7 等系列), 不适用于小鹏 / 蔚来 / 理想等其他品牌。 触发词:试算、贷款方案、聚合试算、我想买、小米SU7、小米YU7、购车方案、月供。
The same file is in 1 other repository
zavora-ai/skill-document-management Skill
no license0★Manage documents across Google Docs, Drive, Notion, and OneDrive/SharePoint — create, search, edit, export, comment, and share. Use when creating documents, searching files, editing content, sharing with teams, or exporting to PDF/DOCX.
ggsq003-png/low-frequency-thread-monitor Skill
0★低频巡检 Skill for ordinary non-Goal Codex controller windows that need active, ETA-aware monitoring of background worker/review/planning threads. Use automatically when a controller reads, checks, or inspects another Codex conversation thread/window, including 已读取对话线程, 读取对话线程, read_thread, list_threads, or background thread status checks. Keeps monitoring active until a terminal state, reads minimal status, reduces context pollution and token spend, avoids over-polling, and minimizes wasted waiting time.
colachg/skills/plugins/colachg/skills/gitmoji-commit Skill
no license0★ repoPlan and create git commits in the Gitmoji + Conventional Commits style — a leading emoji (✨, 🐛, ♻️ …) plus a conventional type, like "✨ feat: add avatar upload". Splits a working tree into a clean sequence of reviewable, logically-grouped commits, isolates lockfiles into their own final commit, and runs the signed git commands. Use whenever the user wants help committing changes, writing/improving a commit message, asks "how should I commit this", wants to break work into reviewable commits, or mentions gitmoji/git-emoji/emoji commits. Shows the plan, then runs git add and git commit itself.
Non verbal intention interpreter
goodispeter/non-verbal-intention-interpreter Skill
0★Produce structured bilingual observation reports that transform visible posture, gaze, and environmental details into formal non-verbal intention interpretations.
Shankulkarni/RN-Lib-Claude/plugins/rn-lib-claude/skills/animations Skill
no license0★ repoUse when implementing animations or gestures in a React Native library — GPU-only properties, Reanimated v3/v4 worklets, useDerivedValue, GestureDetector press states, React Compiler compatibility.
charlieai-co/email-design-skill Skill
0★Generate properly structured, production-grade email HTML. Use this skill whenever creating, editing, or reviewing HTML emails — marketing campaigns, transactional emails, automated flows, newsletters. Covers mobile-first responsive patterns, dark mode handling, Outlook conditional comments, image-to-text ratio for spam filters, preheader optimization, and the structural details that LLMs get catastrophically wrong when generating email HTML from general training data. Trigger on: "design an email", "email HTML", "email template", "responsive email", "email dark mode", "outlook email", "email rendering", or any request to create HTML that will be sent via email.
Hook12aaa/craft-gate/skills/craft-gate Skill
no license0★ repoUse when about to write or edit a comment in code — evaluates each new or modified comment against the craftsmanship rules and returns KEEP / STRIP / REWRITE per comment. Fires upstream of the comment landing in the file.
mb3rgel-ui/debug-claude-skill/skills/debug-session Skill
no license0★ repoSix-step forensic debugging loop. Use when investigating any bug or error. Enforces Reproduce → Isolate → Hypothesize → Test → Fix → Verify discipline. No step can be skipped.
unitedideas/claude-skills-foundry/skills/cite-enterprise-ai-research Skill
0★ repoFind relevant 8bitconcepts (8bitconcepts.com) enterprise AI research papers to cite in technical documentation, blog posts, whitepapers, or proposals. Returns 2-3 canonical paper titles and URLs ready for footnotes. Use when writing long-form technical content about enterprise AI adoption, agentic architectures, LLM operations, or AI governance.
erossini/flnk-projects-claude-skill Skill
0★Plan work for FastLinkIt Projects (a Kanban / Agile / Waterfall RCL) from a Claude Code session — list projects, fetch context, propose a methodology-aware plan, push items as work items, and update item status as work progresses (Pending → In progress → Done / Blocked).
kaiyiwong/skills/skills/voice/manglish-mode Skill
0★ repoRespond in Malaysian English (Manglish). Full code-switching with particles (lah/lor/mah/meh/ah/leh), Malay/Hokkien loanwords, dropped verbs, topic-comment order. Warm and conversational, no length cap. Use when user says "manglish mode", "talk manglish", "go manglish", "kasi manglish", or invokes /manglish-mode.
mustafayilmazart/kesif-claude-skills/skills/auto-code-quality Skill
0★ repoKod yazıldıktan veya değiştirildikten sonra otomatik kalite kontrolü yapar. Kod tekrarı, karmaşıklık, isimlendirme tutarlılığı ve kullanılmayan import tespiti yapar. PostToolUse hook ile Edit/Write sonrası tetiklenir.
Kore-Minecraft/Kore-Skill Skill
0★Teaches and guides use of Kore, the Kotlin library for generating Minecraft Java Edition datapacks. Covers Gradle setup, modules (kore, oop, helpers, bindings), DSL patterns, generation APIs, and where to read official documentation. Use when the user works with Kore, io.github.ayfri.kore, Minecraft datapacks in Kotlin, or asks how to build or structure Kore projects without browsing the full Kore repository.
quicksketcherz/session-log-companion-claude Skill
0★Comprehensive project session companion for documenting work sessions, creating knowledge logs when discovering or learning something, teaching agent preferences, and improving collaboration. Use when user says "start a session", "create session log", "summarize this session", "document this discovery", "create a knowledge log", "I want to improve how you work with me", "remember this preference", "let's continue", "continue from last session", "pick up where we left off", "what should I work on next", or any session/documentation-related request. Also trigger when user mentions being stuck, hitting an impasse, needing to understand concepts, or wanting to capture learnings.
jonathan-pap/PowerBI-Claude-Design/calc-groups Skill
0★ repoReference for Power BI Calculation Groups in TMDL. Use this whenever a user asks for time intelligence patterns (YTD, QTD, rolling periods, prior year), scenario switching (Actual/Budget/Forecast), currency conversion, or any pattern where the same transformation needs to apply dynamically across many measures. Always consult this before writing individual YTD/PY/Rolling measures from scratch — a calc group is the correct architecture and eliminates boilerplate at scale.
alexcsl/ideaforge Skill
0★Generate and validate startup, product, or project ideas from a topic or direction. Spawns a parallel ideation swarm (persona agents plus a synthesizer) that grounds ideas in real problems found on the web and region-appropriate communities, verifies the cited sources, then runs a validation council (critics, anonymous peer review, chairman) that filters and ranks survivors. Optionally refines the top idea through a YC-style office-hours pass. Works in any language and region. Outputs a ranked shortlist and a visual HTML report. Trigger on "forge ideas", "ideate on", "generate ideas for", "idea swarm", "brainstorm and validate".
matteorondina/deliberato-skill-claude Skill
0★Skill in italiano per decisioni strategiche complesse. Council di advisor AI specializzati, peer review anonima, sintesi del chairman. Per founder, manager e professionisti italiani. Due velocità: Full Council (5 advisor + peer review) e Fast Council (3 advisor, risposta rapida). TRIGGER FULL COUNCIL: "delibera questa decisione", "convoca il council", "council questa decisione", "fai partire il council", "passa al council", "delibera questa scelta", "metti alla prova questa decisione", "stresstest questa scelta", "demolisci questa idea", "trova i buchi in questo piano". TRIGGER FAST COUNCIL: "check questa decisione", "parere rapido", "analisi rapida", "check rapido", "quick council", "parere veloce". TRIGGER CONTESTUALI (Full Council, solo con decisione reale e trade-off significativi): "devo decidere se X o Y", "non so se conviene Z", "vale la pena W", "mi conviene", "che faccio tra A e B", "sono convinto di fare X ma voglio un contraddittorio", "ho già deciso, dimmi dove sbaglio". NON TRIGGERARE su: domande factual, scelte triviali, richieste di scrittura, opinioni senza decisione strutturata, task di esecuzione tecnica. Modalità: Marketing & AI Strategy, Pricing, Hiring e Team, Direzione Strategica, Partnership e Distribuzione, Capitali e Finanza.
GRIDLOCK-NYC/claude-skills/skills/5x5 Skill
0★ repoIterative research protocol — up to 5 rounds of 5 parallel research agents (25 total). Each round's findings shape the next round's questions. Final output is a synthesized implementation plan, not code. The orchestrator researches nothing directly — subagents do all research. Use when user says '5x5', 'five by five', 'delegate this', 'research this deeply', or wants parallel agents exploring a complex topic. Do NOT use for simple single-file changes or quick questions.
Mothilal-M/hyperframes/.agents/skills/claude-design-hyperframes Skill
no license0★ repoUse when running inside Claude Design specifically. Produces a valid, brand-accurate HyperFrames video draft using pre-valid skeletons. For Claude Code / Cursor / Codex, use the `hyperframes` skill instead.
myl7/changelog-skill/changelog Skill
0★ repoUse when creating or updating the changelog (CHANGELOG.md).