The catalog
608,666 rows, by stacks then stars
gengshirong1128-boop/claude-cabinet Skill
1★Cost-aware Claude model routing across Fable 5, Opus, and Sonnet. Use when a task needs Claude Code model selection, premium-model cost control, model delegation, explicit escalation gates, Fable/Opus review, Sonnet execution, or a reproducible routing and cost report.
motao123/dev-workflow-kit Skill
1★Use when a software task needs lifecycle support around coding itself: planning, debugging, CI repair, review comment resolution, browser verification, security review, ship-readiness, documentation writing, and other workflow analysis around delivery.
reason211/seqwalk/skills/seqwalk Skill
1★ repoCreate or update self-contained interactive HTML sequence diagrams that help humans understand and review code execution flows, especially AI-written or AI-modified code. Use when asked to inspect code flow, explain what calls what, visualize data movement, review AI-generated code, create architecture walkthroughs, or generate browser-validated HTML sequence diagrams with sticky participants and aligned message lines.
shashankswe2020-ux/flowforge/flowforge/deep_agents/skills/api-and-interface-design Skill
1★ repoGuides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
The same file is in 14 other repositories
dylanmccavitt/loom/skills/assembler Skill
1★ repoSets a repository up for the Factorio workflow kit or refreshes its envelope by reading the repo and generating the repo-local envelope every other kit skill binds to, plus the harness wiring and repo-specific skills and agents. Use when setting up a repo for the kit or refreshing its tracker team/project/label map, domain glossary, build/test/lint commands, PR/issue/doc templates, or repo-specific skills and agents.
keithhegit/product-frontend-design/skills/product-frontend-design Skill
1★ repoRun Product Design and Frontend Design as one UI/UX collaboration workflow. Use when the user invokes Product Design + Frontend Design, asks for a UI/UX redesign, asks to make an interface more user friendly, designs a plugin panel, or wants a product flow turned into polished frontend UI.
zcccc-mxc/codex-skill-router/examples/skills/browser-validation Skill
1★ repoUse when checking browser rendering, Playwright flows, screenshots, page display, and mobile viewport behavior. Do not use for documentation-only edits, database schema changes, or market analysis.
TaoCultivator/decision-ledger-skill/decision-ledger Skill
1★ repoUse this skill to retrieve, create, or reconcile project-owned decision records when work depends on prior accepted, rejected, or proposed choices; repeatable operational experience; incident lessons; specification decisions; or avoiding a previously failed approach. Also use it when maintaining the decision-ledger workflow itself. Do not use it for routine implementation, generic memory questions, or ordinary tool selection unless project history is materially relevant.
spacemata/codex-plugins-for-claude-code/plugins/data-analytics/skills/analyze-data-quality Skill
1★ repoAssess whether tables, query results, files, or dataframes are trustworthy enough for analysis, modeling, dashboards, experiments, or pipelines. Use for grain, freshness, nulls, duplicates, schema drift, broken joins, referential integrity, distribution shifts, leakage, backfills, source mismatches, automated quality checks, and data-quality regressions.
aryasaatvik/vite-plugin-agent-skills/examples/basic/src/skills/release-writer Skill
1★ repoWrite concise release notes from implementation notes and validation results.
Aws devops engineer professional
toddkasper/expert-skills/aws/skills/aws-devops-engineer-professional Skill
1★ repoAWS DevOps engineering — CI/CD pipelines (CodePipeline, CodeBuild, CodeDeploy), infrastructure as code (CloudFormation, CDK, Systems Manager), deployment strategies (blue/green, canary), resilient multi-AZ/multi-region design, CloudWatch monitoring and logging, event-driven incident response and automated remediation, and security/compliance automation. Use when building, reviewing, or debugging AWS delivery pipelines, IaC templates, observability stacks, or auto-remediation. Not security-first design (see aws-security-specialty) or enterprise architecture trade-offs (see aws-solutions-architect-professional). Scoped and benchmarked by the AWS DevOps Engineer – Professional (DOP-C02) blueprint.
Xuanqing visual explainer cards
xuanqing-95/xuanqing-visual-explainer-cards Skill
1★Create illustrated Xiaohongshu/Rednote knowledge-card series that combine GPT Image 2 explanatory illustrations with editorial HTML layout (serif display + IKB Blue structure + Mustard Yellow emphasis). Use when turning abstract concepts, tutorials, AI knowledge, product mechanisms, comparisons, or educational content into clear 3:4 social cards with small in-image Chinese labels, accurate outer typography, reusable layouts, and automated validation. Use this skill whenever the user mentions creating social cards, knowledge posts, visual explanations, educational infographics, Xiaohongshu/Rednote content, or illustrated explainer series — even if they don't explicitly ask for "visual explainer cards."
raydocs/fusion-deck Skill
1★Higher-confidence answers and careful execution. `/fusion` fans a hard question to a panel of top models and writes one judged cross-checked answer; `/fusion-review` audits the same way. Companions: `/fusion-auto` `/fusion-ultra` `/fusion-investigate` `/fusion-plan` `/fusion-context` `/fusion-orchestrate` `/fusion-optimize` `/fusion-refactor` `/fusion-handoff` `/fusion-remind`. Always discloses which models answered. Use whenever the user wants a multi-model / panel / ensemble answer — e.g. "run it through fusion", "fusion-review this", "fusion-plan", "fusion-context", "fusion-orchestrate", "fusion-handoff". Best for high-stakes, contested, or hard-to-reverse work.
nir211/easy-hire/plugins/cv-triage/skills/cv-triage Skill
1★ repoScreen and triage incoming job applications from the user's Gmail against a saved job description and criteria, for any role. For each applicant it gathers the CV (from the email body, a saved-attachments folder in Drive or locally, or a public LinkedIn profile via Claude in Chrome), decides Interview / Hold / Reject with an explained, confidence-rated reason, de-duplicates repeat applicants, ranks the shortlist, and spotlights standout candidates. Decisions are tracked in a local Excel file so handled candidates never reappear and Holds resurface until resolved. Runs on demand, in a loop, or as a scheduled recurring Cowork task. Use whenever the user wants to review, screen, sort, prioritize, shortlist, or go through CVs, resumes, or applicants from their inbox for a role they are hiring for, even if they don't say the word "triage".
lucyfengcl-art/video-prep/skills/video-prep Skill
1★ repoRuns the tedious cleanup pass on raw video recordings before the real edit — cut silent gaps, transcribe subtitles in any language (Mandarin by default), normalize speed, and stitch clips in natural numeric order. Use when the user drops recordings into a raw/ folder or asks to "clean up", "prep", or "edit" their clips. Outputs clean per-clip mp4 + .srt (plus an optional merged, subtitle-burned preview) ready to drop into any editor (CapCut, Premiere, DaVinci, …). This is pre-processing, not the creative edit.
ikhattab/l10n-skill/skills/localization Skill
1★ repoUse this skill whenever a task involves locale-aware formatting, validation, or display of any of the following: currency (symbol position, decimal/thousands separators), dates and times (order, separators, 12/24h), numbers (grouping, decimal mark), units of measurement (metric/imperial/regional), or addresses and phone numbers (field order, postal code format). Trigger on any of: "format for [locale/country]", "localize this", "how is X written in Y", "is this format correct for Z", "display price/date/address for [country]", or whenever user-facing content needs adapting to a specific region or locale code (e.g. de-DE, fr-CA, ja-JP). Also trigger when validating or fixing existing formatted values, generating locale-aware code snippets, or explaining regional formatting differences.
Qnn1y/paper-ingest Skill
1★Ingests a research paper or web article into the user's knowledge base. Accepts an arXiv/DOI/venue URL, a paper title, or a WeChat/Zhihu/blog link. Analyzes the content, classifies it into the user's 30-collection Zotero structure (6 main + 24 sub: SAR研究/图像超分辨率/图像复原增强/扩散模型/基础与方法/待整理), pushes to Zotero via pyzotero, and writes an Obsidian note (one-line takeaway + abstract digest + core contributions + my thinking) that auto-indexes in the Dataview dashboard. Use when the user drops a paper/article link or title and wants it absorbed into their library, or says "读这篇/存一下/入库/归类这篇".
008993368-yaz/expect-the-unexpected Skill
1★Use when the user asks what could break / go wrong / fail in a SPECIFIC scenario (e.g. "what if this webhook fires twice", "a user uploads a 2GB file"); OR gives a bounded surface (a diff/PR, one file, an endpoint, or a feature description) and wants the risky scenarios surfaced FOR them ("what should I worry about before shipping this change?"); asks to pressure-test, stress-test, or red-team a path; or wants a pre-launch / pre-ship / pre-deploy check. Works at design time and on existing code. Do NOT use for generic full-codebase reviews, "review my whole repo", or "find bugs everywhere" — that needs a bounded surface (a diff, file, endpoint, or feature), not the whole repo.
SBTopZZZ-LG/documentation-workspace-skill Skill
no license1★Use this skill whenever the user asks to bootstrap, initialize, set up, scaffold, or create a documentation workspace, docs folder, knowledge base, or note repository in an empty or near-empty directory. Triggers on phrases like "set up a docs workspace", "create documentation structure", "initialize a new docs project", "organize my notes into folders", "I want a new knowledge base", "scaffold a docs folder", or any variant the user uses to express wanting a fresh, organized, file-based documentation system. This skill creates a complete, versioned, self-contained documentation workspace with AGENTS.md, README.md, index.yaml, .gitignore, package.json, and helper scripts (format, validate, hash, reindex). It does NOT cover editing an existing workspace (the workspace's own AGENTS.md governs that), GitHub repository creation or hosting, or rendering the workspace as a UI. If the target directory already contains an AGENTS.md, the workspace is already bootstrapped — do not re-run this skill, just read AGENTS.md and follow it.
szsip239/peter-zhou/skills/peter-zhou Skill
1★ repoStudent-facing wrong-question super-teacher navigator for scanned/photo/PDF student papers. Use when the user starts Peter Zhou, asks for learning status or next actions, recognizes wrong questions, stores a mistake bank, explains mistakes, generates or prints correction practice, grades returned papers, learns a knowledge point, or reports a Peter Zhou problem from an installed user host.
yarrasys/extensions/skills/deepseek Skill
1★ repoOffload a bounded, mechanical dev task so the parent session spends none of its own context or tokens on it — a nested headless `claude` runs the full read→edit→verify loop on DeepSeek's cheaper Anthropic-compatible endpoint instead. Exists to keep grunt work (docstrings, formatting, boilerplate, tests, comments, rename) off the expensive orchestrating model; the child works in an isolated git worktree and its diff comes back as a reviewable patch (never auto-applied unless you opt in) plus a compact JSON receipt. Use when a task is simple/mechanical enough to hand off for token efficiency — not for anything needing judgment, architecture decisions, or touching sensitive paths (`.github`, secrets, `infra` are denied by default). Operations: delegate, apply, init, check, config.
Redfloor/skillsmith/tests/fixtures/skills/flawed-summarizer Skill
1★ repoHelps with various tasks.
wujiajun4/preflight Skill
1★L1: 6 content checks + 3 distribution checks. Don't just write good code — make sure people can find it. L2: full pipeline with --strict, --fix, and --distribute modes. | 中文触发:AI 工具。 Use this skill when the user mentions tool / skill / utility / AI 助手 / agent tool.
knowledgeco/handoff-tracker Skill
1★Structured decision handoffs for multi-model project orchestration. When a model finishes a turn or hands work off — especially when the next step is unclear to the operator, or the operator cannot read the code themselves — the outgoing model must not leave a dead end. It must surface the viable next-step OPTIONS it can see, make an explicit RECOMMENDATION with honest tradeoffs, and leave the CHOICE to the operator. Each handoff records the option set, the recommendation, the operator's choice, and the eventual outcome — which simultaneously keeps the operator oriented when the next step is unclear, becomes a recovery map when a chosen path fails (the untaken options are still sitting at the fork), and forms a provenance trail of exactly where human judgment steered. Use this whenever handing off work between models or sessions, whenever the next step is unclear or consequential, whenever an operator who can't read the code needs the fork framed as a decision they can actually make, or whenever a model is about to stop and owes the operator a "here's what's next" — even if the user doesn't say "handoff," "options," or "decision."
m-binimran/marketing-pack/skills/ab-test Skill
1★ repoDesign an A/B test - hypothesis, single variable, variants, sample size/duration, and the metric - and interpret results honestly. Use when optimizing a page, ad, email, or funnel step.
brainqub3/architecture-as-is/.agents/skills/as-built-architecture Skill
1★ repoUse this skill whenever the user asks to understand, map, audit, reverse-engineer, document, or reason about the architecture of an existing codebase, especially a vibe-coded, prototype, legacy, inherited, or poorly documented repo. This skill guides an agent to discover the architecture as it actually exists, not as it was intended, by combining static inspection, dependency and entrypoint discovery, safe execution, evidence-backed flow tracing, upfront scoping questions, and a timestamped readable HTML as-built architecture report.
richie-liu512/codex-update-briefing/codex-update-briefing Skill
1★ repoUse when the user asks for a Codex Desktop update briefing, cumulative update summary since the last briefing, plugin/Skill changes or recommendations, or asks what a recent Codex Desktop update changed and whether it affects normal use.
DDDDanteeeeeee/skill-radar Skill
1★Recommend which agent or Codex skills a user should install, skip, defer, or record by first inferring their real project needs and existing capability overlap. Use this whenever the user asks which skills to install, whether a skillpack is worth it, whether a GitHub repository is a real skill, how to build a personal or team skill stack, or wants a risk-aware skill recommendation instead of a popularity-based answer.
glyphs-ai/glyph/first-party/skills/agency-role-reference Skill
1★ repoPointer index for ~185 abstract role templates (msitarzewski/agency-agents, MIT). Use as starting points when hiring a specialist — never install directly.
wujiajun4/brain-sync Skill
1★L1: Keeps Memory MCP (cerebellum) and Obsidian (brain) in sync without duplication. Auto-extracts triggers+relations for fast reflexes, leaves deep docs for reasoning. L2: full pipeline, TRUST 5 quality gate, drift detection. | 中文触发:记忆同步。 Use this skill when the user mentions memory sync / brain sync / context save / 记忆管理 / 同步知识库.
tonyminibot/build-website Skill
1★Build and manage a real, hosted website for a user with Make A Website — without writing HTML or setting up hosting. Hosting, a custom domain, HTTPS, web analytics, and a contact form are all included. Best for single-page sites such as business landing/intro pages, restaurants, cafes, local businesses, portfolios, coming-soon pages, and survey or contact pages (more complex sites work too, over a few iterations). Use this whenever a user asks you to create, build, make, design, or publish a website, landing page, or web page — or to update/manage an existing one (change content, check visitor analytics, read contact-form submissions, or connect a custom domain). Linking to the user's account requires the user to approve in the Make A Website iOS app.
AkhilNam/undoable/skills/undoable Skill
1★ repoMakes software changes reversible by planning safe implementation steps, auditing diffs for rollback risk, splitting mixed changes, and creating rollback plans. Use before implementing risky changes, before opening PRs, or before merging.
powtac/skill-hosteurope-kis/hosteurope-kis Skill
1★ repoHelp administer HostEurope / KIS hosting accounts and contracts. Use for inventories, contract/domain/DNS/mail/SSL reviews, costs, renewal dates, cancellation windows, local inventory files, and explicitly confirmed preparation of cancellations, transfers, DNS, mailbox, SSL, or product changes.
skeletont638-code/a11y-sentinel/skills/accessibility-audit Skill
1★ repoUse when building, reviewing, auditing, or remediating any website, web app, or mobile UI for accessibility / ADA / Section 508 / WCAG compliance — or when handling alt text, color contrast, keyboard navigation, screen-reader support, ARIA, focus order, form labels, captions, an accessibility statement, or an ADA demand letter / lawsuit. Loads the complete WCAG 2.2 A/AA criteria checklist so every requirement is checked, not guessed.
0xkangl/skills/.claude/skills/new-skill Skill
no license1★ repo按本仓库约定在 skills/ 下创建一个新 skill——收集定位与触发方式,生成符合规范的 SKILL.md(frontmatter 规则、description 句式判定),并同步 README 的「Skills 一览」表与 npx skills add 命令块。用法:/new-skill <skill-name> [一句话定位]。
jpbaking/compose-helper/skills/shared/compose-helper Skill
1★ repoUse when creating or modifying docker-compose.yaml / docker-compose.yml in a project that contains a compose-helper script (compose-helper.sh or compose-helper.ps1), or when building, starting, stopping, or debugging services in such a project. Covers the "--profile build" convention for services that build local images, exact script command semantics, env-file discovery, and a safe edit-build-verify workflow. Trigger on: docker-compose edits, adding a service, adding a Dockerfile/build block, "image not found" errors after start, or any docker compose lifecycle task in a compose-helper project.
jassonbla/skills/skills/coding-workflow Skill
1★ repoRun coding tasks with a disciplined, PR-oriented agent workflow. Use when the user asks to implement, debug, refactor, review, or investigate code changes and the work benefits from scope framing, repository context, isolated worktrees or worker agents, validation, and concise evidence-based reporting.
uaandesign/bragi-ai-humanizer/skills/bragi Skill
1★ repoBragi(布拉吉)——把一眼假的 AI 草稿,改成对的人爱看、内行挑不出毛病的稿子。 名字取自北欧神话的诗歌与雄辩之神、众神的吟游诗人 skald:他的本事就是把话说得像人、 且看人下菜碟——为不同的厅堂、不同的听众,换不同的讲法。 这个 Skill 做三件事:1) 去 AI 味——按"破绽清单"铲掉排比堆叠、总分总骨架、空心大词、 万能过渡句这些一眼能认出 AI 的痕迹;2) 对准角色——动笔前先问"这稿子给谁看" (业务 leader / 设计 leader / 研发 leader / 运营 / 产解…),明确后按那个角色在乎的东西 重排重点;3) 逼出垂类纵深——把泛泛而谈、外行也能写的句子标出来,向你要真东西 (具体数字、真实机制、内行才知道的取舍),给了就织进去,给不了就如实标"缺料", 绝不凭空编造深度(编的深度内行一眼就看穿)。交稿前还有一道审稿:换独立视角逐句标来源, 指不出处的(串了别处的料、编造)打回;专业性只标疑点抛给用户,AI 不自认"够专业"。 两种用法同一台引擎:A) 改写已有 AI 草稿;B) 0→1——给真实素材(仓库/产物/数据)和"要产出 什么文档、给谁看",Bragi 从素材里抽真材料、搭结构、去味、对角色,素材没有的就问你或标缺料。 当用户想去掉 AI 味、让文字更像人写的、把稿子改得更像人话、按汇报对象改写、做得更有专业深度、 降低 AI 感、润色给 leader 看的文档,或想拿自己的产物/素材 0→1 产出一份汇报/方案/文档时使用。 触发词包括但不限于:去掉 AI 味、这段太 AI 了、改得像人说的、降低 AI 感、按汇报对象优化、 这稿子给 leader 看帮我改、显得更专业更有深度、别这么泛、用 bragi 改改、 拿这个 skill/产物帮我写份汇报、从0到1给设计leader写个文档。 不要用于:**没有任何素材的凭空代写**(必须给真实素材,Bragi 从料里建、不编)、纯翻译、 代码注释、与"让文字更像人/更对路/更有料"无关的编辑。
satishTheLegend/ultimate-idea-watcher-v2 Skill
1★Turns any raw or incomplete product idea into a deeply researched, gap-free, implementation-ready programme — preserves the original idea, auto-fills a product brief, runs deep research with evidence/confidence ratings, defines the full architecture, splits it into dependency-ordered phases, and produces ready-to-paste designer (Stage 1) and engineering (Stage 2) prompts with requirement traceability and security, privacy, and accessibility auditing. Use whenever the user shares a product, app, SaaS, platform, or marketplace idea — even one line like "I want to build X" or "here's my startup idea"; wants to plan, scope, research, or validate a product; wants work split into phases; wants a screen inventory, workflow map, or design system; wants design-before-code prompts; or wants to audit or continue a plan for missing requirements, contradictions, or security/privacy/accessibility gaps. Trigger even without the word "plan" — e.g. "turn this into a real product" or "what should I build first".
Aaryan-Kapoor/coding-agent-handoff Skill
1★Turn the current chat conversation into a self-contained markdown brief (a saved file or artifact) that a coding agent — Claude Code, Codex, Cursor, or similar — can execute in the user's repository. Use when the user asks to hand this off to a coding agent / Claude Code / Codex, write it up as a task or spec to build, or otherwise move the work from this chat into a coding tool to implement.
propiter/landing-craft/skills/brand-voice Skill
1★ repoTrigger: write copy, marketing, landing page text, headline, CTA, value prop, email, social, ad, anti-slop, humanize content, brand voice, tono de marca. Write persuasive on-brand copy that does not read like AI.
jspsych/skills/skills/jspsych-plugin-builder Skill
1★ repoGuide for creating jsPsych plugins following best practices. Use when the user wants to create a new jsPsych plugin, needs help deciding whether to build a new plugin or use existing ones, or asks questions about jsPsych plugin development. Covers when to build plugins, initialization with npx tool, plugin structure, testing, examples, and documentation.
iamurali/system-design-skill/skills/excalidraw-diagram Skill
1★ repoGenerate Excalidraw diagram JSON files that argue visually. Use when the user wants to visualize architectures, workflows, data flows, or concepts as .excalidraw files. Produces structured JSON that renders in any Excalidraw viewer (VS Code extension, excalidraw.com, embedded).
loshoc/LocaleFlow/localeflow Skill
1★ repoExtract localization-ready UI strings from Figma files. Use when a user asks to collect text from the current Figma page, selected frames, sections, components, or instances; compare extracted copy with existing CSV or JSON string files; deduplicate UI copy; generate stable localization keys; classify strings as new, existing, changed, duplicate, or conflict; generate translations; and export clean production-ready CSV/JSON plus one human-readable report for product localization workflows.
yuecao365/agent-codebase-analysis-skill Skill
1★Use when analyzing an LLM-agent repository, agent harness, single-agent runtime, multi-agent system, agent framework, or mature open-source agent project to understand or present its system design, runtime behavior, context/state handling, tools, permissions, memory, RAG, events, artifacts, observability, evals, coordination model, Mermaid architecture diagrams, or plain-language HTML architecture report.
davideferigato/MigraAPI/.claude/skills/api-migration Skill
1★ repoMigrates deprecated API calls to a new API version in Python and JavaScript codebases. Use this skill when the user asks to migrate code from an old API to a new API, upgrade API endpoints, or replace deprecated function calls.
Tatendaz/yapui Skill
1★View, preview, open, render, or serve any HTML file/page/mockup/prototype in the browser with a live two-way feedback loop. Use this whenever the user wants to look at HTML in a browser, see a rendered page, preview a mockup or prototype, or iterate on an HTML UI — instead of a bare `open file.html` (file:// blocks the mic + screen capture and gives no feedback channel). It serves the HTML from a local relay, injects a feedback widget (typed notes, voice dictation, screen recording, screenshots, and click-to-pick element selection), and boots a resident pre-warmed Claude agent that picks up each note the instant it is sent (~0s pickup), applies the fix, streams live "what I'm doing" status to the page, and replies in the browser. Trigger for ANY request to view / preview / serve / open / render HTML.
witczakm/konsylium/skills/konsylium-pl Skill
1★ repoWewnętrzne konsylium AI z wielu perspektyw. Meta-krok „Marszałek" czyta treść pytania i dobiera panel 3–6 person (architekt, sceptyk/red-team, pragmatyk + persony domenowe: bezpieczeństwo, integralność danych, koszt, wydajność), pyta każdą niezależnie (blind), a potem syntezuje jeden werdykt z zachowanym dissentem i sekcją „czego nie wiemy". Użyj przy nietrywialnej lub trudnej do odwrócenia decyzji, wyborze z 2–3 alternatyw, stress-teście opcji, do której się skłaniasz, przy pisaniu design doc/ADR, albo gdy model krąży w kółko. To PRE-CHECK dywergencyjny, który zasila decyzję — nigdy bramka merge (decyduje człowiek). Dla prawdziwie niezależnej bramki cross-model routuje do narzędzia konsensusu wielomodelowego, zamiast udawać niezależność jednym dostawcą.
rahulkolekardev/agentctx/skills/agentctx Skill
1★ repoMake a repository ready for AI coding agents by scanning project facts and generating AGENTS.md, CLAUDE.md, GEMINI.md, Copilot instructions, Cursor rules, repo maps, doctor reports, and task-specific context packs. Use when preparing repos for Claude Code, OpenAI Codex, Gemini CLI, Google Antigravity, GitHub Copilot, Cursor, Windsurf, Amp, Aider, Cline, Roo Code, Continue, OpenHands, Replit Agent, Vercel Skills, or other coding agents.
LevyBytes/AI-skill-drafting Skill
1★Use when creating, updating, reviewing, or validating Codex or Claude skills: drafting SKILL.md files, trigger descriptions, references/scripts/assets, gotchas, verification checks, source-digestion plans, forward tests, or skill-generation prompts, even when the user does not say skill-drafting.
jimtin/production-ai/skills/clarify-before-build Skill
1★ repoQuestion-led planning gate for implementation work. Use when the user wants a project plan, roadmap, feature plan, technical design, implementation plan, migration plan, product workflow, architecture change, or any substantial build before code changes begin. Forces the agent to repeatedly question assumptions, resolve ambiguity, identify risks and dependencies, and reach an explicit shared understanding before implementation starts. For small, low-ambiguity changes it runs a lightweight pass (assumptions stated, only blocking questions asked) instead of the full gate.
maherukhislam/postgres-auth-security-review/skills/postgres-auth-security-review Skill
1★ repoReviews and writes authentication, session-management, and PostgreSQL/Supabase database-access code for common and uncommon security mistakes before it ships. Trigger on login/signup/password-reset flows, JWT or session/cookie handling, SQL queries and migrations, RLS policies, SECURITY DEFINER functions, Postgres roles/grants, Supabase client/key usage, custom JWT implementations (crypto.subtle/HMAC), serverless/edge function routing, object storage (R2/S3/GCS), DB-backed rate limiting, or minor/guardian consent flows. Do not trigger for unrelated UI, styling, or business logic with no auth or database-access surface.
reverie2129/hive-optimization-skill Skill
1★审查或优化 Hive on MapReduce 任务(建表、HQL 查询、JOIN、数据倾斜、参数调优)时必须使用。包含 26 条规则,给出建议前必须先检查相关规则,并在回答中引用具体规则名。
Kisslotina/Steward/.claude/skills/bootstrap-notion Skill
1★ repoCreates the full Steward Notion structure from scratch — all bases with fields, relations, Area rows, filtered views, emojis — and writes the per-user base registry. Use once on first-time setup / fresh install, or when the user asks to bootstrap, initialize, or recreate the Notion bases. Requires the Notion connector with permission to create databases and pages in a chosen parent page.
orzilca/agent-handoff-skills/dist/claude-plugin/skills/continue Skill
1★ repoUse in a fresh session to resume work captured by handoff-prepare. Reads a handoff file and continues from its "Next steps". Takes an optional argument — a file path, or a name to substring-match against handoff filenames; with no argument, loads the newest handoff. Triggers on "handoff-continue", "resume handoff", "continue the handoff".
adjcjh777/agent-bus-skills/skills/agent-bus-delegate Skill
no license1★ repoSend Agent Bus messages, delegate tasks, verify visible delivery, and reply or ACK to Bus messages. Use when the user asks to send, delegate, dispatch, notify, wake, acknowledge, or reply to another agent or thread; handle pending targets; use reply_message or agent-bus reply; or distinguish durable Bus storage from visible Codex thread delivery.
LucasSantana-Dev/repaint Skill
1★Build production-grade frontend UI that doesn't read as "AI-made" — and behaves like an elite product, not just looks like one. A self-contained pipeline — research real references, lock a register + anchor, commit OKLCH tokens + distinctive type, design the interaction (feedback, forgiving input, keyboard, recovery), make it accessible and SEO-ready (semantic HTML, landmarks, alt, metadata), build, then iterate against slop + experience + a11y/SEO audits and a live browser-screenshot loop. Grounded in the industry-standard design systems (Material 3, Apple HIG, Carbon, Polaris, Fluent, Ant, shadcn) and the psychology of interface design (Gestalt, Hick, Fitts, peak-end), with manipulative dark patterns banned. Use for any page, component, dashboard, landing page, settings, data table, onboarding, or app surface — especially when output looks generic, templated, or "AI-made", feels hollow, or is inaccessible/invisible to search; aim at Linear/Vercel/Stripe/Notion quality. Ships a reference library + 23 evals.
Pointa-Labs/who-am-i-skill Skill
1★Analyze the user's OWN messages across all their local AI conversations (Claude Code, Codex, VS Code Copilot, Cursor, and more) to produce a sharp, evidence-grounded "Who Am I" self-portrait — personality, strengths, blind spots, and concrete ways to grow. Use this WHENEVER the user wants to "know themselves" / 认识自己 through their AI chat history, asks for a personality read / 性格分析 / 自我画像 / 自我反思 based on how they talk to AI, wants a report on "what kind of person am I" drawn from past conversations, or says things like "analyze my chat history and tell me who I am", "我想通过我和AI的 对话来了解我自己", "看看我是个什么样的人", or "who am I based on my prompts". Reads only local data; nothing is uploaded.
NishantJoshi00/ghostty-control Skill
1★Script-first control for Ghostty on macOS. Open named terminals, run commands, drive TUIs, wait for rendered output, capture text or screenshots, manage splits/tabs, and clean up through composable gt-* scripts. Use when a task needs a real rendered terminal or terminal workspace.
sumitaich1998/slavex/.cursor/skills/a-skip Skill
1★ repoPerforms the track A-skip drill: a rhythmic skip with a high knee drive and a small hop, traveling forward via a sequence. Use when a command mentions A-skip, a skip drill, sprint skip drill, or high-knee skip drill.