AGENT SKILLS · MISSION KIT
Useful agent skills ranked by real adoption
Browse verified skills from public repositories. Compare what each skill does, package contents, install activity, and source evidence before adding it to your agent.
- CATALOG SCOPE
- VERIFIED
- skills
- 22,822
- repositories
- 3519
- last synced
- Nov 2, 2026
suzhengk2f-flyer
Turn event details, offers, or brand notes into a single-page flyer with a scannable headline, one primary call to action, and mood-matched visual intent—not a brochure, slide deck, or poster wall. Use when the user asks for a flyer, leaflet, handout, promo sheet, open-house sheet, or print/digital one-pager for events, sales, restaurants, fitness, real estate, hiring, or community campaigns. Create flyers with AI-native design and the highest aesthetic standards, powered by the K2F format and e
- 1h installs
- 32
- GitHub stars
- 3
- Updated
- Oct 30
shadcn-uimigrate-radix-to-base
Migrates React projects and components from Radix UI to Base UI. Use when asked to migrate from radix, move to base-ui, convert radix primitives, or switch a shadcn project's base library. Handles single components ("migrate accordion") and whole projects.
- 1h installs
- 32
- GitHub stars
- 126.9K
- Updated
- Oct 29
s546126orca-cli
- Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the orca CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca stat
- 1h installs
- 32
- GitHub stars
- 0
- Updated
- Sep 25
resciencelabseo-geo
SEO & GEO (Generative Engine Optimization) for websites. Analyze keywords, generate schema markup, optimize for AI search engines (ChatGPT, Perplexity, Gemini, Copilot, Claude) and traditional search (Google, Bing). Use when user wants to improve search visibility, search optimization, search ranking, AI visibility, ChatGPT ranking, Google AI Overview, indexing, JSON-LD, meta tags, or keyword research.
- 1h installs
- 30
- GitHub stars
- 1.9K
- Updated
- Oct 25
backnotproppoteto-mode
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
- 1h installs
- 29
- GitHub stars
- 3.1K
- Updated
- Oct 28
backnotpropprinciple-explain-the-number
Apply before you measure, and before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.
- 1h installs
- 29
- GitHub stars
- 3.1K
- Updated
- Oct 28
backnotpropinterrogate
Use for \"interrogate\", \"adversarial review\", \"multi-model review\", \"challenge this\", \"stress test this code\", \"find blind spots\", or \"tear this apart\". Adversaries try to break a change or design, and only findings proven by a run survive.
- 1h installs
- 29
- GitHub stars
- 3.1K
- Updated
- Oct 28
backnotproppoteto-help
Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.
- 1h installs
- 29
- GitHub stars
- 3.1K
- Updated
- Oct 28
metabasemetabase-data-apps
Build and change Metabase data apps, the React apps Metabase serves at /apps/ from dataapps/ / in the Git repository connected through remote sync. Use when the user asks to create, scaffold, set up, or remove a data app; to show Metabase tables, metrics, or saved questions in one, or work with its generated metabase.data.ts schema; to add pages or routing; to add a form or button that writes data through an action; or to migrate an app Metabase marks Outdated, or whose npm run typecheck or npm
- 1h installs
- 29
- GitHub stars
- 50
- Updated
- Oct 10
alpic-aichatgpt-app-builder
Guide developers through creating and updating ChatGPT apps. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects, implementing tools/views, debugging, running dev servers, deploying and connecting apps to ChatGPT. Use when a user wants to create or update a ChatGPT app / MCP server for ChatGPT, or use the Skybridge framework.
- 1h installs
- 29
- GitHub stars
- 2.1K
- Updated
- Sep 18
interfacex-co-jpgenshijin
超圧縮コミュニケーションモード。原始人のように話してトークン使用量を約75%削減。 技術的正確性は完全に維持。強度レベル: 丁寧・通常（デフォルト）・極限の3段階。 「原始人モード」「短く」「簡潔に」「トークン節約」と言うか、/genshijin で起動。
- 1h installs
- 28
- GitHub stars
- 333
- Updated
- Oct 11
interfacex-co-jpgenshijin-commit
超圧縮コミットメッセージ生成。Conventional Commits形式で件名≤50文字、 「何を」より「なぜ」を重視。日本語・英語両対応。 「コミットメッセージ作って」「/commit」「/genshijin-commit」で起動。 ステージング変更時に自動起動候補。
- 1h installs
- 28
- GitHub stars
- 333
- Updated
- Oct 11
interfacex-co-jpgenshijin-compress
自然言語メモリファイル（CLAUDE.md, todos, 設定）を原始人形式に圧縮し入力トークン削減。 技術内容・コード・URL・構造は完全保持。圧縮版が原ファイルを上書き、人間可読版は FILE.original.md として保存。「/genshijin-compress 」「メモリファイル圧縮」で起動。
- 1h installs
- 28
- GitHub stars
- 333
- Updated
- Oct 11
interfacex-co-jpgenshijin-crew
原始人スタイル subagent への委譲判断ガイド。genshijin-investigator (コード位置特定)、 genshijin-builder (1-2ファイル編集)、genshijin-reviewer (diff レビュー) を inline作業 or vanilla Explore の代わりにスポーンするタイミングを示す。subagent 出力は原始人圧縮 → 主コンテキストに戻る tool-result が約60%縮小 → 長セッション持続。 Trigger: 「subagent 委譲」「genshijin-crew 使用」「investigator/builder/reviewer 起動」「コンテキスト節約」「圧縮 agent 出力」。
- 1h installs
- 28
- GitHub stars
- 333
- Updated
- Oct 11
interfacex-co-jpgenshijin-help
全 genshijin モード・スキル・コマンドのクイックリファレンスカード。 1回限り表示・モード変更なし・状態永続化なし。 「/genshijin-help」「原始人ヘルプ」「原始人の使い方」で起動。
- 1h installs
- 28
- GitHub stars
- 333
- Updated
- Oct 11
interfacex-co-jpgenshijin-review
超圧縮PRレビューコメント。1行1指摘: 位置・問題・修正。前置き削除、シグナル優先。 日本語対応。「PRレビューして」「コードレビュー」「/review」「/genshijin-review」で起動。 プルリクエストレビュー時に自動起動候補。
- 1h installs
- 28
- GitHub stars
- 333
- Updated
- Oct 11
backnotpropcorrect
Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.
- 1h installs
- 27
- GitHub stars
- 3.1K
- Updated
- Oct 28
backnotpropcreate-formal-verification-skill
Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, \"model-check this race\", \"prove this invariant\", or when concurrency, retries, state machines, parsers, or unsafe code need more than tests.
- 1h installs
- 27
- GitHub stars
- 3.1K
- Updated
- Oct 28
backnotpropin-your-own-words
Restate in your own words what you think the user's goals are and what problem they're trying to solve. Use for /in-your-own-words.
- 1h installs
- 27
- GitHub stars
- 3.1K
- Updated
- Oct 28
backnotpropketchup-video
Catch the user up like /ketchup, with a short subtitled video of slides for what happened and the waiting calls as text under it. Use for /ketchup-video.
- 1h installs
- 27
- GitHub stars
- 3.1K
- Updated
- Oct 28
backnotpropmaintain-formal-verification-skill
Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /maintain-formal-verification-skill, \"is the model still true to the code\", or after merges and refactors that touched verified code without rechecking it.
- 1h installs
- 27
- GitHub stars
- 3.1K
- Updated
- Oct 28
backnotpropmake-bot-ui
Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.
- 1h installs
- 27
- GitHub stars
- 3.1K
- Updated
- Oct 28
backnotpropprinciple-attack-the-premise
Apply when two or more fixes that share one premise have failed the same gate. Write the premise down and test it directly before you write another fix that assumes it.
- 1h installs
- 27
- GitHub stars
- 3.1K
- Updated
- Oct 28
backnotpropprinciple-experience-first
Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.
- 1h installs
- 27
- GitHub stars
- 3.1K
- Updated
- Oct 28