85683 Skills Available

Find awesome
Agent Skills

Agent-Skills.md is a agent skills marketplace, to find the right agent skills for you.

Popular searches

duroxide-orchestrations

Writing durable workflows using Duroxide in Rust. Use when creating orchestrations, activities, workflows, or when the user mentions duroxide, durable functions, or workflow orchestration.

affandar
affandar
2

azure-cloud

Azure cloud development and operations. Use for ANY Azure task including infrastructure provisioning, data access, compute deployment, monitoring, networking, and security. CRITICAL - For deployments, ALWAYS use azd (Azure Developer CLI), NEVER use az CLI for deployments unless the user explicitly requests it. azd is faster due to parallel provisioning.

charris-msft
charris-msft
2

skill-creator

Guide 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.

keremk
keremk
2

add-replicate-model

Add new Replicate models to the Renku catalog. Fetches JSON schema, looks up pricing from replicate.com, matches/implements cost function, adds entry to replicate.yaml.

keremk
keremk
2

add-fal-model

Add new fal.ai models to the Renku catalog. Fetches JSON schema, looks up pricing from fal.ai, matches/implements cost function, adds entry to fal-ai.yaml.

keremk
keremk
2

integration-astro-static

PostHog integration for static Astro sites using SSG

PostHog
PostHog
2

create-prompt-producer

Create the definition files for the Renku Prompt Producer, which leverages an LLM to generate high-quality, structured prompts or audio narration texts consumed by downstream media generation models within the Renku video-creation blueprint.

keremk
keremk
2

prepare-r2-video

Convert a local video into a web-friendly video asset for Cloudflare R2. Inspects the source with ffprobe, encodes with ffmpeg while preserving aspect ratio, and asks for explicit confirmation before running npx wrangler upload.

keremk
keremk
2

refresh-schema-catalog

Refresh Fal and Replicate model schemas while preserving local override patches and resolving drift safely.

keremk
keremk
2

get-youtube-transcript-raw

Capture a YouTube video transcript as raw material using `ytt`, storing it in the raw/ directory with minimal metadata for later distillation.

dudarev
dudarev
2

raw-undistilled-triage

Identify raw notes in this vault that do not have corresponding distilled notes yet (based on wikilinks and front matter), and report broken raw↔distilled references.

dudarev
dudarev
2

get-web-page-raw

Capture a web page as raw material (extracted text/Markdown) with metadata, storing it in the raw/ directory for later distillation.

dudarev
dudarev
2

plan-incremental-commits

Review a mixed working tree and produce (and optionally execute) a small, logically grouped sequence of incremental git commits.

dudarev
dudarev
2

youtube-search

Search YouTube for recent videos using the python youtube_search library, especially when you need last-7-days results or want to filter by publish time without the YouTube Data API.

dudarev
dudarev
2

make-distilled

Transform raw captured content into distilled knowledge by extracting topics (outline), summary, key points, principles, patterns, entities, and quotes, storing the result in the distilled/ directory.

dudarev
dudarev
2

functional-design-creator

PRDに基づいて機能設計書を作成するスキル。docs/prd.md が存在する場合に、システム構成、データモデル、コンポーネント設計、アルゴリズム設計等を含む機能設計書を作成します。「機能設計書を作成して」「PRDから設計書を作って」「functional design を書いて」等のリクエストで使用してください。

ks6088ts-labs
ks6088ts-labs
2

glossary-creator

プロジェクト用語集を作成するスキル。docs/prd.md や docs/functional-design.md が存在する場合に、ドメイン用語、技術用語、略語、アーキテクチャ用語等を体系的に定義した用語集を作成します。「用語集を作成して」「glossary を作って」「用語を定義して」等のリクエストで使用してください。

ks6088ts-labs
ks6088ts-labs
2

doc-writer

ドキュメント執筆をサポートするスキル。ユーザーがPRDに基づいてドキュメントを作成、編集、または更新したい場合に使用します。このスキルは、docs/prd.md に記載されたプロダクト要求仕様書を参照しながら、技術ドキュメント、設計ドキュメント、ユーザーガイド、APIドキュメントなどの執筆を支援します。「ドキュメントを書く」「仕様書を作成」「ガイドを作る」などのドキュメント作成タスクに言及した場合にトリガーします。

ks6088ts-labs
ks6088ts-labs
2

marp-slide-reviewer

ローカルサーバーで起動している Marp スライドを視覚的に検証し、レイアウト問題を自動修正するスキル。「スライドをレビュー」「Marp スライドの視覚的チェック」「スライドのレイアウトを確認」「プレゼン資料の見た目を検証」などのリクエストでトリガーします。テキストの切れ目、重なり、配置問題、コントラスト不足、はみ出し、余白不足などの視覚的問題を検出・修正します。

ks6088ts-labs
ks6088ts-labs
2

agents-md-creator

AIコーディングエージェント向けの指示書「AGENTS.md」を作成するスキル。プロジェクトにAIエージェントが作業するための文脈と指示を集約するファイルを作成したい場合に使用します。「AGENTS.mdを作成」「AIエージェント用の指示書を作る」「エージェント向けREADMEを作成」などのリクエストでトリガーします。OpenAI Codex、Claude Code、GitHub Copilot、Cursorなど、複数のAIエージェントで共通利用できるオープンな標準フォーマットです。

ks6088ts-labs
ks6088ts-labs
2

skill-creator

効果的なスキルを作成するためのガイド。このスキルは、ユーザーがAIエージェントの機能を専門知識、ワークフロー、またはツール統合で拡張する新しいスキルを作成(または既存のスキルを更新)したい場合に使用します。

ks6088ts-labs
ks6088ts-labs
2

doc-review

ドキュメントレビューを実施するためのスキル。提案書、設計書、PRD、技術仕様書などのドキュメントをレビューする際に使用します。「ドキュメントをレビュー」「提案書をチェック」「設計書を確認」「この文書をレビューして」「ドキュメントの品質を確認」などのドキュメントレビュータスクに言及した場合にトリガーします。ビジネス・戦略観点、論理構造、技術的妥当性、リスク管理、表現の正確性を多角的に評価し、建設的な改善提案を行います。

ks6088ts-labs
ks6088ts-labs
2

press-release-creator

Amazon の Working Backwards 手法に基づいたプレスリリース+FAQ を作成するスキル。新サービスや新機能の企画段階で、顧客視点から価値を明文化し、開発の方向性を定めるために使用します。「プレスリリースを作成」「PR/FAQ を書いて」「Working Backwards で企画」「顧客中心でサービスを設計」などのリクエストでトリガーします。ITサービス、製品、新機能の企画・要件定義に活用できます。

ks6088ts-labs
ks6088ts-labs
2

reverse-engineering

ソフトウェアのリバースエンジニアリングレポートを作成するスキル。リポジトリの構造や機能を調査し、外部仕様・内部実装・使用方法を明確にするレポートを作成します。「リバースエンジニアリングレポートを作成して」「コードベースを分析して」「プロジェクトの構造を調査して」「システムの仕組みを解析して」等のリクエストで使用してください。新規開発者のオンボーディング、プロジェクトの理解、ドキュメント作成、将来の開発のための基礎資料として活用できます。

ks6088ts-labs
ks6088ts-labs
2

architecture-design-creator

PRDと機能設計書に基づいてアーキテクチャ設計書を作成するスキル。docs/prd.md と docs/functional-design.md が存在する場合に、テクノロジースタック、レイヤードアーキテクチャ、データ永続化戦略、パフォーマンス要件、セキュリティ設計等を含むアーキテクチャ設計書を作成します。「アーキテクチャ設計書を作成して」「技術仕様書を書いて」「architecture design を作って」等のリクエストで使用してください。

ks6088ts-labs
ks6088ts-labs
2

code-review

コードレビューを実施するためのスキル。ユーザーがコードの品質、セキュリティ、テスト、パフォーマンス、アーキテクチャの観点からコードレビューを依頼した場合に使用します。「コードレビュー」「コードをチェック」「PRをレビュー」「このコードを確認して」などのコードレビュータスクに言及した場合にトリガーします。セキュリティ脆弱性、ロジックエラー、テスト品質、パフォーマンス問題を優先順位付けして指摘し、具体的な改善提案を行います。

ks6088ts-labs
ks6088ts-labs
2

prd-creator

プロダクト要求仕様書(PRD)を作成するスキル。ユーザーがプロダクトの要件を明確にし、チームメンバー間の認識を統一するためのPRDドキュメントを作成する必要がある場合に使用します。このスキルは、Product Requirements Document の作成、編集、または既存プロダクトの要求仕様書の更新が必要な場合に使用してください。

ks6088ts-labs
ks6088ts-labs
2

marp-slide-creator

Marp を使用してプレゼンテーション用スライドの Markdown ファイルを作成するスキル。ユーザーの要望に基づいて、Marp の機能(ディレクティブ、画像構文、フラグメントリスト、テーマ設定等)をフル活用した高品質なスライドを生成します。「スライドを作成して」「プレゼン資料を作って」「Marp でスライドを書いて」「発表資料を Markdown で作成して」等のリクエストで使用してください。

ks6088ts-labs
ks6088ts-labs
2

spec-task-management

This skill should be used when the user asks to "analyze a specification", "break down a spec", "create tasks from a PRD", "decompose requirements", "generate a task list from a design document", or mentions working from specification documents. Provides comprehensive guidance for transforming specifications into structured, actionable task lists optimized for AI coding agents.

sequenzia
sequenzia
2

simple-task-management

This skill should be used when the user asks to "generate tasks from a spec", "break down a spec", "create tasks from a PRD", "decompose requirements", "generate a task list from a design document", or mentions working from specification documents. Provides guidance for transforming specifications into structured, actionable task lists organized under missions.

sequenzia
sequenzia
2

deno-debugger

Interactive debugger for Deno/TypeScript applications using the V8 Inspector Protocol. This skill should be used when investigating issues in Deno applications, including memory leaks, performance bottlenecks, race conditions, crashes, or any runtime behavior that requires step-by-step debugging, heap analysis, or CPU profiling. Provides CDP client tools, heap/CPU analyzers, and investigation tracking.

willkelly
willkelly
2

obsidian-note-formatting-skill

Create well-formatted Obsidian notes with proper frontmatter, templates, and organization. Use when users want to create notes for their Obsidian vault, document ideas or technical content, or need help structuring information in Obsidian-compatible markdown format.

RS42-AI
RS42-AI
2

ai-architect-lite

Lightweight playbook distilled from AI Architecture to keep dual-engine memory (.ai_context) and manifest dispatcher with minimal overhead; use when bootstrapping or porting the pattern into Claude Skills format.

Carl-312
Carl-312
2

dzmm-builder

Comprehensive skill for building, debugging, and optimizing DZMM.AI applications. Use this skill when users request creating interactive web apps on the DZMM platform, need guidance on DZMM API usage, or require help with existing DZMM applications. Covers AI-driven chatbots, visual novels, dating sims, content generators, RPG games, content platforms, and visual effect systems. Includes state management games, message management (reroll/edit/delete), multi-opening systems, rich text rendering, modular prompt engineering, resource reuse strategies, React/Vue to DZMM migration, and responsive mobile design.

waylon256yhw
waylon256yhw
2

pr-audit-angles

Multi-angle parallel audit of a large PR or branch before merge. Dispatches one capable subagent per angle (matched to the changed surface), each anchored to the repo's own conventions and producing a uniform Blockers / Important / New-concepts-verdict / Verified-clean report; the orchestrator verifies every candidate against current code and synthesizes one merge-readiness verdict. Use when a PR spans multiple subsystems, when you worry it introduces new concepts where patterns already exist, or when asked to "audit before merge", "review from every angle", "is this safe to merge".

propstreet
propstreet
2

pr-fix-angles

Parallel disjoint-lane fix campaign — the execution companion to pr-audit-angles. Takes a set of verified findings and fixes ALL of them across multiple subagents that edit IN PARALLEL without merge conflicts, by partitioning the findings into lanes of exclusive file ownership. A lane whose findings share a file runs as sequential stages; independent lanes run concurrently. Each agent returns a structured completed/deferred/tests report; the orchestrator owns the single final lint→build→test gate and never commits without you. Use after an audit ("fix all the findings", "patch everything blocker→minor", "make it merge-ready"), or for any many-file coordinated remediation. Triggers on "fix all findings", "fix campaign", "remediate the PR".

propstreet
propstreet
2

ask-expert

Creates expert consultation documents with code extraction, git diffs, and size tracking (125KB limit). Use when user asks to "create an expert consultation document", "prepare code for expert review", "gather architecture context", or needs comprehensive technical documentation for external analysis. Requires Node.js 18+.

propstreet
propstreet
2

analyze-deps

Analyze dependency updates and generate a changelog report with breaking changes, new features, and actionable recommendations. Use after updating packages, before planned upgrades (preflight), or to research what changed between specific versions. Triggers on "analyze deps", "analyze dependencies", "dependency update report", "breaking changes in update", "what changed in dependency update".

propstreet
propstreet
2

trim-pr

Trim a PR before merging - remove complexity that accumulated during development. Use when preparing to merge, cleaning up code, trimming unnecessary complexity, or asked to simplify a PR.

propstreet
propstreet
2

mine-history

Extract and synthesize learnings from past Claude Code session transcripts into project documentation. Use when asked to "mine history", "extract learnings from past sessions", "what patterns keep recurring", or "improve docs from history".

propstreet
propstreet
2

deep-interview

Start a structured interview to gather requirements for complex features. Use when tackling multi-layer features, validating PRDs, or defining scope for implementation.

propstreet
propstreet
2

debrief

Capture session learnings and update project docs. Use when ending a session, after completing a feature, or when asked to "debrief", "capture learnings", "update project knowledge", or "what did we learn".

propstreet
propstreet
2

update-pr

Creates comprehensive PR descriptions by systematically reviewing ALL changes - features, bug fixes, tests, docs, and infrastructure. Use when user asks to "update the PR", "prepare PR for review", "write PR description", or "document branch changes". Requires gh CLI.

propstreet
propstreet
2

academic-writing-cs

Comprehensive toolkit for writing high-quality computer science research papers (conference, journal, thesis). Provides narrative construction guidance, sentence-level clarity principles (Gopen & Swan), academic phrasebank, CS-specific conventions, and section-by-section quality checklists. Use when assisting with academic paper writing, revision, or structure planning across all stages from drafting to submission.

SipengXie2024
SipengXie2024
21

prompt-engineer

Build, analyze, and optimize LLM prompts and technical documentation. Activates when user wants to create, modify, review, or improve prompts, or when requests are ambiguous and need clarification before writing.

Shavakan
Shavakan
2

git-commit

Create git commits with succinct technical messages. Activates when user requests git commit creation.

Shavakan
Shavakan
2

sinusitis-care

Expert sinusitis consultant. IMMEDIATELY search 10+ authoritative sources (UpToDate, AAO-HNS, EPOS, Mayo, PubMed/PMC, Cleveland Clinic, Hopkins, Springer, NORD, ENT Today, USA Sinus) for ANY sinus question. Use WebFetch to read sources deeply. Mark uncertainty explicitly.

milsonson
milsonson
2

aiwf:spec-driven-development

Use when starting new features, building applications from scratch, or needing structured development workflow - provides standalone specification-first methodology without external dependencies, generates specs, plans, tasks directly, with superpowers integration for execution

moonklabs
moonklabs
2

aiwf:error-tracking

Add Sentry v8 error tracking and performance monitoring to your project services. Use this skill when adding error handling, creating new controllers, instrumenting cron jobs, or tracking database performance. ALL ERRORS MUST BE CAPTURED TO SENTRY - no exceptions.

moonklabs
moonklabs
2

aiwf:frontend-dev-guidelines

Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with features directory, MUI v7 styling, TanStack Router, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend code.

moonklabs
moonklabs
2

Page 1342 of 1714 · 85683 results

Adoption

Agent Skills are supported by leading AI development tools.

FAQ

Frequently asked questions about Agent Skills.

01

What are Agent Skills?

Agent Skills are reusable, production-ready capability packs for AI agents. Each skill lives in its own folder and is described by a SKILL.md file with metadata and instructions.

02

What does this agent-skills.md site do?

Agent Skills is a curated directory that indexes skill repositories and lets you browse, preview, and download skills in a consistent format.

03

Where are skills stored in a repo?

By default, the site scans the skills/ folder. You can also submit a URL that points directly to a specific skills folder.

04

What is required inside SKILL.md?

SKILL.md must include YAML frontmatter with at least name and description. The body contains the actual guidance and steps for the agent.

05

How can I submit a repo?

Click Submit in the header and paste a GitHub URL that points to a skills folder. We’ll parse it and add any valid skills to the directory.