85369 Skills Available

Find awesome
Agent Skills

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

Popular searches

pr-code-review-and-pr-draft-comment

Review a PR with the code-review skill, then post that feedback as inline draft comments with the pr-draft-comment skill. Use when asked to review a PR and leave the findings as pending/draft inline comments.

leighmcculloch
leighmcculloch
1

metadata-naming

Define, apply, or review a reusable metadata-based filename standard for files, folders, inventories, archives, and generated catalogs. Use when the user wants to extract a naming convention into a standard, normalize filenames, choose between human-readable and machine-friendly naming, or create naming rules for repositories, skills, software inventories, snapshots, and long-lived records.

luw2007
luw2007
1

skill-yao-manager

|

luw2007
luw2007
1

skill-selector

通用 skill 选择器。通过 ai-skills CLI 下载候选 skill 源码到临时目录,基于 SKILL.md + 代码的深度分析构建决策树,引导用户在 1-3 轮交互内选定最合适的 skill。当用户面对多个功能相近的 skill 不知选哪个时触发。

luw2007
luw2007
1

skill-iter

|

luw2007
luw2007
1

see

repo-brief Clone a GitHub repository to ~/ai/ and generate a structured technical brief for understanding how the project is implemented — architecture, core mechanisms, design decisions, failure modes, and a guided comprehension path. Use when the user provides a GitHub repo URL and asks for analysis, a brief, a report, or wants to understand a project's implementation principles.

luw2007
luw2007
1

rtk-rewrite

>

luw2007
luw2007
1

octocode

AI-powered code indexer with semantic search, knowledge graphs (GraphRAG), and persistent memory system. Use when you need to (1) perform semantic code searches across large codebases, (2) analyze file relationships and dependencies through GraphRAG, (3) store and retrieve code insights with memory system. This skill uses Bash to call octocode CLI directly with automatic index management.

luw2007
luw2007
1

exploration-tree

|

luw2007
luw2007
1

fast-rebase

>-

luw2007
luw2007
1

favorites-curator

Build and maintain a local favorites catalog from installed repositories, apps, skills, extensions, and hooks. Use when the user asks to create, refresh, curate, scan, or summarize a favorites collection, software inventory, skill inventory, or daily digest of useful local resources.

luw2007
luw2007
1

langextract-search

集成智谱搜索、DuckDuckGo 搜索和多模型结构化提取的完整工作流。

luw2007
luw2007
1

worktree-cleanup

>-

luw2007
luw2007
1

cli-help-layers

|

luw2007
luw2007
1

prd-to-json-implementation

Transform PRD specifications into structured PRD.json files with reference documents, or implement existing PRD.json user stories. Use when user asks to convert PRD to PRD.json with decomposition into user stories and tasks, or implement one or multiple user stories from an existing PRD.json. Handles creating PRD.json with reference_document metadata, implementing tasks sequentially with status updates, running tests including TypeScript, stashing after each completed US, and making a single final commit.

seb7152
seb7152
1

rfp-json-analyzer

Analyze RFP JSON exports to score suppliers, calculate weighted rankings, generate syntheses, compare responses, and identify risks. Use when working with RFP evaluation data in JSON format (requirements with weights, supplier responses with scores). Supports executive summaries, detailed category analysis, pairwise comparisons, and risk identification using weighted scoring methodology.

seb7152
seb7152
1

coverage

Collect and enforce code coverage using Deno

sachitv
sachitv
1

test

Execute the project test suite using Deno

sachitv
sachitv
1

lint

Check for style and static analysis warnings using Deno lint

sachitv
sachitv
1

fmt

Format TypeScript sources using Deno formatter

sachitv
sachitv
1

python-code-style

Professional Python code style enforcement for generation and review. When Claude needs to work with Python code for: (1) Generating Python code, scripts, functions, or classes, (2) Reviewing or auditing existing Python code, (3) Refactoring Python code, (4) Creating .py files, or any Python coding tasks.

pillarliang
pillarliang
1

text-to-diagrams

Given a text, analyze its content and generate one or more structured diagrams (HTML + inline SVG) into a single HTML page plus per-figure SVG files. Triggers on "把这段文字画成图 / 给这段话配图 / 文本转图表 / 帮我把这段内容做成图 / make diagrams from this text / visualize this".

pillarliang
pillarliang
1

orchestra-gherkin

Generate Gherkin scenarios from an orchestra PRD or spec — produces Feature/Scenario blocks in fenced gherkin markdown. Use when translating acceptance criteria or implementation steps into executable BDD scenarios.

mpazaryna
mpazaryna
1

orchestra-merge

Merge a reviewed implementation branch into main — resolve conflicts, close the work item, and clean up the branch. Use when an implementation has passed review and is ready to ship.

mpazaryna
mpazaryna
1

orchestra-milestone

Review milestones and project progress — diff materials table against repo state, surface gaps, check for orphaned work items, and propose next actions. Use when the user asks about milestones, project status, what to work on next, what's left to do, or wants to check progress on the roadmap.

mpazaryna
mpazaryna
1

orchestra-plan

Planning conductor — runs the full PRD → Spec → Gherkin loop in a single interactive session with human approval gates. Use when starting new work from a ticket or brief, or resuming an in-progress planning session.

mpazaryna
mpazaryna
1

orchestra-prd

Define the what and why for a piece of work — objective, success criteria, materials table, and context. The foundational Score document before any spec is written. Use when a piece of work needs to be scoped before execution — whether surfaced by a milestone review, a ticket, a stakeholder request, or a spike finding.

mpazaryna
mpazaryna
1

orchestra-program

Explain what Orchestra is — a software development lifecycle encoded for agents, its SDLC roots, the pipeline, roles, file structure, status vocabulary, and skill index. Use when someone asks what Orchestra is, how it works, where its components come from, or where to start.

mpazaryna
mpazaryna
1

kairos-weekly-plan

Draft the start-of-week plan — project triage, load calculation, and priority setting. Use when beginning a new work week.

mpazaryna
mpazaryna
1

yoga-theme-developer

Craft yoga teaching narratives, verbal cues, and thematic arcs that connect poses to meaningful intention. Use when developing the storytelling layer of a yoga class.

mpazaryna
mpazaryna
1

yoga-professor

Evaluate yoga teaching readiness through scenarios, knowledge probes, and guided learning exercises. Use when a teacher wants to test their understanding or prepare for a class.

mpazaryna
mpazaryna
1

yoga-orchestrator

Coordinate yoga class planning by routing queries to specialist skills and synthesizing responses. Use when planning a yoga class, building sequences, or researching poses.

mpazaryna
mpazaryna
1

yoga-asana-strategist

Design yoga sequences — class structures, pose progressions, and balanced practices. Use when building a yoga class sequence or evaluating pose flow.

mpazaryna
mpazaryna
1

yoga-anatomy-expert

Provide yoga anatomy expertise — biomechanics, contraindications, modifications, and anatomical rationale behind postures. Use when a teacher needs safety guidance or modification options for poses.

mpazaryna
mpazaryna
1

orchestra-usher

Orient at session start — read project state, surface what needs attention, and route to the right skill. Use when starting a work session, when unsure what to work on next, or any time a current read of project state is needed.

mpazaryna
mpazaryna
1

orchestra-uml

Generate UML diagrams as Mermaid code and save them to .orchestra/uml/. Supports sequence, class, deployment, component, and state diagram types. Use when documenting system architecture, agent workflows, deployment topology, or state machines.

mpazaryna
mpazaryna
1

orchestra-ticket

Capture a work ticket as the starting point for the orchestra loop — read a brief, scaffold the work item folder, and set up for PRD and spec. Use when starting new work from a ticket, task, or brief.

mpazaryna
mpazaryna
1

orchestra-spec

Generate an execution spec from an approved PRD — define approach, steps, deliverables, acceptance criteria, and risks. Use when a PRD is approved and the work needs a concrete execution plan.

mpazaryna
mpazaryna
1

orchestra-scaffold

Scaffold the .orchestra/ agent knowledge base in a project — creates folder structure, templates, README, and ADR-000. Use when setting up a new project or adding .orchestra/ to an existing one.

mpazaryna
mpazaryna
1

orchestra-roadmap

Bootstrap or manage the .orchestra/roadmap.md — interactive project setup when no roadmap exists, or status/update/add commands when one does. Use when setting up a new project's vision and milestones, checking project status, or updating the roadmap.

mpazaryna
mpazaryna
1

orchestra-review

Review a completed implementation branch against its spec and acceptance criteria — catch gaps, shortcuts, and quality issues before merge. Use when an implementation branch is complete and ready for review.

mpazaryna
mpazaryna
1

writing-no-slop

Clean, human-sounding prose style guide that bans common LLM clichés, filler phrases, dramatic language, and vague vocabulary. Use when writing articles, documentation, blog posts, or any prose that should sound human and direct.

mpazaryna
mpazaryna
1

orchestra-adr

Capture an architectural decision record — document a decision that was made during work, why it was made, and its consequences. Use when a significant technical or process decision needs to be recorded for future agents and developers.

mpazaryna
mpazaryna
1

orchestra-afk

Conductor discipline for unattended (AFK) sessions — advance the work item from repo state, pause at human decisions by committing a gate file, resume from answered gates. The repo is the workspace; gates are files; approval is a commit. Use when running as a scheduled or headless session with nobody at the keyboard — the session must leave the repo in a state the next session (or a human) can pick up cold.

mpazaryna
mpazaryna
1

orchestra-devlog

Write the engineer's journal — session logs, narrative progress notes, and git journals that capture the story behind the commits. The programme notes for whoever works here next. Use when capturing what happened during a work session, why decisions were made, or what a future agent or developer will need to know.

mpazaryna
mpazaryna
1

orchestra-eval

Grade the outputs of an orchestra skill run against its eval assertions — reads produced files, checks each assertion, and writes a grading report. Use when an orchestra skill has just been run and its outputs need verifying — run `orchestra-eval <skill-name> [work-item-id]` in the project where the skill was executed.

mpazaryna
mpazaryna
1

orchestra-implement

Execute an approved spec — create a branch, work through each step, commit progress, and mark complete. Use when a spec is approved and ready for implementation.

mpazaryna
mpazaryna
1

digest

Extract key points from a URL (web or YouTube) and organize the output. Usage: /digest <url>

mpazaryna
mpazaryna
1

sandbox-sdk

Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

mpazaryna
mpazaryna
1

swift-lang

Master advanced Swift language features: macros, concurrency, generics, networking, testing. Use when working with Swift macros, async/await patterns, protocol design, or optimizing for performance. See swift-ui for SwiftUI-specific patterns.

mpazaryna
mpazaryna
1

Page 1456 of 1708 · 85369 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.