84919 Skills Available

Find awesome
Agent Skills

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

Popular searches

security

Review implementation for security vulnerabilities and best practices. Checks input validation, injection prevention, auth/authz, secrets handling. Use after code review before merge.

matthew-plusprogramming
matthew-plusprogramming
0

route

Analyze task complexity and route to appropriate workflow. Defaults to oneoff-spec (specs are cheap, bugs are expensive). Use oneoff-vibe only for truly trivial changes or explicit user override. Use orchestrator for large multi-workstream efforts. Use journal-only for non-spec work that needs documentation.

matthew-plusprogramming
matthew-plusprogramming
0

prd

Create PRDs through the gather-criticize loop, sync existing PRDs, push amendments, and check PRD status.

matthew-plusprogramming
matthew-plusprogramming
0

orchestrate

Orchestrate large multi-workstream projects using git worktrees for parallel development. Load MasterSpec, allocate worktrees, dispatch implementers, monitor convergence, process merge queue.

matthew-plusprogramming
matthew-plusprogramming
0

investigate

Investigate connection points between specs, atomic specs, and master specs. Surface inconsistencies in env vars, APIs, data shapes, and deployment assumptions before implementation.

matthew-plusprogramming
matthew-plusprogramming
0

implement

Implement code changes based on approved atomic specs. Executes one atomic spec at a time, gathers evidence, and escalates if implementation reveals spec gaps. Use after spec group approval.

matthew-plusprogramming
matthew-plusprogramming
0

flow-verify

Verify cross-boundary wiring correctness across independently-created systems. Catches missing imports, unregistered routes, mismatched event names, wrong config references, disconnected handlers, and missing middleware.

matthew-plusprogramming
matthew-plusprogramming
0

enforce

Validate atomic specs meet atomicity criteria

matthew-plusprogramming
matthew-plusprogramming
0

e2e-test

Generate end-to-end tests from spec contracts. Produces Playwright browser tests for frontend and HTTP API tests for backend. Black-box only -- never reads implementation source code. Runs in parallel with implementer and test-writer.

matthew-plusprogramming
matthew-plusprogramming
0

docs

Generate documentation from implementation. Creates user docs, API docs, and architecture docs. MANDATORY for all spec-based workflows (oneoff-spec, orchestrator). Only skipped for oneoff-vibe.

matthew-plusprogramming
matthew-plusprogramming
0

doc-audit

Documentation audit skill for diagnosing documentation health across all doc directories. Supports quick scan and deep audit levels with variable scope.

matthew-plusprogramming
matthew-plusprogramming
0

deploy

Deploy CDKTF infrastructure stacks to AWS. Handles stack deployment, asset staging, output management, and environment configuration. Understands deployment sequences and stack dependencies.

matthew-plusprogramming
matthew-plusprogramming
0

code-review

Review implementation for code quality, style consistency, and best practices. Runs before security review. READ-ONLY - reports issues but does not fix them.

matthew-plusprogramming
matthew-plusprogramming
0

challenge

Dispatch the challenger agent for operational feasibility scrutiny. Convergence loop for pre-implementation and pre-orchestration stages; single-pass for pre-test and pre-review. MANDATORY for both oneoff-spec and orchestrator workflows.

matthew-plusprogramming
matthew-plusprogramming
0

browser-test

Execute browser-based UI testing using Chrome MCP tools. Tests user interactions, visual outcomes, captures evidence. Use for UI features after implementation and security review.

matthew-plusprogramming
matthew-plusprogramming
0

atomize

Decompose high-level specs into atomic specs

matthew-plusprogramming
matthew-plusprogramming
0

code-quality-report

生成代码质量报告。当用户请求为项目源代码生成质量报告时,使用此功能。输出名为 code-quality-report.html 的单页 HTML 文件作为质量报告,该报告集成了 Node.js 脚本和 HTML 模板。

warmeaf
warmeaf
0

black-swan-seeker

Specialized agent skill for identifying "Black Swan" events—high-impact, low-probability outliers—and systemic risks in any subject matter. Use for red-teaming, stress-testing strategies, or exploring "unthinkable" scenarios.

prodbybuddha
prodbybuddha
0

qwen3-tts

Generate multilingual CustomVoice samples and one-off voice replies with Qwen3‑TTS (no Remotion). Includes local setup (Conda Py3.12) and simple CLI scripts.

yusufferdogan
yusufferdogan
0

react-starter-skill

|

izz520
izz520
0

tailscale-runpod

Setup Tailscale for SSH access to RunPod, Vast.ai, or any cloud GPU instance. Use when user asks to "setup Tailscale", "SSH to RunPod", "connect to cloud GPU", or needs VPN/mesh networking.

koshimazaki
koshimazaki
0

map-relationships

Visualize and expand the relationship network around an entity - allies, enemies, debts, secrets, romantic connections, and power dynamics. Use when user wants to "map connections", "show relationships", or "visualize the network" around a character or organization.

hopeoverture
hopeoverture
0

expand-history

Expand a historical era or event with detailed timeline, key figures, artifacts, witnesses still living, and consequences that echo to the present. Use when user wants to "detail this war", "expand this age", or "develop this event's history".

hopeoverture
hopeoverture
0

expand-faction

Build out an organization with member hierarchy, internal politics, resources, secret plots, rivals, and operational details. Use when user wants to "flesh out a guild", "expand an organization", or "detail a faction".

hopeoverture
hopeoverture
0

generate-politics

Generate political systems including alliance webs, active conflicts, treaties, succession crises, and power brokers. Use when user wants to add "political intrigue", "alliances", "faction conflict", or "power dynamics" to a world.

hopeoverture
hopeoverture
0

expand-entity

Expand an existing entity with additional detail, create related sub-entities, or generate deeper connections. Use when user wants to "flesh out", "expand", "add more detail to", or "develop" an existing entity like a city, character, or organization.

hopeoverture
hopeoverture
0

expand-region

Fill a region with villages, landmarks, encounters, local legends, travel hazards, and points of interest. Use when user wants to "flesh out a region", "populate an area", or "detail a territory".

hopeoverture
hopeoverture
0

generate-world

Generate an entire world with interconnected entities. Creates 80-120 entities including continents, regions, settlements, NPCs, organizations, history, and more. Use when the user wants a complete world generated automatically.

hopeoverture
hopeoverture
0

link-entities

Create bidirectional wikilinks between existing entities. Use when user wants to "connect", "link", or "relate" two or more entities, or when they mention entities should reference each other.

hopeoverture
hopeoverture
0

linkify

Automatically add [[wikilinks]] to all mentions of existing entities within a file or entire world. Scans for entity names, aliases, and partial matches, then wraps them in wikilink syntax. Use when user wants to "linkify", "auto-link", "add links to existing entities", or "wikilink this file".

hopeoverture
hopeoverture
0

generate-quests

Generate adventure hooks, quest lines, and story seeds tied to existing world entities. Creates bounties, mysteries, faction missions, and personal quests. Use when user wants "quest ideas", "adventure hooks", "story seeds", or "mission board" content.

hopeoverture
hopeoverture
0

expand-settlement

Deep-dive into a settlement, generating NPCs, shops, taverns, districts, local issues, rumors, and daily life details. Use when user wants to "flesh out a city", "populate a town", or "add NPCs to a settlement".

hopeoverture
hopeoverture
0

generate-image

Generate an image for a worldbuilding entity using OpenAI's gpt-image-1.5 model. Reads the filled prompt from the entity file, generates the image, downloads it locally, and updates the entity to reference it.

hopeoverture
hopeoverture
0

generate-economy

Generate economic systems including trade routes, resource nodes, merchant guilds, black markets, price variations, and commercial relationships. Use when user wants to add "trade routes", "economy", "commerce", or "merchant networks" to a world.

hopeoverture
hopeoverture
0

populate-entity

Scan an entity file to identify mentions of people, places, organizations, and other entities in the text. Creates missing entities using appropriate templates and adds wikilinks. Use when user wants to "populate", "fill out", "create linked entities", or "auto-generate connections" for an entity.

hopeoverture
hopeoverture
0

random-encounter

Generate random encounters appropriate for a location, party level, or situation. Creates combat, social, or exploration encounters using existing world entities. Use when user wants "random encounter", "encounter table", or "what happens at [location]".

hopeoverture
hopeoverture
0

session-prep

Prepare materials for a D&D game session. Generates session notes, NPC cheat sheets, encounter summaries, and location briefs from world entities. Use when DM wants to "prep for session", "prepare for game night", or "create session notes".

hopeoverture
hopeoverture
0

validate-template

Validate a template or entity file has all required sections, YAML fields, and follows the worldbuilding system conventions. Use when creating new templates or checking if entities are properly structured.

hopeoverture
hopeoverture
0

worldbuild

Interactive guided worldbuilding with questions, choices, and incremental creation. Creates worlds collaboratively through a question-and-answer workflow rather than automatic generation. Use when the user wants to thoughtfully build a world step-by-step.

hopeoverture
hopeoverture
0

generate-culture

Generate deep cultural elements for a people, nation, or species - festivals, customs, taboos, cuisine, art, coming-of-age rituals, death rites, and social norms. Use when user wants to "create culture for", "define customs of", or "flesh out traditions".

hopeoverture
hopeoverture
0

campaign-arc

Track multi-session story arcs, plot threads, and campaign progression. Manages ongoing narratives, NPC relationships, party goals, and session continuity across multiple game sessions.

hopeoverture
hopeoverture
0

create-entity

Generate a fully populated worldbuilding entity from a template and save it to a world. Use when the user wants to create a specific entity like "create a dwarven city called Ironhold" or "make a fire deity named Pyraxis".

hopeoverture
hopeoverture
0

create-template

Create a new worldbuilding template for the Obsidian vault. Use when the user wants to add a new entity type template like "tavern template", "spell template", or "dungeon template".

hopeoverture
hopeoverture
0

create-world

Create a new worldbuilding project with full folder structure. Use when the user wants to start a new world, campaign setting, or fantasy setting like "create a world called Eldoria".

hopeoverture
hopeoverture
0

audit-world

Audit a world for consistency, D&D 5e 2024 rule compliance, broken links, orphaned entities, and connection gaps. Provides detailed reports and can auto-fix issues.

hopeoverture
hopeoverture
0

runbook-generator

Creates structured runbooks to document reproducible scenarios for APIs, UX flows, and technical procedures

Jonathan Delgado <hi@jon.soy> (https://jon.soy)
Jonathan Delgado <hi@jon.soy> (https://jon.soy)
0

pr-creator

Creates GitHub pull requests in draft mode following Conventional Commits format. Use when user requests "create PR", "make pull request", "open PR", or similar. Automatically pushes branch, analyzes changes, generates structured title/body with proper labels, and assigns to creator. Never modifies code or merges branches.

Jonathan Delgado <hi@jon.soy> (https://jon.soy)
Jonathan Delgado <hi@jon.soy> (https://jon.soy)
0

coaching-reporter

Generates detailed reports and analysis from coaching sessions. Use when analyzing coaching session files, tracking coachee progress, extracting insights from coaching notes, or creating structured reports for coaching development plans.

Jonathan Delgado <hi@jon.soy> (https://jon.soy)
Jonathan Delgado <hi@jon.soy> (https://jon.soy)
0

runbook-executor

Executes runbooks and generates timestamped evidence documentation of the execution results

Jonathan Delgado <hi@jon.soy> (https://jon.soy)
Jonathan Delgado <hi@jon.soy> (https://jon.soy)
0

seo-content-writer

Generate SEO-optimized content for traditional search engines, AI answer engines, and generative AI platforms. Use when the user needs help writing or optimizing content for (1) Blog posts, articles, or web pages targeting organic search, (2) Content optimized for Google AI Overviews and featured snippets, (3) Answer Engine Optimization (AEO) for ChatGPT, Perplexity, and voice assistants, (4) Generative Engine Optimization (GEO) for AI citations, (5) E-E-A-T optimization, (6) Schema markup and structured data, (7) Keyword research and topic cluster planning, or any content requiring search visibility across traditional and AI-powered discovery.

[Ben Sabic](https://bensabic.ca)
[Ben Sabic](https://bensabic.ca)
0

Page 1575 of 1699 · 84919 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.