agent-skills

A collection of AI agent skills — reusable workflows, protocols, and knowledge packs for agentic systems. Skills follow the Agent Skills open format, making them compatible with any agent framework that supports the standard.

Skills

agent-skills

Reference for the Agent Skills open format itself — directory structure, frontmatter schema, naming conventions, and progressive disclosure model. Use this meta-skill when creating or reviewing any other skill in this repository.

arr-cli

Radarr and Sonarr media library management. Two CLIs (radarr-cli for movies, sonarr-cli for TV series) with one shared skill wrapper. List movies and series, search for additions, check calendars and wanted/missing episodes. Separate API keys per app.

brand-designer

Create comprehensive brand identity documentation for any brand. Guides you through documenting strategy, visual identity (logo, color, typography, imagery), voice and tone, application guidelines, governance, and asset inventory. Produces markdown specs, compiled brand books, and brand-compliant images via reference-image-aware generation. Ships 7 templates, a brand-book CLI for validation/compilation, and a generate script for brand card and mockup imagery.

cli-builder

Build and refactor CLI tools for AI agent consumption. 10 universal patterns (non-interactive, --json, --dry-run, idempotent, lazy auth, progressive help), an agent-compatibility test suite, a Python API client pattern, and a bash scaffold template. Principles grounded in real failures from building 15+ agent-facing CLIs.

confluence-cli

Atlassian Confluence from the terminal. List spaces, browse pages, view content with body extraction, search with CQL, and create pages. Same API token as Jira.

data-architect

Act as a virtual data architect. Discover data assets, assess maturity, evaluate platforms, design architectures, establish governance, and create migration plans. Covers modern data patterns (data mesh, data lakehouse, streaming, real-time analytics) with vendor evaluation frameworks and maturity models.

data-scientist

PhD-level expertise in data science, statistics, and machine learning. Rigorous statistical methodology, experimental design, causal inference, Bayesian analysis, model selection and diagnostics, and research-grade communication. Ships five analysis scripts (power analysis, assumption diagnostics, model comparison, effect size calculator, experimental design generator) with Python + R dual-language support.

epub

EPUB file format expert — read, write, edit, convert, and repair EPUB2/EPUB3 ebooks. Ten CLI scripts: structure inspection, text extraction, knowledge extraction (LLM mode via env vars), scaffold creation, surgical editing, image extraction, batch processing, EPUB2→3 conversion, repair, and validation. Eight reference files covering format internals, Python libraries, spec/validation, tutorials, capability discovery, fixed-layout, accessibility, and media overlays. Portable across any AgentSkills harness.

forgejo-cli

Forgejo or Gitea self-hosted Git forge from the terminal. List repositories, search repos, manage issues, and view pull requests.

ghost-cli

Ghost CMS from the terminal. Manage posts and pages, list tags, and check site info. Admin API key from Ghost Integrations. JWT authentication handled automatically.

jellyfin-cli

Jellyfin media server from the terminal. Check server info, browse recently added, search your library by type, list libraries, and view statistics.

kanban-guru

A virtual Kanban expert for engineering teams. Diagnose flow problems, design board configurations, calibrate WIP limits, establish service level expectations, set up multi-portfolio operating models, and navigate Scrum-to-Kanban transitions. Covers all seven cadences, classes of service, Little's Law, flow metrics, and the full practitioner's playbook with rich reference material.

jira-cli

Atlassian Jira from the terminal. Search issues with JQL, view details, create issues, add comments, list projects, and transition status. API token from id.atlassian.com.

jira-jql

Expert-level Jira Query Language reference covering all operators, functions (date/time, user, sprint/version, issue, custom field, JSM), history operators (WAS/CHANGED), relative dates, performance best practices, role-based ready queries, REST API usage, and troubleshooting. Three companion references: complete function catalog, role-specific query bank (dev, scrum master, PO, power user, admin), and gotchas/troubleshooting guide.

nous-branding

Generate images and content consistent with the Nous Research brand identity. Ships four reference images (color palette card, official high-res mascot, brand collage) that can be used as img2img inputs. Covers the Nous Girl mascot specs, cyber-classical art style, texture system (risograph grain, CRT scan lines, photocopy noise), hex-accurate color palette, and image prompt templates for text-only and reference-image-driven workflows.

Cross-pollination note: This skill was developed in parallel with plntrprotocol/nous-branding — a sibling project created independently, in friendship, for the same purpose. We've been learning from each other's approaches throughout development, and each repo has strengths the other doesn't. If you're using ours, go check out theirs too.

openlibrary-cli

Open Library book metadata from the terminal. Search books and authors, get work and edition details, lookup by ISBN. No API key required — the public Open Library API is free for everyone.

peertube

PeerTube federated video platform from the terminal. Browse videos and channels, search across instances, view server info. OAuth2 login with token persistence. Set PEERTUBE_SERVER to point at any instance.

software-architecture-analysis

Reverse-engineer a software codebase to understand its architecture, data flow, privacy posture, and feature surface — then produce a clean-room design document, PRD, or migration plan under new constraints (local-first, privacy-first, self-hosted). Includes an interface extraction pattern for designing swappable storage provider abstractions.

systematic-debugging

4-phase root cause debugging protocol: understand bugs before fixing. Covers schema/environment divergence, exception type specificity in fallback chains, progressive characterization grids for API/retrieval failures, dependency source detection (editable dev forks), macOS sandboxed application debugging, and the Rule of Three for recognizing architectural problems. Adapted from obra/superpowers (MIT) with significant expansion from real-world use.

tempest-cli

Hyper-local weather from a WeatherFlow Tempest station. Query current conditions, 7-day forecast, historical observations, and real-time UDP broadcasts. A complete reference implementation of the cli-builder patterns in a working, testable project — including the CLI binary and full API field layout reference.

tmdb-cli

The Movie Database API from the terminal. Search and discover movies and TV by genre, certification, rating, and date range. Check trending, upcoming, and now playing. Free API key from themoviedb.org.

trakt

Trakt.tv media discovery from the terminal. Browse trending, anticipated, and popular movies and TV shows. Read-only — uses only a Client ID, no OAuth required.

transistor

Transistor.fm podcast hosting from the terminal. Manage shows and episodes, view subscriber analytics. API key from transistor.fm settings.

---

Installation

Skills don't require installation in the traditional sense. They are loaded by your AI agent when triggered. Each agent framework documents its own skill directory path and loading mechanism — follow the links below for the authoritative setup guide for your harness.

Harness	Setup Guide
Claude Code	code.claude.com/docs/en/skills
OpenCode	opencode.ai/docs/skills
OpenAI Codex	developers.openai.com/codex/skills
GitHub Copilot	docs.github.com/en/copilot/concepts/agents/about-agent-skills
Cursor	cursor.com/docs/context/skills
Gemini CLI	geminicli.com/docs/cli/skills
Hermes Agent	See below

Hermes Agent

Hermes Agent loads skills from ~/.hermes/skills/, organized by category subdirectory:

cp -r cli-builder ~/.hermes/skills/devops/
cp -r systematic-debugging ~/.hermes/skills/software-development/
cp -r tempest-cli ~/.hermes/skills/devops/

Hermes loads skill metadata at session start. Use the /skills command to list available skills, and skill_view(name) to load a specific skill's full instructions. Skills can also be pinned for persistent availability.

Generic / Other Frameworks

The agentskills.io clients page maintains an up-to-date list of every agent framework that supports the Agent Skills format, with links to each one's setup instructions. Any framework listed there can load these skills — follow that framework's specific documentation for the correct directory path and loading mechanism.

For frameworks without built-in skill loading, the format is intentionally simple:

1. Place the skill directory in your agent's accessible file path
2. The agent reads SKILL.md when triggered by keywords in the task
3. Supporting files in references/, templates/, and scripts/ are loaded on demand

You can also instruct your agent to read specific SKILL.md files at session start, or reference skills in your agent's system prompt or CLAUDE.md/AGENTS.md.

---

Contributing

Skills follow the Agent Skills specification. See the agent-skills reference skill for format details, and AGENTS.md in this repo for agent-specific loading and compliance guidance.

Before submitting a new skill:

1. Ensure SKILL.md has valid YAML frontmatter (required: name, description)
2. The name field must match the parent directory name
3. Keep SKILL.md under 500 lines and 5,000 tokens
4. Move detailed reference material to references/ for progressive disclosure
5. Validate with skills-ref validate ./my-skill if available

---

License

MIT — see LICENSE.md for full terms.