Agents Skills — Testing skill for Claude Code
Persönliche, portierbare Agent-Skills (Agent-Skills-Spec, .agents/skills): ui-review, codegraph-project-setup und agent-config.
How to install Agents Skills
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open reisi007/agents-skills and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agents Skills does
Persönliche, portierbare Agent-Skills (Agent-Skills-Spec, .agents/skills): ui-review, codegraph-project-setup und agent-config. Zentrale Quelle für eigene Skills — global registriert via OpenCode skills-Array, kein Skill mehr in Einzelprojekten.
Alternatives in Testing
- Gstack — 15,000+ Garry Tan's exact Claude Code setup: 6 opinionated tools that serve as CEO, Eng Manager, Release Manag 33.9k ★
- Marketing Skills Versions — Current versions of all skills 13.8k ★
- N9e Config Driven E2e — Maintain config-driven Nightingale E2E tests that convert JSON config data into UI-readable normalized values 301 ★
README
agents-skills
**Persönliche Agent-Skills (OpenCode & Co.) — portabel über die Agent-Skills-Spec.**
Zentrales, versioniertes Repo für alle **eigenen** Skills. Kein Skill lebt mehr in einem Einzelprojekt — hier ist die einzige Quelle. Registriert via globalem `skills`-Array in `~/.config/opencode/opencode.jsonc` → verfügbar in **jedem** Projekt.
Struktur
agents-skills/
├── .agents/skills/ ← Agent-Skills-Spec-Struktur (portabel für OpenCode, Claude Code, …)
│ ├── agent-config/ ← Globales Setup: opencode.jsonc, MCP, Skills-Registrierung
│ ├── codegraph-project-setup/ ← Bootstrap: codegraph init + Pre-Commit-Hook + AGENTS.md
│ ├── model-updater/ ← Modell-Empfehlungen gegen ocgo/cc Preis-Tracker (UPDATE/KEEP)
│ ├── permissions/ ← Security-Policy: username isolation, secrets, macOS privacy, .env
│ ├── vision-agents/ ← 3 locked-down vision subagents: technical / creative / document
│ └── ui-review/ ← Playwright-Screenshot-Loop + Vision-Analyse
└── .githooks/pre-commit ← CodeGraph-Index-Sync vor jedem Commit (fails open)
Installation / Registrierung (einmalig pro Maschine)
git clone git@github.com:reisi007/agents-skills.git ~/dev/agents-skills
# ~/.config/opencode/opencode.jsonc
"skills": ["/Users//dev/agents-skills/.agents/skills"],
Danach in **jeder** OpenCode-Session verfügbar. Einzelheiten & MCP-CodeGraph: siehe Skill `agent-config`.
Skills erweitern
# Neuer Skill
mkdir -p .agents/skills//
# SKILL.md mit Frontmatter (name + description), kebab-case-ID = Ordnername
git add -A && git commit && git push
Keine Config-Änderung nötig — das Verzeichnis ist bereits registriert.
Ownership-Regeln
| Skills | Ort |
|---|---|
| Eigene Skills | hier (agents-skills/.agents/skills/) |
| Offizielle/Third-Party-Packs (daisyui, find-skills, stripe-*) | dort, wo der Installer sie platziert |
| Projekt-spezifische Skills (nx-*, blog-beitrag, testimonial) | im |
Related Skills
Dsh Plugin Dev Agent Skill
Global agent skill: create, extend, secure, test and publish Cordis plugins for the DeepSeek Harness (DSH). Ve
Valcraft
Agent skills for spec-driven delivery — one plugin for Claude Code, OpenAI Codex, and OpenCode. At the center:
Jax OS
Self-hosted cockpit for AI coding agents: watch Claude Code, Codex and OpenCode work in tmux, and run spec, co
Flw
agentic flow package across claude, codex, and opencode: skills rotation (spec->execute->review), OKF-inspired
Ralph Output Adversarial Review
Adversarially reviews the artifacts produced by a RALPH run (code/tests/UI/config) against repo policy (testin
DocOps
Drop a card on the board, pick Claude Code, Codex CLI, OpenCode or the Hermes agent, and watch it work in its
Related Agents
Config Manager
Owns the global Claude Code setup and its self-improvement loop. Use via the /update-config skill (or directly
Architecture Watchdog
High-Level-Architektur-Review für xbuddy. Prüft Spec-Drift, Skalierbarkeit (Familie-3-Probe), Sackgassen, Komp
Integration Setup
Installs, checks, and configures dotclaude's optional integrations (CodeGraph, Headroom, the Codex CLI). Use t