all-the-vibes/atv-phoenix/phoenix-setup

Claude Code and agent skill by all-the-vibes/atv-phoenix

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Install the ATV-Phoenix self-healing harness into GitHub Copilot. Builds the Rust MCP server (if needed) and registers the phoenix agent plus its MCP server so Copilot can call phoenix_sense / phoenix_snapshot / phoenix_heal / phoenix_verify_trace. Use when the user types /phoenix-setup or asks to install or enable Phoenix.

Install

npx vskill@latest install all-the-vibes/atv-phoenix/phoenix-setup

SKILL.md

/phoenix-setup

This skill installs ATV-Phoenix into the GitHub Copilot CLI so the phoenix agent and its four self-healing tools become available.

What it does

  1. Ensures the Rust binary phoenix-mcp exists (builds it with cargo build --release if missing).
  2. Registers the phoenix MCP server in ~/.copilot/mcp-config.json (so the tools auto-load).
  3. Installs the phoenix agent definition to ~/.copilot/agents/phoenix.agent.md (so

copilot --agent phoenix works after a restart).

  1. Installs the 13 bundled skills into ~/.copilot/skills, then **self-checks them with

phoenix-mcp doctor** (the harness validates its own skills).

  1. Installs the bundled TokenMasterX for token-efficient retrieval (best-effort; needs graphify).

How to run it

The setup script ships in this skill's directory. Locate it, then run it with the repo root:

  1. Run /skills info phoenix-setup and read the skill's directory path from the output.
  2. Run the setup script, passing the skill dir and the repo root:
python <skill-dir>/setup.py --repo <ATV-Phoenix-repo-root>

If --repo is omitted, the script looks for the repo via the PHOENIX_REPO env var or the current directory. It prints exactly what it registered and the restart command.

After install

Restart Copilot (or start with copilot --agent phoenix). Then ask Copilot to verify and self-heal a task — it will call phoenix_sense / phoenix_heal and only report success on objective evidence.

Honesty

The tools report objective signals only (exit codes / hashes / regex). A fabricated "done" is the failure mode Phoenix prevents; "I'm not sure it passed" is acceptable.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/all-the-vibes/atv-phoenix/phoenix-setup/badge)](https://verified-skill.com/skills/all-the-vibes/atv-phoenix/phoenix-setup)

Something wrong with this skill or its page? Tell us.