Repair logo

Repair

Community
xiaolai
repair

Non-interactive re-run of all cc-suite bridge and registration scripts. No questions asked — idempotent escalation step after the diagnose skill finds issues it could not fix. Skill counterpart to /cc-suite:repair.

Overview

Publisherxiaolai
Repositorycc-suite
Skill namerepair
Stars
56
Forks
21
Bundled files
1
LicenseISC
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by xiaolai on GitHub. Read the source before you install it.

Installation

Install the Repair AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/xiaolai/cc-suite/tree/main/skills/cc-suite/repair
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/xiaolai/cc-suite.git /tmp/cc-suite
mkdir -p .claude/skills
cp -r /tmp/cc-suite/skills/cc-suite/repair .claude/skills/repair
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Repair in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Repair on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Repair is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Repair

Re-run every cc-suite setup script in sequence without prompts. All scripts are idempotent — correct artifacts are left alone, missing or broken ones are recreated.

When to Use

  • /cc-suite:diagnose found issues and its auto-fix did not resolve them
  • The cc-suite layer is in an inconsistent state (e.g. after a manual edit gone wrong)
  • After reinstalling cc-suite to a project, to restore all artifacts at once

If repair still leaves issues, the next step is /cc-suite:init in a Claude Code session (full interactive re-initialization).

Workflow

Step 0: Resolve the plugin root

CLAUDE_PLUGIN_ROOT is set by Claude Code only — in a Codex or Antigravity session it is unset. Resolve the root from the bridged skills symlink (it points at <plugin-root>/skills/cc-suite):

bash
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$(dirname "$(dirname "$(readlink -f .claude/skills/cc-suite 2>/dev/null)")")}"
[ -d "${PLUGIN_ROOT}/scripts" ] || echo "! cannot resolve the cc-suite plugin root — ask the user to type /cc-suite:bridge-skills in Claude Code first, or export CLAUDE_PLUGIN_ROOT"

Every command below uses ${PLUGIN_ROOT}. Stop if it could not be resolved.

Step 1: Bridge init

bash
bash "${PLUGIN_ROOT}/scripts/init.sh"

Creates AGENTS.md, CLAUDE.md, Codex scaffolding, the .agents/ workspace skills/MCP projections, and the .gitignore block. Antigravity CLI (agy) reads AGENTS.md natively and no new Gemini-era project scaffolding is created. Skips each artifact if it is already in place.

Step 2: Expose skills

bash
bash "${PLUGIN_ROOT}/scripts/bridge_skills.sh"

Links plugin skills into .claude/skills/cc-suite/ and ensures .agents/skills → ../.claude/skills.

Step 3: Remove the dead codex-cli MCP registration

bash
bash "${PLUGIN_ROOT}/scripts/prune_codex_mcp.sh"

Deletes the codex-cli entry an older cc-suite (≤2.0.1) wrote into .mcp.json: it pointed at codex mcp-server, which Codex CLI no longer has, so Claude Code fails to connect to it every session. A codex-cli entry cc-suite did not write is left alone.

Step 4: Register claude-code MCP server

bash
bash "${PLUGIN_ROOT}/scripts/mcp_claude.sh"

Adds claude-code (claude-octopus) to .codex/config.toml so Codex can invoke Claude as a tool.

Step 5: Mirror MCP servers

bash
bash "${PLUGIN_ROOT}/scripts/bridge_mcp.sh"

Copies additional MCP servers from .mcp.json into .codex/config.toml and the generated .agents/mcp_config.json projection for agy. User-managed agy configuration without cc-suite provenance is preserved.

Step 6: Bridge hooks

bash
python3 "${PLUGIN_ROOT}/scripts/bridge_hooks.py"

Mirrors .claude/settings.json hooks into .codex/hooks.json. Skips gracefully if nothing to bridge.

Step 6b: Bridge additional coding agents

bash
python3 "${PLUGIN_ROOT}/scripts/bridge_tools.py"

Mirrors the project MCP surface into any registry-bridged tools (Grok Build, opencode, Qwen Code, Kimi CLI) enabled in .cc-suite.md's ## Enabled Tools section. No-op when none are enabled.

Step 7: Status check

bash
bash "${PLUGIN_ROOT}/scripts/status.sh"

Show the full status output. Then report:

  • All green: "Repair complete — cc-suite is healthy."
  • Issues remain: list remaining · and ! items. Distinguish:
    • Items fixable only interactively (e.g. AGENTS.md missing when a non-importable CLAUDE.md exists): "Run /cc-suite:init in a Claude Code session."
    • Items requiring manual action (Codex trust prompt, Codex CLI not installed): give the exact manual step.

Example Invocations

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Repair AI skill do?

Non-interactive re-run of all cc-suite bridge and registration scripts. No questions asked — idempotent escalation step after the diagnose skill finds issues it could not fix. Skill counterpart to /cc-suite:repair.

Why use Repair on TypingMind?

Because you install it once and use it with any model. Repair is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Repair in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/xiaolai/cc-suite/tree/main/skills/cc-suite/repair. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Repair?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Repair?

As many as you like. As long as a model supports skills, you can use Repair with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Repair AI skill free?

Yes. It is published on GitHub by xiaolai under the ISC license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇