Tooluck logoTooluck
SKILL.md

mcp-attribution-worktree

Agent skill fromTencentCloudBase/CloudBase-AI-Toolkit

Triage, repair, and close MCP attribution issues from the local report API with evidence-driven decisions and isolated Worktrunk worktrees. Use this skill when Codex needs to process `tool` attribution issues and skills-related attribution issues, inspect related runs, decide whether the issue is actionable in `mcp/src` or `config/source/skills`, update attribution fields as `owner=codex`, and then complete the fix loop through GitHub issue tracking, worktree-based code changes, PR submission, and follow-up iteration when the problem is repairable.

How to install mcp-attribution-worktree

install mcp-attribution-worktree
# install the CloudBase-AI-Toolkit pack with the skills CLI
npx skills add TencentCloudBase/CloudBase-AI-Toolkit

# or add only this skill to Claude Code: copy the folder

skills/mcp-attribution-worktree/

# into

~/.claude/skills/mcp-attribution-worktree/ (all projects)

.claude/skills/mcp-attribution-worktree/ (one project)

skills/mcp-attribution-worktree/SKILL.md

MITFull file
1# MCP Attribution Worktree
2
3Process MCP and skills-related attribution issues as an auditable maintenance workflow instead of ad-hoc debugging.
4
5## What this skill does
6
7Use this skill to:
8
9- fetch pending MCP and skills-related attribution issues from the local report API
10- inspect issue detail plus representative runs before making any status decision
11- map failures back to concrete `mcp/src` tools, `config/source/skills`, or classify them as environment / grader / duplicate noise
12- update attribution issues with concise evidence, `owner=codex`, and links to external GitHub work
13- isolate each actionable repair in its own Worktrunk worktree and branch
14- carry actionable issues through repo repair and PR creation instead of stopping at issue state updates
15- continue from existing GitHub issues or PRs when later review or evaluation feedback shows the first direction was incomplete or wrong
16- run a real post-PR evaluation when an evaluation interface is available, and use that result to decide whether another repair loop is needed
17
18## Do not use this skill for
19
20- generic bug fixing without attribution evidence
21- unrelated attribution categories that do not map to `mcp/src` or `config/source/skills`
22- bulk repo changes unrelated to a specific attribution issue
23- direct database or backend mutation outside the documented report API endpoints
24
25## Workflow
26
271. Start with focused `tool` and `skill` backlog queries.
28…

Excerpt shown under the repository's MIT license.

More skills in CloudBase-AI-Toolkit

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates