mcp-attribution-worktree

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.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and well-structured, with a clear workflow, validation preflight checklists, and a clean one-level reference layout. The main weakness is conciseness: substantial overlap between the workflow, operating rules, and preflight sections inflates the token budget without adding new guidance.

Suggestions

Consolidate the Operating Rules with the Workflow so each rule appears once; cross-reference the preflight checklists instead of restating their steps inline.

Merge the Required preflight and Required closure preflight into a single closure-aware checklist where the steps genuinely overlap, keeping only the distinct closure-only steps separate.

Tighten the Model-oriented repair heuristic and Operating rules, which repeat the 'map to familiar concepts / name dangerous defaults' guidance multiple times.

Dimension	Reasoning	Score
Conciseness	The body is mostly high-signal maintenance rules but is long (~150 lines) with notable repetition — the Operating Rules restate Workflow steps, the two preflight checklists overlap the main workflow, and several rules echo one another — fitting 'mostly efficient but could be tightened'.	2 / 3
Actionability	Provides copy-paste-ready Quick commands (`curl` report-API endpoints, `wt switch`, `gh issue create`, `gh pr create`) plus concrete field names (`resolutionStatus`, `owner`, `notes`, `externalUrl`), matching the fully-executable anchor.	3 / 3
Workflow Clarity	A numbered 12-step workflow is paired with two explicit preflight checklists (Required preflight, Required closure preflight) and a Minimum self-check, giving clear sequencing with validation checkpoints and feedback loops for batch/destructive attribution changes.	3 / 3
Progressive Disclosure	The body is a concise overview with a Routing table mapping each task class to a single one-level-deep reference file; all six referenced files (report-api-workflow, value-triage, worktree-repair, iteration-loop, evaluation-verification, subagent-orchestration) exist in references/, so navigation is well-signaled and real.	3 / 3
	Total	11 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and distinctive, with an explicit 'Use this skill when' trigger clause and concrete actions. The main weakness is trigger-term naturalness: the keywords are technically precise but lack the common, conversational variations a user would naturally say.

Suggestions

Add conversational trigger terms a user would naturally say (e.g., 'fix MCP tool failures', 'clear the attribution backlog', 'rework failed skill attributions') alongside the technical phrasing.

Trim the long tail of implementation detail (e.g., 'owner=codex', exact directory paths) from the description to keep it a high-signal trigger rather than a mini-procedure.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Triage, repair, and close', 'inspect related runs', 'update attribution fields as `owner=codex`', 'worktree-based code changes, PR submission, and follow-up iteration' — matching the score-3 anchor.	3 / 3
Completeness	Explicitly answers both what ('Triage, repair, and close MCP attribution issues...') and when ('Use this skill when Codex needs to process `tool` attribution issues...'), satisfying the score-3 anchor.	3 / 3
Trigger Term Quality	Relevant terms like 'MCP attribution issues', 'tool attribution issues', 'skills-related attribution issues' are present but lean technical; common natural-language variations a user would say are limited, matching 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche — MCP/skills attribution via the local report API with `mcp/src` or `config/source/skills` scope — making it unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: TencentCloudBase/CloudBase-AI-Toolkit
Path: skills/mcp-attribution-worktree/SKILL.md
Commit: 3dcff8b

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.