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

88%

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%Weight 40%Scale 1-5

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

A well-structured, highly actionable skill body with clear workflow sequencing, validation checkpoints, and clean progressive disclosure to real reference files. The main weakness is redundancy: the preflight and closure-checklist content is restated in several sections and could be tightened.

Suggestions

Consolidate the preflight and closure-preflight content that currently appears in both the Workflow steps and the dedicated Required preflight / Required closure preflight / Minimum self-check sections to reduce token cost.

Consider trimming the Minimum self-check to only the items not already enforced by the Operating rules, since most questions restate those rules.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and avoids explaining concepts Claude already knows, but the preflight/closure-preflight/self-check material is restated across the Workflow, Operating rules, Required preflight, Required closure preflight, and Minimum self-check sections and could be consolidated. Not a 4 because the redundancy is more than minor; not a 2 because no sections are pure padding or concept over-explanation.	3 / 5
Actionability	Provides executable commands (curl report API endpoints, `wt switch --create`, `gh issue create`, `gh pr create/view`), concrete fields (`owner=codex`, `resolutionStatus`, `notes`, `externalUrl`), specific paths (`mcp/src`, `config/source/skills`), and a routing table to real reference files — copy-paste ready and covering common cases.	5 / 5
Workflow Clarity	A 12-step sequenced workflow with explicit validation checkpoints (existing-artifact preflight, closure preflight, minimum self-check) and feedback loops (iterate on review comments / post-PR evaluation results), appropriate for a batch/destructive attribution-and-PR operation.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview with a routing table linking to six real, one-level-deep reference files (report-api-workflow.md, value-triage.md, worktree-repair.md, iteration-loop.md, evaluation-verification.md, subagent-orchestration.md), each clearly signaled by task.	5 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

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

A strong, specific description that answers both what the skill does and when to use it, with concrete actions and a distinct niche. The only weakness is trigger-term phrasing that leans technical rather than echoing the natural phrases users would say.

Suggestions

Add a few natural-language trigger synonyms users might actually say (e.g. "attribution backlog", "fix the real tool issues") alongside the technical terms.

Consider including relevant file extensions or artifact names (e.g. `.json` skill sources) to broaden natural-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Triage, repair, and close", "inspect related runs", "decide whether the issue is actionable in `mcp/src` or `config/source/skills`", "update attribution fields as `owner=codex`", "GitHub issue tracking, worktree-based code changes, PR submission, and follow-up iteration" — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Clearly states what ("Triage, repair, and close MCP attribution issues from the local report API...") and an explicit "Use this skill when Codex needs to process..." clause with concrete trigger conditions, satisfying both what and when.	5 / 5
Trigger Term Quality	Good keyword coverage ("MCP attribution issues", "tool attribution issues", "skills-related attribution issues", "report API", "worktree", "PR"), but the language is jargon-heavy and omits natural synonyms or file extensions a user might say. Not a 5 because it is not comprehensive on natural-term variants; not a 3 because it goes well beyond a single generic keyword.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (MCP/skills attribution issues via the local report API, scoped to `mcp/src` and `config/source/skills`) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	19 / 20 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: f07c33c

Reviewed: 4 days 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.