break-loop

Deep post-fix bug analysis across five dimensions: root cause categorization, fix failure analysis, prevention mechanisms, systematic expansion, and knowledge capture. Updates .trellis/spec/ guides with lessons learned to prevent recurring bugs. Use when a debugging session completes, after fixing a tricky bug, when the same class of bug keeps recurring, or when you want to capture debugging insights into project documentation.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/break-loop/SKILL.md

Quality

Content

50%

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

The body is a well-structured, self-contained analysis framework with concrete tables and an output template, but it carries some motivational padding, open-ended analysis prompts, and no verification checkpoints. It is competent but could be tightened and made more procedural.

Suggestions

Trim the Core Philosophy section (remove "30 minutes of analysis saves 30 hours" and the Tactical/Strategic/Philosophical levels) to cut motivational padding that restates the intro's purpose.

Tighten the duplication between the Analysis Framework tables and the Output Format template, or move the detailed category/prevention tables into a reference file so the body stays a lean overview.

Add an explicit verification step to the After Analysis workflow (e.g., confirm the updated `.trellis/spec/` file exists and the `src/templates/markdown/spec/` sync succeeded) to provide a real feedback checkpoint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tables and checklists, but the Core Philosophy block ("The value of debugging is not in fixing the bug...", "30 minutes of analysis saves 30 hours") and the Tactical/Strategic/Philosophical levels add motivational padding that could be trimmed.	2 / 3
Actionability	Provides concrete category tables and a copy-paste output format template, but the analysis dimensions themselves are framed as open questions ("Which category does this bug belong to?") rather than fully specified procedures, leaving key detail to Claude.	2 / 3
Workflow Clarity	The five dimensions are clearly sequenced (1–5) with a follow-on Immediate Actions section and a knowledge-capture checklist, but there are no verification checkpoints (e.g., confirming spec files were actually written or the sync succeeded) to close the loop.	2 / 3
Progressive Disclosure	Well-organized into clear sections, but at ~125 lines the content is a single monolithic document with no one-level-deep references to split out the detailed category tables or output template, which could ease navigation.	2 / 3
	Total	8 / 12 Passed

Description

100%

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, third-person, and answers both what the skill does and when to use it with natural trigger terms and a distinct niche. It is a strong, concise description with no notable weaknesses.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "root cause categorization, fix failure analysis, prevention mechanisms, systematic expansion, and knowledge capture" plus "Updates .trellis/spec/ guides with lessons learned" — matching the anchor for enumerating several specific actions.	3 / 3
Completeness	Explicitly answers both what (five named analysis dimensions + updating spec guides) and when via a clear "Use when ..." clause with multiple explicit triggers, matching the top anchor.	3 / 3
Trigger Term Quality	Natural triggers users would say are well covered: "after fixing a tricky bug," "debugging session completes," "same class of bug keeps recurring," "capture debugging insights into project documentation," rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (post-fix deep bug analysis tied to a specific .trellis/spec workflow) with distinctive triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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: zhukunpenglinyutong/desktop-cc-gui
Path: .agents/skills/break-loop/SKILL.md
Commit: 786846c

Reviewed: about 14 hours 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.