CtrlK
BlogDocsLog inGet started
Tessl Logo

trellis-break-loop

Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention mechanisms, and captures knowledge into specs. Use after fixing a bug to prevent the same class of bugs.

67

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

71%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, actionable analysis framework with a clear output template and concrete spec-update targets. The main weakness is missing validation checkpoints around the mandatory spec-writing and commit actions, which caps workflow clarity.

Suggestions

Add an explicit validation checkpoint before committing spec updates — e.g. verify the updated guide renders/links correctly and that the bug class is actually covered, then only commit on success.

Trim the motivational Core Philosophy section or fold its one-liner into the intro to reduce token cost without losing the framing.

Consider moving the detailed Root Cause / Prevention tables into a referenced file to keep SKILL.md a lean overview while preserving the full taxonomy.

DimensionReasoningScore

Conciseness

Mostly lean with tables and checklists rather than padded prose, though the motivational Core Philosophy section and repeated table 'Example' columns could be trimmed slightly.

4 / 5

Actionability

Provides a concrete 5-dimension framework, an explicit output-format template, and named file targets for spec updates (e.g. cross-platform-thinking-guide.md), with only minor gaps in execution detail.

4 / 5

Workflow Clarity

A clear 5-step analysis sequence and output template exist, but the 'MUST immediately' file-writing actions (updating and committing specs) lack validation or verification checkpoints, capping this dimension at 3 for batch/destructive-style operations.

3 / 5

Progressive Disclosure

Self-contained single-file skill with well-organized sections (Analysis Framework, Output Format, Core Philosophy, Immediate Actions) and clearly signaled external spec paths; no nested references, though a couple of sections could be split out.

4 / 5

Total

15

/

20

Passed

Description

90%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 clearly states both capabilities and trigger conditions in third person. Minor trigger-term synonym coverage gaps prevent a perfect trigger_term_quality score.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Analyzes root cause category', 'why fixes failed', 'prevention mechanisms', 'captures knowledge into specs') with comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (four concrete analysis actions) and 'when' ('Use after fixing a bug to prevent the same class of bugs') with a concrete trigger phrase.

5 / 5

Trigger Term Quality

Natural trigger terms like 'fixing a bug' and 'fix-forget-repeat cycle' are present, but common synonyms and broader variations (e.g. 'debugging', 'postmortem') are missing.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (post-fix deep analysis, fix-forget-repeat cycle) with distinct triggers and minimal overlap risk with general debugging skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mindfold-ai/Trellis
Reviewed

Table of Contents

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.