sig-audit-loop

Iteratively improve Fallow maintainability using measured SIG audit deltas, retaining only changes that improve the targeted property without regressions.

Quality

76%

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 ./.claude/skills/sig-audit-loop/SKILL.md

Quality

Content

86%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.

The body is an exceptionally lean, well-sequenced iterative loop with an explicit validation gate and feedback loop; the only gaps are unspecified measurement commands and implicit error-recovery detail.

Dimension	Reasoning	Score
Conciseness	Eight lines with zero padding or over-explanation of concepts Claude already knows; every token earns its place, matching the 'lean and efficient' anchor.	5 / 5
Actionability	Names concrete commands (`sig-audit`, `review`) and a clear keep/discard procedure, but the measurement step leaves the exact command unspecified and 'implement' is abstract, fitting 'mostly executable guidance; minor gaps'; not a 5 due to no copy-paste examples.	4 / 5
Workflow Clarity	A clearly numbered 1-6 sequence with an explicit validation gate (step 4) and a repeat loop (step 5); not a 5 because discard-on-failure recovery is implicit rather than spelled out as fix->revalidate and there is no checklist.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, no external references needed, and well-organized with a heading plus numbered list, satisfying the simple-skill exception for a top score.	5 / 5
	Total	18 / 20 Passed

Description

66%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.

The description is specific, domain-distinctive, and free of fluff, but it omits any explicit 'Use when...' trigger guidance, which caps completeness at 3 and limits the trigger and distinctiveness scores.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when improving Fallow maintainability scores via SIG audits, or when the user mentions SIG deltas, maintainability properties, or regression-free refactors.'

Include natural trigger synonyms (e.g. 'SIG score', 'maintainability rating', 'code quality audit') so the description surfaces for varied phrasings of the same intent.

Name the concrete operation the skill drives (e.g. 'run sig-audit, measure deltas, keep only improvements') to lift specificity from 4 toward 5.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('measured SIG audit deltas', 'retaining only changes that improve the targeted property without regressions', iterative improvement), fitting the 'several specific actions; minor gaps' anchor; not a 5 because no specific commands or operations are enumerated.	4 / 5
Completeness	Has a clear 'what' (iteratively improve Fallow maintainability via measured SIG deltas) but no 'when' — a missing 'Use when...' clause caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Good domain keywords ('SIG audit', 'maintainability', 'regressions', 'targeted property') that a user in this domain would naturally say; not a 5 because there is no 'Use when' phrasing or synonym/extension coverage.	4 / 5
Distinctiveness Conflict Risk	The 'Fallow maintainability' + 'SIG audit deltas' framing is a clear niche with mostly distinct triggers; not a 5 because without a 'Use when' clause there is minor overlap risk with generic audit/review skills.	4 / 5
	Total	15 / 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: fallow-rs/fallow
Path: .claude/skills/sig-audit-loop/SKILL.md
Commit: 7e1e075

Reviewed: 3 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.