sig-audit-loop

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

Quality

72%

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/sig-audit-loop/SKILL.md

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 body is concise and well-sequenced with a real validation gate and feedback loop, well suited to a simple instruction skill. Its main gap is actionability: the measure/delta step would benefit from a concrete command or example of how the before/after comparison is performed.

Suggestions

Add a concrete example of the measurement step, e.g. the exact sig-audit invocation and how to compute the target property's delta before and after.

Specify what 'identical settings' means in practice (same files, same SIG profile/options) so the before/after comparison is unambiguous.

Give one short concrete example of a 'bounded structural change' and its expected measurable effect.

Dimension	Reasoning	Score
Conciseness	The body is a lean numbered loop with no padding and no explanation of concepts Claude already knows; every line earns its place, matching the 'lean and efficient' anchor.	3 / 3
Actionability	It names concrete tools (sig-audit, review) and a clear keep/reject gate, but step 2 and the measure/delta comparison lack executable commands or specifics, leaving key details missing.	2 / 3
Workflow Clarity	A clear numbered sequence with an explicit validation checkpoint (step 4: keep only when the target improves and verification stays green) and a repeat-until feedback loop, matching the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	Under 50 lines with no need for external references and a single well-organized section, so the simple-skill allowance applies and it scores 3 on structure.	3 / 3
	Total	11 / 12 Passed

Description

60%

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 and third-person with a clear gating mechanism, but lacks an explicit 'when to use' trigger and relies on project jargon rather than natural user terms. Adding a 'Use when...' clause with common phrasings would lift completeness and trigger_term_quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when improving Fallow maintainability, running a SIG audit, or deciding which refactors to keep.'

Include natural user phrasings alongside the jargon (e.g. 'maintainability', 'code quality', 'refactor gate').

Clarify the niche boundary so it does not fire for general cleanup or unrelated audit tasks.

Dimension	Reasoning	Score
Specificity	Names the concrete domain ('Fallow maintainability'), the mechanism ('measured SIG audit deltas'), and an explicit retention gate ('retaining only changes that improve the targeted property without regressions'), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	The 'what' is clearly stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	'maintainability' is a somewhat natural term, but 'SIG audit deltas' and 'Fallow' are project-specific jargon; common natural variations a user would say (e.g. 'code quality', 'refactor') are missing.	2 / 3
Distinctiveness Conflict Risk	The Fallow/SIG niche is fairly distinct, but without explicit triggers it could still overlap with adjacent audit/refactor skills, so it does not reach the 'clear niche with distinct triggers' level.	2 / 3
	Total	9 / 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: fallow-rs/fallow
Path: .agents/skills/sig-audit-loop/SKILL.md
Commit: 55944e8

Reviewed: about 17 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.