sig-audit

Measure Fallow maintainability using the repository's SIG system properties and update the evidence-backed audit report.

Quality

64%

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/SKILL.md

Quality

Content

75%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 exemplar of lean, token-efficient writing with a clearly sequenced audit workflow and built-in guardrails against fabricating metrics. Its main weakness is actionability: no concrete paths, commands, or file locations, so Claude must discover the audit scripts and evidence stores on its own.

Suggestions

Add concrete pointers for where to find the inputs, e.g. 'The audit report lives at docs/sig-audit.md and measurement scripts at scripts/sig/' (or a discovery command), to raise actionability.

Name the actual measurement command(s) or the entry-point script for step 2 so the core action is executable rather than descriptive.

Close the feedback loop in step 6: state what to do when repository verification fails (fix the tooling/docs and re-run) to lift workflow_clarity toward an explicit validate-and-retry pattern.

Dimension	Reasoning	Score
Conciseness	The body is 16 lines with zero padding: it assumes Claude's competence, uses a bare ordered list plus one guardrail sentence ('Do not estimate missing metrics or turn a proxy into a measured result'), and every token earns its place. Nothing is over-explained, matching the 'lean and efficient' anchor exactly.	5 / 5
Actionability	The steps are directive and specific about intent ('Run every supported property measurement on the same revision', 'Record commands, raw evidence locations, limitations, and current scores') but include no executable commands, script paths, or locations for 'the existing audit and measurement scripts'. This is 'some concrete guidance but incomplete; missing key details' — above level 2 because each step states exactly what must be done, below level 4 because nothing is copy-paste executable.	3 / 5
Workflow Clarity	The six steps are clearly sequenced (read scripts -> measure -> record -> compare against previous revision with identical settings -> update only supported claims -> run repository verification), and step 6 plus step 5 act as validation checkpoints. It falls short of 5 because the checkpoints lack feedback-loop detail (no 'fix and re-measure' path if verification fails), matching 'clear sequence with most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	For a sub-50-line single-purpose skill this is well-organized: one heading, one ordered list, one guardrail line, and no inlined content that belongs in a separate file. It is a 4 rather than 5 because the steps reference 'the existing audit and measurement scripts' and 'raw evidence locations' without any pointer or discovery hint for where these live, leaving minor navigation gaps.	4 / 5
	Total	16 / 20 Passed

Description

53%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 concise and specific about what the skill does within a clearly-scoped niche, but it lacks any explicit 'when to use' trigger guidance, which both caps completeness and weakens trigger-term quality. Adding a 'Use when...' clause with natural trigger phrases would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. 'Use when asked to run a SIG audit, refresh maintainability scores, or update the SIG audit report.'

Include natural synonyms users would say such as 'SIG audit', 'maintainability score', 'system properties rating', and 'audit report' in the trigger phrasing to improve trigger_term_quality and completeness together.

Briefly expand the 'what' with one more concrete capability (e.g. 'compare scores against the previous revision') to move specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	The description names its domain ('Fallow maintainability using the repository's SIG system properties') and two concrete actions ('Measure... maintainability', 'update the evidence-backed audit report'), which matches the anchor for 1-2 concrete actions without comprehensive coverage. It is not a 4 because the actions are generic verbs ('measure', 'update') with no detail on what the measurement or report update entails.	3 / 5
Completeness	The 'what' is clear (measure maintainability via SIG system properties, update the evidence-backed audit report), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' half is concrete and specific rather than vague.	3 / 5
Trigger Term Quality	It contains relevant keywords ('Fallow', 'maintainability', 'SIG system properties', 'audit report') that a user in this repository would plausibly say, but misses common variations and synonyms (e.g. 'SIG audit', 'maintainability score', 'system properties'). This sits at 'some relevant keywords but missing common variations', below 4 because natural trigger phrasings a user would actually utter are largely absent.	3 / 5
Distinctiveness Conflict Risk	The proper nouns 'Fallow' and 'SIG system properties' carve out a clear niche tied to this repository's audit system, so overlap risk with generic skills is minor. It is not a 5 because the action words ('measure', 'maintainability', 'audit report') are generic enough that a broader code-quality or audit skill could partially overlap.	4 / 5
	Total	13 / 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/SKILL.md
Commit: 74177e5

Reviewed: 5 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.