sig-audit

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

Quality

70%

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/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 a lean, well-sequenced instruction set for an audit workflow with a built-in verification step and integrity guard. Its main gap is the absence of concrete commands/paths and an explicit error-recovery feedback loop.

Suggestions

Add concrete commands or file paths (e.g., the actual measurement script invocation and audit report path) to lift actionability toward 5.

Include an explicit feedback loop after the verification step ('If verification fails, review errors, fix tooling/docs, and re-run verification before proceeding').

Optionally name the specific SIG properties to measure so 'every supported property measurement' is unambiguous.

Dimension	Reasoning	Score
Conciseness	The ~70-word body is lean and directive with no padding or explanation of concepts Claude already knows; every line instructs or constrains. Matches the 'lean and efficient, assumes competence' anchor.	5 / 5
Actionability	Concrete verbs and specifics ('Run every supported property measurement', 'Record commands, raw evidence locations, limitations, and current scores') give mostly executable guidance, but no actual commands, paths, or code are provided. Not a 5 due to missing concrete tooling invocations.	4 / 5
Workflow Clarity	A clear 6-step sequence includes an explicit verification checkpoint (step 6) and a guard ('Update only claims supported by current measurements'), but lacks an explicit error-recovery feedback loop. Not a 5 because no 'if verification fails, fix and re-run' loop is stated.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, no bundle files present, and organized as a clean ordered list. Per the rubric's simple-skill note, this can score 5 with well-organized sections and no external references needed.	5 / 5
	Total	18 / 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 clearly communicates a niche audit task with a clear 'what' but omits explicit 'when' trigger guidance, capping completeness. Trigger terms are domain-specific but lack natural user phrasings.

Suggestions

Add a 'Use when...' clause stating when Claude should invoke this skill (e.g., 'Use when maintaining or auditing Fallow maintainability metrics, or when SIG property scores need updating').

Include natural trigger phrases and synonyms users would say (e.g., 'maintainability audit', 'SIG score', 'quality assessment') alongside the technical terms.

List the concrete actions more comprehensively (e.g., measure, compare, score, report) to push specificity toward 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain ('SIG system properties', 'evidence-backed audit report') and 1-2 concrete actions ('Measure', 'update'), but coverage is not comprehensive. It is not a 4 because only two actions are listed.	3 / 5
Completeness	It clearly states what to do ('Measure... and update the audit report') but lacks any 'Use when...' trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords ('SIG', 'maintainability', 'audit', 'audit report') appear but common user phrasings, synonyms, and concrete trigger phrases are missing. Not a 2 because the terms are moderately natural rather than pure jargon.	3 / 5
Distinctiveness Conflict Risk	The niche domain ('Fallow maintainability', 'SIG system properties') is mostly distinct with only minor overlap risk. Not a 5 because the trigger phrasing is not as crisp as the anchor example.	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: .agents/skills/sig-audit/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.