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 ./.agents/skills/sig-audit/SKILL.md

Quality

Content

72%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is lean and well-structured with a clear sequence and verification step, but stays at the level of instruction rather than executable specifics and lacks an explicit error-recovery feedback loop.

Suggestions

Add the concrete invocation for verification (e.g. the exact repository verification command or script path) so step 6 is executable rather than descriptive.

Insert an explicit feedback loop after verification: 'If verification fails, fix the tooling/docs and re-run before updating the report.'

Specify how to invoke the measurements (script names or commands) in step 2 so the workflow is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is a tight 6-step list plus one guardrail line with no concept over-explanation; every line carries an instruction. Not 2 because there is no padding or unnecessary explanation to tighten.	3 / 3
Actionability	Steps name concrete actions ('Run every supported property measurement', 'Run repository verification') but give no executable commands, property names, or script invocations. Not 3 because nothing is copy-paste ready; not 1 because it instructs specific actions rather than describing abstractly.	2 / 3
Workflow Clarity	A clear numbered sequence exists and step 6 is a verification step, but there is no explicit feedback loop (e.g. 'if verification fails, fix and re-run'). Per the rubric, batch/measurement workflows without explicit checkpoints cap at 2; not 1 because the sequence and a verification step are present.	2 / 3
Progressive Disclosure	This is a simple skill under 50 lines with no bundle files (references/scripts/assets absent) and a well-organized numbered list under a clear header, which the rubric allows to score 3. Not 2 because nothing inline should be split out and organization is clean.	3 / 3
	Total	10 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 states a clear, distinctive niche and concrete-ish actions but omits any explicit usage trigger, leaving the 'when' implicit. Trigger terms lean technical rather than user-natural.

Suggestions

Add an explicit trigger clause, e.g. 'Use when updating the Fallow/SIG audit report or remeasuring maintainability on a new revision.'

Include natural user-facing variations of the trigger ('audit report', 'maintainability score', 'SIG properties') alongside the technical 'SIG system properties'.

Expand the action list to be more concrete (e.g. 'measure each SIG property, record raw evidence, compare revisions, and update the report') to lift specificity.

Dimension	Reasoning	Score
Specificity	It names the domain ('Fallow maintainability', 'SIG system properties', 'audit report') and two actions ('Measure', 'update'), but does not enumerate multiple concrete actions. Not 3 because the actions are high-level rather than a comprehensive list; not 1 because concrete actions are stated rather than vague.	2 / 3
Completeness	It answers 'what' (measure maintainability, update the audit report) but provides no 'Use when...' or equivalent trigger for 'when'. Per the rubric guideline, a missing trigger clause caps completeness at 2; not 1 because the 'what' is explicit.	2 / 3
Trigger Term Quality	'audit report' and 'maintainability' are natural terms, but 'SIG system properties' is jargon and common variations are absent. Not 3 because coverage of user-natural phrasing is thin; not 1 because some relevant, sayable keywords exist.	2 / 3
Distinctiveness Conflict Risk	The combination of 'Fallow maintainability', 'SIG system properties', and 'evidence-backed audit report' defines a narrow, repo-specific niche unlikely to trigger for unrelated skills. Not 2 because it is far more specific than 'Works with document files'.	3 / 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/SKILL.md
Commit: 55944e8

Reviewed: 7 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.