sig-audit-loop

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

Quality

73%

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

92%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 exemplary lean process skill: a clear, well-sequenced loop with explicit validation and feedback criteria, and no wasted tokens. Its only gap is moderate specificity in how to execute the abstract steps (how to invoke sig-audit, what settings to hold identical, what counts as a bounded change).

Suggestions

Add one line of invocation detail for `sig-audit` and `review` (arguments, expected output format) so the commands are copy-paste executable.

Clarify what "bounded structural change" and "identical settings" mean concretely, e.g., which audit settings must be pinned between the before and after measurements.

Dimension	Reasoning	Score
Conciseness	The body is six lean numbered steps plus one rule ("Never combine unrelated cleanup into one measurement iteration") with zero padding and no explanation of concepts Claude already knows — every token earns its place.	5 / 5
Actionability	Concrete commands (`sig-audit`, `review`) and an explicit keep/discard decision rule ("Keep the change only when the target improves and verification remains green") make the guidance mostly executable, but step 2 ("Identify a bounded structural change with a measurable expected effect") is abstract and command invocations lack arguments or settings detail.	4 / 5
Workflow Clarity	The numbered sequence has explicit validation checkpoints (measure before and after with identical settings, keep only on improvement plus green verification) and a built-in feedback loop (repeat until the target is met or no credible benefit remains), plus a final review gate.	5 / 5
Progressive Disclosure	The skill is well under 50 lines, needs no external references, and is cleanly organized with a heading and one rule — matching the simple-skill exception where a short, well-organized body with no bundle files scores 5.	5 / 5
	Total	19 / 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 communicates a clear, distinct purpose in third person, but it reads as domain jargon without an explicit "when to use" trigger clause or natural user-facing keywords. Adding trigger guidance and more concrete action language would raise it to the top anchors.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to improve maintainability or code quality of the Fallow codebase, or mentions SIG audit results."

Include natural trigger terms and synonyms users would actually say (maintainability, code quality, SIG/Software Improvement Group, refactoring, audit ratings) alongside the existing jargon.

Make the actions more concrete — e.g., name the actual operations (run sig-audit, pick a weak property, apply a bounded change, keep only if the metric improves and verification stays green).

Dimension	Reasoning	Score
Specificity	The description names the domain ("Fallow maintainability", "measured SIG audit deltas") and 1-2 actions (improve, retain/reject changes), but the actions are abstract verbs with no concrete operations, matching the anchor for domain plus 1-2 concrete actions rather than a list of several specific actions.	3 / 5
Completeness	It clearly answers "what" (iteratively improve maintainability using measured audit deltas, retaining only beneficial changes) but has no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant domain keywords like "SIG audit", "maintainability", and "regressions" are present, but common natural variations users would say (e.g., code quality, refactoring, audit, Software Improvement Group) are missing.	3 / 5
Distinctiveness Conflict Risk	The specific pairing of SIG audits with Fallow maintainability gives it a clear niche with minimal conflict risk, though it could still overlap with general refactoring or code-quality skills.	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-loop/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.