CtrlK
BlogDocsLog inGet started
Tessl Logo

sig-audit-loop

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

62

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/sig-audit-loop/SKILL.md
SKILL.md
Quality
Evals
Security

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.

An exemplary lean skill body: a crisp numbered loop with explicit keep/revert validation, a termination condition, and a guard against confounding changes. The only minor gap is actionability — the measurement invocation and what 'identical settings' means are left implicit.

DimensionReasoningScore

Conciseness

Eighteen lines with zero padding: every step ('Run `sig-audit` and select one weak property', 'Keep the change only when the target improves and verification remains green') earns its place and assumes Claude's competence. Matches the 'lean and efficient' anchor exactly.

5 / 5

Actionability

Concrete commands (`sig-audit`, `review`) and a specific measure-before/measure-after procedure, but 'Identify a bounded structural change with a measurable expected effect' and 'with identical settings' give direction without an example invocation or which settings to hold fixed. Mostly executable with minor gaps — anchor 4, not 5.

4 / 5

Workflow Clarity

Clear numbered sequence with an explicit validation gate (step 4: keep only when the target improves and verification stays green), a termination condition (step 5), a final `review` checkpoint (step 6), and a guard rule ('Never combine unrelated cleanup into one measurement iteration'). This is a complete measure → implement → re-measure → keep/revert feedback loop, matching the anchor-5 example.

5 / 5

Progressive Disclosure

Under 50 lines, single-purpose, self-contained with no need for external references; the title plus numbered list is well-organized. Per the rubric's guideline for simple skills, this scores 5 with just well-organized sections.

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.

A distinctive, appropriately terse description with a clear 'what', but it entirely lacks a 'when' / trigger clause, which caps both completeness and trigger-term quality at 3. Adding an explicit 'Use when...' sentence with natural user phrasing would lift the weakest dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to improve Fallow maintainability, mentions SIG audit scores, or wants to act on sig-audit results.'

Include natural user phrasings and variations as trigger terms (e.g. 'maintainability rating', 'SIG 4-star target', 'audit regression') so the description surfaces for common formulations.

Name one or two more concrete actions in the description itself (e.g. 'runs sig-audit, selects the weakest property, and re-measures after each change') to raise specificity from 3 to 4.

DimensionReasoningScore

Specificity

Names the concrete domain ('Fallow maintainability', 'SIG audit deltas') and 1-2 concrete actions ('iteratively improve', 'retaining only changes that improve the targeted property'), but coverage is not comprehensive — the actual loop steps are absent. Fits anchor 3 rather than 4 because it lists fewer distinct specific actions than the anchor-4 example.

3 / 5

Completeness

The 'what' is clear (iterative improvement gated on measured audit deltas), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Contains relevant niche keywords ('Fallow', 'SIG audit', 'maintainability') that a user in this domain would say, but provides no common variations, synonyms, or explicit trigger phrases. Matches 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

'Fallow' plus 'SIG audit' carves a clear niche with minimal conflict risk against generic skills. Not 5 because the description states no distinct trigger phrasing and could mildly overlap with general refactoring/maintenance requests.

4 / 5

Total

13

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.