CtrlK
BlogDocsLog inGet started
Tessl Logo

sig-audit

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

61

Quality

71%

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/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The content is exceptionally lean and well-sequenced with an explicit verification checkpoint, and it is appropriately self-contained for a simple single-task skill. Its only weakness is actionability: steps name artifacts but omit the executable commands, script names, or file paths that would make them fully copy-paste ready.

Suggestions

Add the concrete commands or script paths for the key steps (e.g., how to run a property measurement and how to invoke 'repository verification') to move actionability toward 3.

Name the specific measurement scripts referenced in step 1 so Claude knows exactly what to read and run.

Optionally add a one-line note on the expected verification command or exit criteria to make the step-6 checkpoint fully executable.

DimensionReasoningScore

Conciseness

The body is a terse 6-step list plus one constraint line with no padding and no explanation of concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor; it is not the level below because there is nothing unnecessary to tighten.

3 / 3

Actionability

Steps refer to concrete artifacts ('existing audit and measurement scripts', 'repository verification') but give no executable commands, script names, or file paths, so guidance is directional but missing the key execution details; it is above level 1 because it does instruct concretely rather than vaguely.

2 / 3

Workflow Clarity

Steps 1-6 form a clear sequence with an explicit verification checkpoint in step 6 ('Run repository verification...') and a quality gate in step 5, matching the 'clear sequence with explicit validation steps' anchor; for a simple skill this suffices despite the lack of a retry loop.

3 / 3

Progressive Disclosure

No bundle files exist and the body is under 50 lines, single-task, and well-organized as a self-contained numbered workflow, so per the rubric's simple-skill guideline progressive disclosure scores 3 on well-organized sections alone.

3 / 3

Total

11

/

12

Passed

Description

57%

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 occupies a clearly distinctive niche, but it omits an explicit 'Use when...' trigger clause and relies on domain jargon rather than broad natural keyword coverage. Completeness and trigger-term quality are the main weaknesses, while distinctiveness is strong.

Suggestions

Add an explicit 'Use when...' clause stating when to run this skill (e.g., 'Use when auditing Fallow maintainability or refreshing the SIG audit report'), which would lift completeness to 3.

Broaden trigger-term coverage with natural variations a user might say (e.g., 'SIG audit', 'maintainability score', 'audit report refresh') rather than relying solely on 'SIG system properties'.

Spell out a few more concrete measured actions (e.g., 'compute property scores', 'diff against the prior revision') to move specificity toward a comprehensive list of operations.

DimensionReasoningScore

Specificity

Quotes 'Measure Fallow maintainability using the repository's SIG system properties' and 'update the evidence-backed audit report' — names the domain and two concrete actions, but the actions are conceptual rather than a comprehensive list of specific operations, matching the anchor that names a domain and some actions without being comprehensive.

2 / 3

Completeness

It states what the skill does ('Measure... update the... audit report') but has no 'Use when...' clause or equivalent explicit trigger guidance for when to invoke it, so completeness is capped at 2 per the judging guidelines.

2 / 3

Trigger Term Quality

Keywords like 'SIG system properties', 'maintainability', and 'audit report' are relevant to the niche, but the phrasing leans on proper-noun jargon and omits common natural variations a user might say, matching 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

The narrow proper-noun framing 'Fallow maintainability using the repository's SIG system properties' defines a clear niche with distinct triggers unlikely to overlap with generic skills, matching the clear-niche anchor.

3 / 3

Total

9

/

12

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.

Validation16 / 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.