Home / Reports / skill-creator

skill-creator

Validated 5 Jun 2026 · Repository

PRO

Needs Work

0 critical

4 warnings

17 suggestions

88 passed

Domain scores

Anti-Slop

100

Accessibility

100

Enterprise

100

Issues

Warnings (4)

16.1-no-stop-conditionline 7

Complex skill lacks explicit stop conditions

Fix: Add stop/termination criteria (e.g., 'Stop after N iterations', 'Abort if error rate exceeds threshold')

19.2-reviewer-no-criterialine 7

Reviewer pattern detected but no evaluation criteria documented

Fix: Add a criteria section (checklist, rubric, or pass/fail conditions)

19.3-generator-no-output-specline 7

Generator pattern detected but no output format specified

Fix: Document the output format (template, schema, or example output)

4.5-desc-no-triggersline 2

Description lacks triggering conditions

Fix: Add phrases like 'Use when...', 'Triggers on...', or 'Applies to...' to help Claude select this skill

Suggestions (17)

16.3-no-rollbackline 7

State-modifying skill lacks rollback or recovery guidance

Fix: Add rollback instructions: how to undo changes if something goes wrong (e.g., git revert, backup/restore steps)

16.4-no-idempotencyline 7

Skill does not document whether it is safe to re-run

Fix: Add idempotency guidance: state whether running the skill twice produces the same result or causes side effects

17.1-no-input-contractline 7

No input contract found; unclear what data the skill expects

Fix: Document what the skill expects as input (format, required fields, constraints)

17.2-no-output-contractline 7

No output contract found; unclear what the skill produces

Fix: Document what the skill produces (format, structure, side effects)

14.3-no-binary-verdictline 1

Skill has success criteria but no binary pass/fail language

Fix: Add explicit pass/fail indicators so evaluators reach the same verdict independently

3.4-gerund-namingline 2

Skill name could use gerund form for clarity

Fix: Consider gerund-style names like 'processing-pdfs' or 'analyzing-logs' (per best practices)

18.1-no-confidence-signalline 1

No confidence signal found for orchestrator decision-making

Fix: Add confidence indicators (e.g., confidence: high/medium/low) so orchestrators can route or retry

18.3-no-structured-outputline 1

No structured output format defined for machine consumption

Fix: Define a structured output format (JSON, YAML, or table) so downstream tools can parse results

4.2-ambiguous-termline 29

Ambiguous term 'good' found