74/ 100Needs Work
0 critical
3 warnings
11 suggestions
112 checks passed
Domain scores
Anti-Slop
100
Accessibility
100
Enterprise
100
Issues
Warnings (3)
14.1-no-success-criterialine 1
No concrete success criteria found for eval readiness
Fix: Add pass/fail criteria or measurable outcomes (e.g., 'must return valid JSON', 'output < 100 lines')
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
1.2-desc-whenline 4
Description missing WHEN clause - recommended by agentskills spec
Fix: Consider adding 'Use when...' or 'Activate when...' to description
Suggestions (11)
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)
17.3-no-mode-awarenessline 7
Skill does not clarify standalone vs composed behavior
Fix: Clarify whether the skill works standalone, in pipelines, or both
14.2-no-examplesline 1
No input/output examples found
Fix: Add example input/output pairs or <example> blocks to make the skill testable
14.6-no-must-avoidline 1
No prohibitions or failure conditions found (nothing the skill must not do)
Fix: Add a short "Must not" or "Anti-patterns" list (e.g., 'never overwrite existing files', 'do not invent citations') so evaluators can write negative tests
3.3-name-single-wordline 2
Single-word names are less discoverable
Fix: Consider a two-word name like 'task-tracker' or 'code-reviewer'
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
1.19-non-portable-fieldline 3
Frontmatter keys outside the agentskills spec: category. Claude Code loads the skill with them; claude.ai uploads and the Skills API reject it with 'Unexpected key(s)'
Fix: Nothing to do for Claude Code or plugin distribution. To upload to claude.ai or the Skills API, ship frontmatter with only name, description, license, compatibility, metadata and allowed-tools
7.4-no-version-pinline 4
Package installation without version pinning
Fix: Pin versions for reproducible builds (e.g., package@1.2.3)
7.4-no-version-pinline 16
Package installation without version pinning
Fix: Pin versions for reproducible builds (e.g., package@1.2.3)
7.6-limited-negative-casesline 1
Skill has minimal negative case coverage; consider adding: limitations/constraints, error handling, edge cases
Fix: Document failure modes, limitations, and edge cases for production-ready skills
Badges
skillcheck
✕ passed
skillcheck
antislop 100
skillcheck
WCAG AA
skillcheck
WCAG AAA
skillcheck
enterprise
Get a report like this for your own skill
Run the free validator to see your score in seconds. Pro adds the substance checks: anti-slop, security, accessibility and agent readiness.