Home / Reports / agent-platform-tuning-management

agent-platform-tuning-management

Validated 5 Jun 2026 · Repository
PRO
75
Good
0 critical
3 warnings
10 suggestions
96 passed
Domain scores
Anti-Slop
100
Accessibility
100
Enterprise
80
Issues

Warnings (3)

10.1-no-env-docsline 1
No environment variable documentation found
Fix: Document required environment variables for deployment
19.2-reviewer-no-criterialine 11
Reviewer pattern detected but no evaluation criteria documented
Fix: Add a criteria section (checklist, rubric, or pass/fail conditions)
1.2-desc-whatline 3
Description missing WHAT clause (action verb) - recommended by agentskills spec
Fix: Consider starting with what the skill does, e.g., 'Creates...', 'Generates...', 'Validates...'

Suggestions (10)

16.3-no-rollbackline 11
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 11
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 11
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 11
No output contract found; unclear what the skill produces
Fix: Document what the skill produces (format, structure, side effects)
10.6-no-metadata-basicsline 1
Enterprise skill missing metadata.author and metadata.version for discoverability
Fix: Add metadata fields: author (team/org name) and version (semver). MCP-enhanced skills should also include mcp-server.
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 36
Ambiguous term 'correctly' found
Fix: Replace with specific, measurable criteria
OWASP Agentic (Cat 26)
Agent surface detected — performs consequential actions
1 warning
ASI-01: skippedASI-02: skippedASI-03: skippedASI-04: failASI-05: skippedASI-06: skippedASI-07: skippedASI-08: skippedASI-09: skippedASI-10: skippedASI-11: skipped
Badges
skillcheck ✕ passed skillcheck antislop 100 skillcheck WCAG AA skillcheck WCAG AAA skillcheck ✕ enterprise
Ship with confidence

Get a report like this for your own skill

Run the free validator to see your structural score, then unlock the substance checks — anti-slop, security, accessibility, agent-readiness — that move a skill from valid to safe to ship.