Home / Reports / setup

setup

Validated 11 Oct 2026 · Repository
Pro
0/ 100Poor
14 critical
17 warnings
17 suggestions
78 checks passed

Domain scores

Anti-Slop
90
Accessibility
100
Enterprise
100

Issues

Critical (14)

2.1-lines-criticalline 18
Body exceeds 800 lines (got 3105)
Fix: Split into smaller sections or use external references
7.2-injection-riskline 133
Potential injection risk: unescaped variable in shell
Fix: Sanitize inputs and use parameterized commands
7.2-injection-riskline 339
Potential injection risk: unescaped variable in shell
Fix: Sanitize inputs and use parameterized commands
7.2-injection-riskline 724
Potential injection risk: unescaped variable in shell
Fix: Sanitize inputs and use parameterized commands
7.2-injection-riskline 1725
Potential injection risk: unescaped variable in shell
Fix: Sanitize inputs and use parameterized commands
7.2-injection-riskline 1726
Potential injection risk: unescaped variable in shell
Fix: Sanitize inputs and use parameterized commands
7.2-injection-riskline 1729
Potential injection risk: unescaped variable in shell
Fix: Sanitize inputs and use parameterized commands
7.2-injection-riskline 1936
Potential injection risk: unescaped variable in shell
Fix: Sanitize inputs and use parameterized commands
7.2-injection-riskline 2775
Potential injection risk: unescaped variable in shell
Fix: Sanitize inputs and use parameterized commands
7.2-injection-riskline 2778
Potential injection risk: unescaped variable in shell
Fix: Sanitize inputs and use parameterized commands
7.2-injection-riskline 2782
Potential injection risk: unescaped variable in shell
Fix: Sanitize inputs and use parameterized commands
7.2-injection-riskline 2786
Potential injection risk: unescaped variable in shell
Fix: Sanitize inputs and use parameterized commands
9.2-body-tokens-criticalline 18
Body exceeds 8000 token maximum (estimated 27223)
Fix: Significantly reduce content or use external references
9.3-total-tokensline 1
Total exceeds 15000 token budget (estimated 27315)
Fix: Reduce overall skill length significantly

Warnings (17)

16.1-no-stop-conditionline 18
Complex skill lacks explicit stop conditions
Fix: Add stop/termination criteria (e.g., 'Stop after N iterations', 'Abort if error rate exceeds threshold')
2.2-hardcoded-pathline 1901
Hardcoded user path detected
Fix: Use environment variables or relative paths
19.3-generator-no-output-specline 18
Generator pattern detected but no output format specified
Fix: Document the output format (template, schema, or example output)
19.4-inversion-no-questionsline 18
Inversion pattern detected but no question framework documented
Fix: Document what questions the skill asks and when it stops asking
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
4.7-desc-workflow-stepsline 2
Description contains workflow iteration verb ('for each'): Claude may treat description as complete instruction and skip SKILL.md body
Fix: Move workflow steps to the SKILL.md body. Description should only contain activation triggers (when to use, what it does)
1.2-desc-whenline 3
Description missing WHEN clause - recommended by agentskills spec
Fix: Consider adding 'Use when...' or 'Activate when...' to description
1.3-tools-unknownline 5
Unknown tool 'TeamCreate' in allowed-tools
Fix: Use known tools: Read, Write, Edit, Bash, Glob, Grep, etc.
1.3-tools-unknownline 5
Unknown tool 'SendMessage' in allowed-tools
Fix: Use known tools: Read, Write, Edit, Bash, Glob, Grep, etc.
7.5-pii-detectedline 674
Potential international phone number detected in content
Fix: Use placeholder: +1-555-000-0000
7.5-pii-detectedline 1976
Potential US phone number detected in content
Fix: Use placeholder: 555-000-0000
7.5-pii-detectedline 1977
Potential US phone number detected in content
Fix: Use placeholder: 555-000-0000
7.5-pii-detectedline 3031
Potential email address detected in content
Fix: Use placeholder: user@example.com
7.5-pii-detectedline 3033
Potential email address detected in content
Fix: Use placeholder: user@example.com
7.7-task-ambiguityline 45
Ambiguous instruction detected (vague-completeness)
Fix: List the specific cases or scope to cover
12.3-workflow-vague-stepline 1106
Step is too brief to be actionable: "**Persist.**"
Fix: Add specific details: what, where, and how
12.5-no-exit-criterialine 94
13 of 13 phases lack exit criteria; Claude may skip phases or run past completion
Fix: Add exit criteria to each phase: 'Exit when: [specific condition]'

Suggestions (17)

5.4-ai-vocabularyline 693
AI-vocabulary word detected: underscores
Fix: Replace with a plain word; these words cluster in LLM output
17.4-no-interface-sectionline 18
Input and output contracts exist but lack a dedicated interface section
Fix: Add a ## Interface or ## I/O section to consolidate contract documentation
3.3-name-single-wordline 2
Single-word names are less discoverable
Fix: Consider a two-word name like 'task-tracker' or 'code-reviewer'
15.6-subagent-no-return-formatline 2265
Subagent spawning at line 2265 lacks return format specification
Fix: Specify what format the subagent should return results in (JSON, markdown table, structured text)
13.2-excessive-referencesline 18
Skill references 30 unique file paths; consider organizing into a reference section
Fix: Group related paths under a ## References or ## Files heading
13.3-no-reference-sectionline 18
Skill has 5+ file references but no dedicated reference section
Fix: Add a ## References, ## Files, or ## Dependencies section to organize paths
4.2-ambiguous-termline 452
Ambiguous term 'appropriate' found
Fix: Replace with specific, measurable criteria
4.2-ambiguous-termline 772
Ambiguous term 'many' found
Fix: Replace with specific, measurable criteria
4.2-ambiguous-termline 1027
Ambiguous term 'appropriate' found
Fix: Replace with specific, measurable criteria
4.2-ambiguous-termline 2390
Ambiguous term 'many' found
Fix: Replace with specific, measurable criteria
4.3-output-formatline 1
Skill mentions output but doesn't specify format
Fix: Add an '## Output' section with format examples
4.6-wisdom-platitudeline 585
Platitude detected: '[X] is essential/crucial/important to [Y]'
Fix: Replace with a concrete instruction or measurable criterion
1.12-maxturns-not-skill-fieldline 15
maxTurns is a subagent field; Claude Code ignores it in SKILL.md
Fix: Remove maxTurns, or set it in a subagent definition and run the skill there with 'context: fork' and 'agent: <that subagent>'
1.19-non-portable-fieldline 4
Frontmatter keys outside the agentskills spec: argument-hint, effort, maxTurns. 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 1097
Package installation without version pinning
Fix: Pin versions for reproducible builds (e.g., package@1.2.3)
9.4-reference-countline 1
High number of external references (74)
Fix: Consider consolidating references
12.4-no-troubleshootingline 18
Complex technical skill lacks troubleshooting section
Fix: Add a ## Troubleshooting section with Error/Cause/Fix table for common issues

OWASP Agentic (Cat 26)

Agent surface detected: declares tool beyond Read/Glob/Grep: Bash; declares tool beyond Read/Glob/Grep: Write; declares tool beyond Read/Glob/Grep: Edit; declares tool beyond Read/Glob/Grep: AskUserQuestion; declares tool beyond Read/Glob/Grep: Agent; declares tool beyond Read/Glob/Grep: TeamCreate; declares tool beyond Read/Glob/Grep: SendMessage; ingests external content; orchestrates subagents; performs consequential actions
4 warning
  • 26.04-ASI04-unpinned-dep warning unpinned npm install "playwright" (no @version) line 1080
    Fix: pin the version, e.g. npm install playwright@X.Y.Z
  • 26.09-ASI09-destructive-no-gate warning destructive op "overwrite" has no confirmation/approval gate within +/-10 lines line 1546
    Fix: add an explicit human-approval gate (STOP:, AskUserQuestion, confirm) before the destructive op
  • 26.09-ASI09-destructive-no-gate warning destructive op "truncate" has no confirmation/approval gate within +/-10 lines line 1671
    Fix: add an explicit human-approval gate (STOP:, AskUserQuestion, confirm) before the destructive op
  • 26.10-ASI10-safeguard-disable warning safeguard-disabling instruction "bypass" with no explicit user-approval note line 755
    Fix: require explicit user approval before disabling a safeguard, or remove the bypass
ASI-01: passASI-02: skippedASI-03: skippedASI-04: failASI-05: skippedASI-06: passASI-07: passASI-08: skippedASI-09: failASI-10: failASI-11: skipped

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.