health-plugin/skills/health-agentic-audit/SKILL.md
Audit skills, commands, and agents for agentic output compliance — optimization tables, bare CLI commands. Use when batch-checking skill documentation quality.
npx skillsauth add laurigates/claude-plugins health-agentic-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Scan all plugin skills, commands, and agents for CLI output optimization opportunities. Checks for missing Agentic Optimizations tables, bare CLI commands without compact flags, and stale review dates.
Standards reference: .claude/rules/agentic-optimization.md and .claude/rules/skill-quality.md.
| Use this skill when... | Use another approach when... |
|------------------------|------------------------------|
| Auditing skills for agentic optimization compliance | General plugin audit (use /health:audit) |
| Finding missing Agentic Optimizations tables | Comprehensive environment check (use /health:check) |
| Reviewing CLI command patterns in skills | Plugin registry issues (use /health:plugins) |
| Quality-checking skill documentation | Manual skill review preferred |
| Batch-updating skill quality standards | Single skill needs updating |
pwdfind . -name 'SKILL.md' -o -name 'skill.md'find . \( -name 'SKILL.md' -o -name 'skill.md' \)find . -path '*/agents/*.md' -not -name 'README.md'| Parameter | Description |
|-----------|-------------|
| --fix | Add skeleton Agentic Optimizations tables to flagged skills and update modified dates |
| --verbose | Show all scanned files and detailed pattern matching results |
Execute this agentic output audit:
Find all skills, commands, and agents in the codebase:
find . -name 'SKILL.md' -o -name 'skill.md'find . \( -name 'SKILL.md' -o -name 'skill.md' \)find . -path '*/agents/*.md' -not -name 'README.md'Classify each file by type (skill, command, agent) for the report.
For each skill file:
## Agentic Optimization (with or without trailing "s")```bash or ```sh)Skip skills without any bash code blocks (informational skills). Note them in verbose mode.
Read execution and context sections of all files. Match commands against the bare CLI patterns in REFERENCE.md.
Search for these patterns inside fenced code blocks and backtick context commands (! backtick syntax).
For each file, extract the modified date from YAML frontmatter:
modified: YYYY-MM-DD from the first 20 linesmodified is older than 90 days as staleOutput a structured markdown report with these sections:
modified datesIf --verbose: also list all scanned files with their status (pass/fail per check).
When --fix is passed:
modified date in frontmatter of each modified file to today's datePrompt the user to fill in the TODO entries with actual optimized commands.
Match fenced code blocks to identify CLI tools:
```bash
<command>
And inline backtick commands in context sections:
<command>
### Frontmatter Extraction
Use the standard extraction pattern:
```bash
head -20 "$file" | grep -m1 "^modified:" | sed 's/^[^:]*:[[:space:]]*//'
| Context | Command |
|---------|---------|
| Agentic audit scan | /health:agentic-audit |
| Audit with auto-fix | /health:agentic-audit --fix |
| Verbose output | /health:agentic-audit --verbose |
| Find all skill files | find . \( -name 'SKILL.md' -o -name 'skill.md' \) 2>/dev/null |
| Check for Agentic Optimizations table | grep -l "## Agentic Optimizations" $(find . -name 'SKILL.md') 2>/dev/null |
/health:check - Full diagnostic scan/health:audit - Plugin relevance audit.claude/rules/agentic-optimization.md - Optimization standards.claude/rules/skill-quality.md - Required skill sectionsdevelopment
Debug HTTP APIs: trace requests, inspect headers. Use when a request fails: check status first.
documentation
Render architecture diagrams from text sources. Use when documenting system topology.
tools
Inspect JSON payloads and extract nested fields. Use when parsing API responses.
tools
--- name: no-description allowed-tools: Read --- # No Description This skill has no description and must be dropped with a warning.