agentleFS
jackchukajackchuka/skills/claude-skill-orchestration-audit/SKILL.md

claude-skill-orchestration-audit

Skill15 starsChanged 9 days agoMITView on GitHub

Audit skills for agentic orchestration quality. Checks subagent dispatch patterns, parallelism opportunities, anti-patterns, and alignment with the three-phase pattern (setup → dispatch → aggregate). Use when reviewing skill quality, saying "audit orchestration", "check my skills for parallelism", "skill orchestration review", or "/claude-skill-orchestration-audit".

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check skills against orchestration best practices in references/subagent-orchestration-best-practices.md.

    line 22
  2. Very specific:

    Read references/subagent-orchestration-best-practices.md — defines the rules

    line 32
  3. Very specific:

    Read references/agent-skill-analyzer.md — defines the per-skill analysis task

    line 33
  4. Distinctive:

    Look for phases that iterate over N independent items — even if written as sequential steps:

    line 47
  5. Distinctive:

    After all agents return:

    line 73
  6. Distinctive:

    After fixing, re-run the check and show updated table.

    line 114

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill Orchestration Audit

Check skills against orchestration best practices in references/subagent-orchestration-best-practices.md.

Arguments

  • Skill names: filter to specific skills
  • --fix: suggest and apply corrections interactively
  • Default: scan all skills authored by the user (metadata.author match)

Step 1: Setup

  1. Read references/subagent-orchestration-best-practices.md — defines the rules
  2. Read references/agent-skill-analyzer.md — defines the per-skill analysis task
  3. Glob ~/.claude/skills/*/SKILL.md to discover skills. If a directory path is provided as argument, glob <path>/*/SKILL.md instead
  4. Filter to skills where metadata.author matches the user (default: jackchuka). If skill names provided, filter to those instead
  5. Classify each skill into one of these categories:
CategoryAudit typeSignal
Multi-source aggregationOrchestration qualityAlready dispatches 2+ parallel agents against independent sources
Multi-step workflowLatent parallelism scanSequential phases where some sub-tasks within a phase are independent
Single-source operationSkipOne tool/API, truly linear flow, no fan-out possible
Meta/utilitySkipRouters, reference libraries, formatters

How to detect latent parallelism in multi-step workflows:

Look for phases that iterate over N independent items — even if written as sequential steps:

PatternExampleSignal
Per-item scaffolding"scaffold X for each actor/flow/feature"N independent CLI calls
Per-item implementation"write one file per resolver/page/command"N independent file writes to separate paths
Multi-source research"search Odoo, Oracle, SAP"N independent web fetches
Independent tracks"implement commands" then "implement queries"Parallel tracks after a shared dependency

A skill is "multi-step workflow" (audit it) if any phase has 2+ items that don't depend on each other. If every phase is truly linear with no fan-out, classify as "single-source operation" and skip.

  1. Set SKILLS_TO_AUDIT = all skills classified as "multi-source aggregation" or "multi-step workflow"

Step 2: Dispatch Agents (parallelize if possible)

Launch one agent per skill in SKILLS_TO_AUDIT. Each agent receives:

  • The skill's SKILL.md content
  • The skill's references/ directory listing (if any)
  • Its classification from Step 1
  • The check rules from references/agent-skill-analyzer.md

Each agent returns structured findings per the format in the reference file. If a skill's SKILL.md can't be read, skip gracefully.

Step 3: Aggregate & Report

After all agents return:

  1. Merge findings across all skills
  2. Sort by severity: ERROR → WARN → INFO
  3. Produce single consolidated report:
## Orchestration Audit

### Skills with existing orchestration

| Skill | Category | S1-4 | P1-4 | C1-3 | A1-3 | X1-4 | Issues |
|-------|----------|------|------|------|------|------|--------|

### Skills with latent parallelism opportunities

| Skill | Opportunity | Phase | Benefit | Issues |
|-------|-------------|-------|---------|--------|

### Findings

#### [skill-name]: [issue count] issues
- **[RULE]:[SEVERITY]** — [description]
  - Current: [what the skill does now]
  - Suggested: [what it should do]

### Top N Highest-Impact Improvements
Rank by benefit (high > medium > low) and usage frequency.

### Summary
N skills checked, M have orchestration, P have latent parallelism, X issues found (E errors, W warnings, I info)

Fix (if --fix or user asks)

SeverityAction
ERRORShow the fix, apply with Edit after user confirms
WARNShow suggestion, apply only if user agrees
INFONote for awareness, no auto-fix

After fixing, re-run the check and show updated table.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.