Agent skill · Security

tool-process-audit

Diagnose a named or described business/engineering process for bottlenecks, risks, and optimization opportunities. Use when a user asks to review, map, or improve a workflow and wants concrete next steps with effort/impact tradeoffs.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill tool-process-audit --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 6 KB
Bundled scripts: none
Path: skills/analysis/tool-process-audit/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Process Audit Audit a business or engineering process end-to-end. Confirm what process is in scope, map current state, test for failure/inefficiency, and return ranked, actionable improvements. Keep momentum high: avoid long interviews unless ambiguity or risk justifies deeper questioning. ## Relationship to Other Skills - `lp-do-critique`: Critiques document quality. Use this skill for process reality and operational performance. - `lp-do-fact-find`: Produces planning artifacts for feature/build work. Use this skill for process diagnosis and optimization recommendations. ## Inputs | Input | Required | Notes | |------|----------|-------| | Process name or description | Yes | One sentence is enough to start. | | Optional focus tests | No | User-specified lenses (for example: compliance, handoffs, cost, automation). | | Optional artifacts | No | SOPs, checklists, tickets, logs, screenshots, dashboards. | If the user gives minimal detail, proceed with a normal walkthrough audit and clearly mark assumptions. ## Operating Mode **CONFIRM -> MAP -> TEST -> RANK -> RECOMMEND** **Allowed:** - Ask targeted clarifying questions (max 5 per turn) - Infer missing details and mark confidence as

What's inside
Steps it walks through
  1. Relationship to Other Skills
  2. Inputs
  3. Operating Mode
  4. Workflow
  5. 1) Intake
  6. 2) Disambiguation (only when uncertainty exists)
  7. 3) Scope What to Test
  8. 4) Map Current State
  9. 5) Run Audit Lenses
  10. 6) Rank Findings
  11. 7) Build Optimization Plan
  12. 8) High-Stakes Risk Rule
  13. Output Contract (Required Order)
  14. Response Template
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the tool-process-audit skill do?

Diagnose a named or described business/engineering process for bottlenecks, risks, and optimization opportunities. Use when a user asks to review, map, or improve a workflow and wants concrete next steps with effort/impact tradeoffs.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill tool-process-audit --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going