Install Completeness Auditor
Pick your agent. Every command is ready to paste.
npx skills add zhnnky329/MathModeling-skills --skill completeness-auditorThe open skills CLI detects your agents (Claude Code, Cursor, Codex and 70+ more) and installs to the right folder. Add -g to install globally.
01
Install it
Run the command above, or upload the folder in Claude.
02
Ask naturally
Describe the task. Your agent loads completeness-auditor when the request matches its description.
03
Name it if needed
If it does not trigger, say “use the completeness-auditor skill”. In Codex, type $completeness-auditor.
Purpose
Check deliverable evidence, not whether every invoked skill left a ceremonial report.
Lean Checks
Per active Qx, require as applicable:
- manifest;
- method card;
- human decision ledger;
- risk-probe summary;
- latest run summary.
Lean completeness does not require final reports, freeze, paper, or G6 artifacts.
Submission Checks
Per Qx require:
- final method explanation;
- current language review JSON with all required named checks passing;
- final result analysis;
- robustness report;
- solution package;
- current frozen numbers;
- paper section and referenced figures.
Globally require symbol table, assumptions, references, consistency audit, completeness audit, and QA report.
Workflow
- Read
rigor_profile. - Resolve active Qx from manifests or artifacts.
- Check required artifacts and semantic fields.
- Check staleness only against materially cited evidence.
- Accept documented legacy equivalents during migration.
- Save
paper/audits/completeness_audit.mdonly in submission/final mode.
Status
PRESENT: required evidence exists and is current.MISSING: required evidence absent.INSUFFICIENT: artifact exists but required semantic fields/checks are missing.STALE: cited material evidence changed after approval/review.NOT_APPLICABLE: justified by task/profile.
Rules
- Do not require
≥5prose pass items. - Do not require a report just because a skill ran.
- Do not mark a decision stale for unrelated code, formatting, or file changes.
- Do not treat legacy artifact count as proof of semantic completeness.
- Do not repair artifacts during audit.
Verification
- Requirements match the active profile.
- Every gap names the missing evidence and producer/owner.
- Staleness links to a material changed source.
- Final verdict is
PASSEDonly when all submission requirements are satisfied.
Tips for Completeness Auditor
- • Start a fresh session after installing so your agent picks up the new skill.
- • It is part of a pack with 29 skills. Install only the ones you need with --skill to keep triggers precise.
- • If two skills overlap, mention the one you want by name.
Questions about Completeness Auditor
What does the Completeness Auditor skill do?
Audit whether the semantic evidence required by the active lean or submission profile exists and is current, without requiring one verbose artifact per skill or an arbitrary number of pass bullets.
How do I install Completeness Auditor?
Run "npx skills add zhnnky329/MathModeling-skills --skill completeness-auditor" in your project. The skills CLI installs it for Claude Code, Cursor, Codex and 70+ other agents. In Claude on the web, upload the skill folder as a ZIP under Customize > Skills.
Does Completeness Auditor work in Cursor and Codex?
Yes. Completeness Auditor uses the open SKILL.md format, so it works in Claude Code, Claude, Cursor, OpenAI Codex, Gemini CLI, GitHub Copilot and other agents that support agent skills.
Is Completeness Auditor free?
Completeness Auditor is open source on GitHub under the MIT license. It is free to install; check the license before commercial use.
Who made Completeness Auditor?
Completeness Auditor is published by zhnnky329 in the zhnnky329/MathModeling-skills repository, together with 28 other skills.




