Setting the skill. One moment.
Skills
Skill 36 of 200
Enforce output quality, evidence verification, and quality gates across security audits.
1 minute · 270 words · 4 sections
Install
npx skills add github/awesome-copilot --skill audit-integritynpx skills add github/awesome-copilot/plugin marketplace add github/awesome-copilotThe first command installs just this skill, by the name in its SKILL.md; the second installs the whole repository.
Enforce output quality, intellectual honesty, and continuous improvement across security audits and code reviews.
This skill provides 7 modular capabilities in the references/ directory. Load each file when you reach its execution phase:
| Component | Reference File | Purpose |
|---|---|---|
| Clarification Protocol | references/clarification-protocol.md (opens in a new tab) | Ask a maximum of 2 targeted questions when scope is not clear |
| Anti-Rationalization Guard | references/anti-rationalization-guard.md (opens in a new tab) | Prohibited rationalizations and mandatory responses for findings |
| Self-Critique Loop | references/self-critique-loop.md (opens in a new tab) | Mandatory second pass to verify evidence and coverage |
| Retry Protocol | references/retry-protocol.md (opens in a new tab) | Tool failure and empty search handling: retry once, then document |
| Non-Negotiable Behaviors | references/non-negotiable-behaviors.md (opens in a new tab) | Mandatory rules: do not fabricate, cite evidence, report gaps |
| Self-Reflection Quality Gate | references/self-reflection-quality-gate.md (opens in a new tab) | Scoring rubric (1–10 scale) with a minimum threshold of 8 |
| Self-Learning System | references/self-learning-system.md (opens in a new tab) | Templates and rules for lessons and security memories |
Load reference files as you reach each phase:
Enforce output quality, evidence verification, and quality gates across security audits. Use this skill when you perform SAST, SCA, threat modeling, or security code reviews. Use this skill to verify code locations and taint traces for all findings. Use this skill to prevent the suppression of valid security findings. Use this skill to evaluate reports against quality thresholds (score ≥ 8/10) before delivery.
The verbatim description from this skill’s front matter — the string an agent matches on to decide whether to load it.
skills/audit-integrity/SKILL.mdmain, last pushed 6 November 2026.SKILL.md, not by matching a directory convention. 2 distinct layouts observed: .github/skills/*/SKILL.md, skills/*/SKILL.md.h1 and no skipped levels:.github/plugin/marketplace.json by GitHub, declaring 207 plugins. It is read for editorial metadata only — never as the skill index, which is always the repository tree./github/awesome-copilot.md, and each skill at its own .md URL.7 files · 14 KB
Everything this skill ships beside its prose. All of it is set here, as subchapters of skill 36.
Documentation the agent loads on demand, rather than up front.