跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

full-audit

Exhaustive, denominator-driven audit of an entire area (codebase, docs, memory, skills, DB, config). Runs a 6-phase pipeline: scope agreement + prior-map diff -> deterministic sweep (counts/versions/paths/parsing plus cross-index reconciliation) -> parallel read-only content review (citations forced, rule dry-run) -> judgment (false-positive/UNCERTAIN triage) -> fix-vs-addition split (fixes applied immediately, additions proposed only) -> coverage-map recording. NOT for single-file or single-question checks (use a regular code review instead) or harness-maturity scoring against a fixed checklist (use a dedicated scoring tool instead). Triggers: '/full-audit', 'audit everything', 'full audit', 'find every gap'.

AlexZio00 · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add AlexZio00/sovereign-skills --skill full-audit

技能说明


name: full-audit description: "Exhaustive, denominator-driven audit of an entire area (codebase, docs, memory, skills, DB, config). Runs a 6-phase pipeline: scope agreement + prior-map diff -> deterministic sweep (counts/versions/paths/parsing plus cross-index reconciliation) -> parallel read-only content review (citations forced, rule dry-run) -> judgment (false-positive/UNCERTAIN triage) -> fix-vs-addition split (fixes applied immediately, additions proposed only) -> coverage-map recording. NOT for single-file or single-question checks (use a regular code review instead) or harness-maturity scoring against a fixed checklist (use a dedicated scoring tool instead). Triggers: '/full-audit', 'audit everything', 'full audit', 'find every gap'." skill_type: audit-orchestrator user_invocable: true triggers:

  • "/full-audit"
  • "audit everything"
  • "exhaustive audit"
  • "full audit"
  • "double-check everything"
  • "find every gap" depends_on: skills: [] agents: [] files: []

self-contained: Phase 2 spawns ad-hoc read-only reviewer subagents rather than

calling a fixed named skill/agent, and this skill ships with no bundled files of

its own — nothing environment-specific to declare here.

concurrency_profile: parallel_safe: true parallel_phase: "Phase 2 content review only (read-only reviewers, unlimited fan-out)" serialized_phases: "Phase 1 sweep and Phase 4 fix-bucket edits run sequentially, not concurrently with Phase 2" not_for:

  • "Single-file or single-question checks (use a code review instead)"
  • "Harness maturity scoring with a fixed checklist (that's a different, narrower tool)"
  • "A single docs-vs-code drift check (too narrow a scope for this)" see_also:
  • skill: project-check relation: "project-check=fixed-checklist health score, full-audit=open-ended exhaustive sweep with a denominator"

Full Audit — Exhaustive Area Review (v1.0)

Dominant Variable

Accuracy of the coverage claim — the word "exhaustive" ships with a method label or it doesn't ship at all. The moment an unreviewed area gets reported as reviewed, this skill has failed its own purpose.

Trigger

  • /full-audit [area] · "audit everything" · "exhaustive audit" · "full audit" · "double-check everything"

Discard If

  • Single file / single question needs checking → use a regular code review instead
  • The goal is a harness-maturity score against a fixed checklist → use a fixed-checklist scoring tool instead
  • The goal is a single docs-vs-code drift check → too narrow a scope for this
  • An identical-scope full audit finished within the last 7 days and nothing has changed → just diff against the existing coverage map instead

Key Assumptions

  1. Target area is agreed in Phase 0 — if not, don't start without an area table.
  2. Deterministic sweeping (scripts/grep) is available for the target — if not, skip Phase 1 and never claim "exhaustive" from Phase 2 (LLM review) alone.
  3. A prior coverage map can shrink the scope via diff — if not, do a full re-scan.

Phase 0: Agree Scope + Diff Against Prior Map

  1. Declare the target areas as a table (e.g. codebase / docs / global skills / memory / DB / settings).
  2. If a prior coverage map exists, read it and queue its remaining gaps first.
  3. Areas the user explicitly excludes go on the map as "intentionally excluded" — never silently dropped.

Phase 1: Deterministic Sweep

Whatever a machine can count, a script counts — never eyeball it:

  • Counts (test count, DB rows, file count) / version stamps (single source of truth in N places) / path and reference existence (dead links)
  • Parsing (YAML frontmatter, JSON settings) / stale-number greps (old numbers still lingering) / expiry (TTL, aging)
  • No inline throwaway scripts — write a script to a file, run it, then delete it (guards against quoting/escaping mistakes)
  • Reuse existing checkers first (test suites, project-specific validation scripts, linters)

Cross-index contract sweep (mandatory sub-step — this is the layer most exhaustive audits skip): The layer most easily missed in "exhaustive" audits is "does the index/routing doc match the real files?" — careful reading of individual files alone will never catch this. Sweep deterministically:

  • Index vs. reality reconciliation: names listed in an inventory/index file vs. the actual directory/file listing — check both directions (ghost entries with no backing file, and real files missing from the index)
  • Routing vs. reality reconciliation: names a routing table points to vs. whether those targets actually exist (dead routes to archived/renamed targets)
  • Declared-dependency sweep: for each unit's declared dependencies (other files/skills/agents it depends on), do all of them actually exist? (including malformed declarations, e.g. a flag where a name was expected)
  • Frontmatter parsing integrity: duplicate YAML keys in frontmatter (the later one silently wins — a safety profile could flip silently)
  • Rationale: in comparable audits, most of the gap came not from "reading more carefully" but from "did we actually sweep these specific things deterministically" — a model-independent, reproducible methodology improvement.

Phase 2: Content Review + Rule Dry-Run (Three-Layer Principle)

Structural checks (Phase 1) alone do NOT justify calling something "exhaustive" — exhaustive = structure + content + rule dry-run, three layers. Rules and guards can't be confirmed as actually working just by reading their documentation — only running them against mock input fills in the third layer. The three layers are non-substitutable: structural checks can come back clean while the content is wrong, and the content can be correct while a rule still fails to fire at runtime.

  • Fan out parallel review agents (unlimited breadth for coverage, read-only — never give reviewers edit access)
  • Force citations: reviewers must attach a grep/ls output as proof when they claim something is
阅读完整来源 ↗