audit-docs
Audit cross-document coherence: docs ↔ roadmap ↔ code ↔ fix index ↔ issues. Finds drift — features in docs/ not in the roadmap (or vice versa), fix-index entries already merged/closed, broken documentation-map links, dependency cycles, artifacts in the wrong language, naming-conv
Install
npx skills add https://github.com/gtrabanco/agentic-workflow/tree/main/skills/audit-docs
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install gtrabanco-agentic-workflow@llmmart
git clone https://github.com/gtrabanco/agentic-workflow.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole gtrabanco/agentic-workflow collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Audit Docs
A read-first audit answering "do the docs still match reality?" Produces a findings report; it does not silently rewrite docs.
Turn contract — verify before ending the turn
✓ The AUDIT DOCS fixed-format report was printed, ending in `Decision: PASS | FAIL`
✓ No doc was rewritten without explicit --fix / user go-ahead
✓ The closing `→ Next:` block is printed as the ABSOLUTE last output
About to end the turn with any box unchecked? The turn is NOT done — complete the missing box first (weak models drop end-of-document duties; this list is first on purpose).
When to use
- Before a release or milestone, after merging several features/fixes, or whenever the doc set might have drifted from the code and issues.
Step 0 — Discover the project (always first)
Per the agent guide's Workflow conventions + documentation map, then read what THIS skill needs: the roadmap, the fix index + template, and the feature folder layout — the map tells you which links and invariants to check.
Checks
Run these and collect findings (cite paths/lines/issue numbers each):
- Roadmap ↔ feature folders. Every
docs/features/<NN>-<slug>/is in the roadmap, and every roadmap entry has a folder (or is explicitly "scheduled"). - Feature dependencies. SPEC
Depends on/Branchfields are valid; no dependency cycles; ordering is consistent with the roadmap. - Fix index hygiene. Every entry maps to an open issue and an unmerged branch; flag entries whose issue is closed or whose PR merged (should have been removed). Flag open fix branches missing from the index.
- Documentation-map links resolve. Every file the map references exists; flag "scheduled, not yet authored" items so they aren't mistaken for drift.
- Broken intra-doc links. Relative links/anchors point at real files/sections.
- Issue references. Acceptance/known-issues lines referencing
#Naren't pointing at long-closed issues without note. - Language & naming conventions. Artifacts in the project's docs language (this repo: English); file/dir naming matches conventions (e.g. kebab-case TS files, PascalCase components).
- Invariant tags. If the project uses invariant/decision IDs (e.g. INV-/D-/KI-), spot-check that referenced IDs exist where claimed.
- PR-link integrity on
donerows. Every roadmap row (and fix-index entry) with statusdonecarries a linked PR reference —done · [#<pr>](<pr-url>). For each baredone, find its PR in the forge (gh pr list --state all --head feat/<NN>-<slug>or by title) and propose the row update; adonewith no PR found at all is HIGH severity (the unit may never have been closed out).
Workflow discipline (checks 10–14) — the executor skills enforce these at write time; this audit verifies they actually held. Each check is mechanical: run the command shown, don't infer.
- Phase naming — keyed on the carrier, like check 11.
- lane-era —
bun scripts/phase-lint.mjs <unit-doc>(ownerskills/phase-contract/SKILL.md) must printverdict PASS, andbun scripts/ceremony.mjs docs check-phase-labels --slug <slug>must answervalid: true. AS#hit in a lane-era doc is not a phase label: since #308S#is the requirement id. - legacy carriers only —
grep -rnE '\bS[0-9]+\b|\bStep [0-9]' docs/features/*/{PLAN,TASKS,progress}.mdmust return nothing: plans useP1, P2, …("phases") only. Any hit: LOW (rename), plus check the executor argument still resolves. Today's 22 hits are all literalStep 0 — Discover the projectcitations; the grep is the legacy carrier's, so a lane-eraS#is never read through it.
- lane-era —
- Per-phase doc discipline — keyed on the unit's own carrier. Pick the
carrier mechanically, never by guess:
TASKS.mdin the unit folder means legacy carriage; its absence means the unit doc's## Tasks/## Log.- lane-era —
bun scripts/ceremony.mjs docs check-tasks-ticks --slug <slug>andbun scripts/ceremony.mjs docs check-progress-entry --slug <slug>must both reportvalid: true: every- [x] P<n>has itsP<n>line in## Log, and no task lacks one. Cite those two fields, nevercheck-all(itscommit-format/docs-languagefields are checks 14 and 7). A doc with no## Taskssection answersn/a—no ## Tasks section — legacy carrier— so the vacuous case routes to the legacy branch, never to a silent pass. - legacy — the original assertions on that unit's own files: completed
phases ticked in
TASKS.md, oneprogress.mdentry per completed phase, the literal close-out tasks in the final phase. - Severity — a
doneunit whose ledger disagrees with its tasks: HIGH. The same on anin-progressunit: LOW (it may still be settling). Onlyhigh/lowexist in this report's legend. - Close-out is
audit-pr's contract (receipt + ordered gates): cite its verdict, never re-derive the retired literal tasks here.
- lane-era —
- Branch & PR discipline vs the forge. For every
doneunit: its PR exists, targets the default branch, has a non-empty body, and carriesCloses #<n>when the unit is issue-born (SPEC references an issue). Also scan recent default-branch history (git log --first-parent) for feature/fix-scoped changes committed directly without a PR: HIGH. - Generated-docs provenance (only when the documentation map declares a
Docs siteblock; otherwise state n/a). Scan the declared content dir for orphan pages each: (a) itssource-unitexists in the roadmap or fix index — no match is an orphan (low: propose deletion or re-attribution); (b) the unit's PR merged after the page'supdateddate with commits touching the page's subject paths — that page is stale (LOW: propose ). Cite page path + unit per finding. - Commit format & dependency discipline. Sample the unit branches'
commits:
<type>(<scope>): <summary>conventional format (violations: LOW). Everyin-progress/donerow'sDepends on:closure was merged — a unit built on unmerged deps is HIGH unlessdecisions.mdrecords a user-forced override (--force), which downgrades it to LOW (documented risk). - README currency against what shipped. Run each README against the
tree:
rg -n '<a retired name or stale claim>' README.md packages/*/README.mdand every hit that names a surface the tree no longer carries (a retired skill in an install/uninstall example, a command count or package count the tree contradicts, a "none yet" beside shipped subcommands) is HIGH — the claim misleads a reader who acts on it. Its mirror: a shipped, consumer-facing surface with no README entry at all is HIGH (the document-or-don't-coin residue read at README scope —product-auditowns the product-wide sweep, this check is the docs-tree half). Superseded prose left standing beside its replacement is LOW. Owners: the rule isAGENTS.md§Working rules, the step isskills/unit-lane/references/DOCS.md.
Adapt the list to what the project has; skip checks for absent structures and say so.
Process
Discover, then run the checks with
grep, file reads, and the forge CLI (per Workflow conventions; examples usegh).Produce the findings report — return exactly (fixed output contract):
AUDIT DOCS — scope: <docs tree / roadmap / fix index / issues checked> | # | Check (1-15) | Finding | Sev | Evidence | Proposed fix | |---|-------------|---------|-----|----------|--------------| | 1 | <which> | <what> | high|low | <path:line / #issue> | <smallest action> | Checks run: <n>/15 (skipped: <which + why — absent structures only>) Summary: <1-2 sentences> Decision: PASS | FAIL (FAIL if any high-severity finding is open)Sev: high = misleading or broken; low = cosmetic. Only
highandloware defined in this legendFix only on request. With explicit
--fix(or user go-ahead), apply the low-risk corrections (remove a merged fix-index row, fix a dead link, register a missing roadmap entry, add a verified PR link to a baredonerow). Leave judgment calls to the user.
Guardrails
- Read-first; never bulk-rewrite docs unprompted.
- Distinguish genuine drift from intentionally "scheduled/deferred" items — don't report deliberate tradeoffs as errors.
- Keep changes surgical and within docs; no code or behavior changes.
Portability (agents other than Claude Code)
The workflow is the contract; Claude Code features are conveniences. On an agent that lacks one, apply the fallback — never skip the step the feature enables:
- No slash-command menu — where this skill says
/<skill>, open that skill'sSKILL.md(wherever your agent installed the skills) and follow it literally, in a fresh conversation: hand-offs assume a clean context. - No per-skill
model:/effort:— no skill pins a tier; pick tiers yourself: these are mostly mechanical cross-document checks — a mid-tier model is enough; escalate to your strongest only for a deep audit.
Relationship to other skills
- Complements
unit-lane(which creates the docs this audits) andtriage-issue(which keeps the fix index honest). - Run standalone anytime; no required predecessor.
Done when
A severity-ranked findings report exists, and any approved low-risk fixes are applied — with genuine deferrals left untouched and labeled as such.
The closing
→ Next:block is printed:→ Next: apply the approved low-risk fixes, then re-run /audit-docs to confirm clean · real drift (not cosmetic) → /triage-issue · a concrete defect → /unit-lane --fix <n> · already clean → nothing to do
Files (agentic-workflow)
-
SKILL.md 10.7 KB
--- name: audit-docs user-invocable: true version: 4.10.0 argument-hint: "[--fix]" author: "Gabriel Trabanco <1969593+gtrabanco@users.noreply.github.com>" license: MIT description: > Audit cross-document coherence: docs ↔ READMEs ↔ roadmap ↔ code ↔ fix index ↔ issues. Finds drift — features in docs/ not in the roadmap (or vice versa), fix-index entries already merged/closed, broken documentation-map links, dependency cycles, artifacts in the wrong language, naming-convention violations — and reports them ranked by severity, fixing only low-risk items on request. Model-agnostic: the skill inherits whatever model and effort your agent session is already using. Triggers: "check doc consistency", "are the docs in sync", "audit the docs", "doc coherence review", "did the docs drift", "validate the roadmap". --- # Audit Docs A read-first audit answering "do the docs still match reality?" Produces a findings report; it does not silently rewrite docs. ## Turn contract — verify before ending the turn ``` ✓ The AUDIT DOCS fixed-format report was printed, ending in `Decision: PASS | FAIL` ✓ No doc was rewritten without explicit --fix / user go-ahead ✓ The closing `→ Next:` block is printed as the ABSOLUTE last output ``` About to end the turn with any box unchecked? The turn is NOT done — complete the missing box first (weak models drop end-of-document duties; this list is first on purpose). ## When to use - Before a release or milestone, after merging several features/fixes, or whenever the doc set might have drifted from the code and issues. ## Step 0 — Discover the project (always first) Per the agent guide's **Workflow conventions** + **documentation map**, then read what THIS skill needs: the roadmap, the fix index + template, and the feature folder layout — the map tells you which links and invariants to check. ## Checks Run these and collect findings (cite paths/lines/issue numbers each): 1. **Roadmap ↔ feature folders.** Every `docs/features/<NN>-<slug>/` is in the roadmap, and every roadmap entry has a folder (or is explicitly "scheduled"). 2. **Feature dependencies.** SPEC `Depends on` / `Branch` fields are valid; no dependency cycles; ordering is consistent with the roadmap. 3. **Fix index hygiene.** Every entry maps to an **open** issue and an unmerged branch; flag entries whose issue is closed or whose PR merged (should have been removed). Flag open fix branches missing from the index. 4. **Documentation-map links resolve.** Every file the map references exists; flag "scheduled, not yet authored" items so they aren't mistaken for drift. 5. **Broken intra-doc links.** Relative links/anchors point at real files/sections. 6. **Issue references.** Acceptance/known-issues lines referencing `#N` aren't pointing at long-closed issues without note. 7. **Language & naming conventions.** Artifacts in the project's docs language (this repo: **English**); file/dir naming matches conventions (e.g. kebab-case TS files, PascalCase components). 8. **Invariant tags.** If the project uses invariant/decision IDs (e.g. INV-/D-/KI-), spot-check that referenced IDs exist where claimed. 9. **PR-link integrity on `done` rows.** Every roadmap row (and fix-index entry) with status `done` carries a linked PR reference — `done · [#<pr>](<pr-url>)`. For each bare `done`, find its PR in the forge (`gh pr list --state all --head feat/<NN>-<slug>` or by title) and propose the row update; a `done` with no PR found at all is HIGH severity (the unit may never have been closed out). **Workflow discipline (checks 10–14)** — the executor skills enforce these at write time; this audit verifies they actually held. Each check is mechanical: run the command shown, don't infer. 10. **Phase naming — keyed on the carrier, like check 11.** - **lane-era** — `bun scripts/phase-lint.mjs <unit-doc>` (owner `skills/phase-contract/SKILL.md`) must print `verdict PASS`, and `bun scripts/ceremony.mjs docs check-phase-labels --slug <slug>` must answer `valid: true`. A `S#` hit in a lane-era doc is not a phase label: since #308 `S#` is the requirement id. - **legacy carriers only** — `grep -rnE '\bS[0-9]+\b|\bStep [0-9]' docs/features/*/{PLAN,TASKS,progress}.md` must return nothing: plans use `P1, P2, …` ("phases") only. Any hit: LOW (rename), plus check the executor argument still resolves. Today's 22 hits are all literal `Step 0 — Discover the project` citations; the grep is the legacy carrier's, so a lane-era `S#` is never read through it. 11. **Per-phase doc discipline — keyed on the unit's own carrier.** Pick the carrier mechanically, never by guess: `TASKS.md` in the unit folder means legacy carriage; its absence means the unit doc's `## Tasks`/`## Log`. - **lane-era** — `bun scripts/ceremony.mjs docs check-tasks-ticks --slug <slug>` and `bun scripts/ceremony.mjs docs check-progress-entry --slug <slug>` must both report `valid: true`: every `- [x] P<n>` has its `P<n>` line in `## Log`, and no task lacks one. Cite those two fields, never `check-all` (its `commit-format`/`docs-language` fields are checks 14 and 7). A doc with no `## Tasks` section answers `n/a` — `no ## Tasks section — legacy carrier` — so the vacuous case routes to the legacy branch, never to a silent pass. - **legacy** — the original assertions on that unit's own files: completed phases ticked in `TASKS.md`, one `progress.md` entry per completed phase, the literal close-out tasks in the final phase. - **Severity** — a `done` unit whose ledger disagrees with its tasks: HIGH. The same on an `in-progress` unit: LOW (it may still be settling). Only `high`/`low` exist in this report's legend. - **Close-out** is `audit-pr`'s contract (receipt + ordered gates): cite its verdict, never re-derive the retired literal tasks here. 12. **Branch & PR discipline vs the forge.** For every `done` unit: its PR exists, targets the default branch, has a non-empty body, and carries `Closes #<n>` when the unit is issue-born (SPEC references an issue). Also scan recent default-branch history (`git log --first-parent`) for feature/fix-scoped changes committed directly without a PR: HIGH. 13. **Generated-docs provenance (only when the documentation map declares a `Docs site` block; otherwise state n/a).** Scan the declared content dir for orphan pages each: (a) its `source-unit` exists in the roadmap or fix index — no match is an **orphan** (low: propose deletion or re-attribution); (b) the unit's PR merged **after** the page's `updated` date with commits touching the page's subject paths — that page is **stale** (LOW: propose ). Cite page path + unit per finding. 14. **Commit format & dependency discipline.** Sample the unit branches' commits: `<type>(<scope>): <summary>` conventional format (violations: LOW). Every `in-progress`/`done` row's `Depends on:` closure was merged — a unit built on unmerged deps is HIGH unless `decisions.md` records a user-forced override (`--force`), which downgrades it to LOW (documented risk). 15. **README currency against what shipped.** Run each README against the tree: `rg -n '<a retired name or stale claim>' README.md packages/*/README.md` and every hit that names a surface the tree no longer carries (a retired skill in an install/uninstall example, a command count or package count the tree contradicts, a "none yet" beside shipped subcommands) is **HIGH** — the claim misleads a reader who acts on it. Its mirror: a shipped, consumer-facing surface with no README entry at all is **HIGH** (the document-or-don't-coin residue read at README scope — `product-audit` owns the product-wide sweep, this check is the docs-tree half). Superseded prose left standing beside its replacement is **LOW**. Owners: the rule is `AGENTS.md` §Working rules, the step is `skills/unit-lane/references/DOCS.md`. Adapt the list to what the project has; skip checks for absent structures and say so. ## Process 1. Discover, then run the checks with `grep`, file reads, and the forge CLI (per Workflow conventions; examples use `gh`). 2. Produce the findings report — **return exactly** (fixed output contract): ``` AUDIT DOCS — scope: <docs tree / roadmap / fix index / issues checked> | # | Check (1-15) | Finding | Sev | Evidence | Proposed fix | |---|-------------|---------|-----|----------|--------------| | 1 | <which> | <what> | high|low | <path:line / #issue> | <smallest action> | Checks run: <n>/15 (skipped: <which + why — absent structures only>) Summary: <1-2 sentences> Decision: PASS | FAIL (FAIL if any high-severity finding is open) ``` Sev: **high** = misleading or broken; **low** = cosmetic. Only `high` and `low` are defined in this legend 3. **Fix only on request.** With explicit `--fix` (or user go-ahead), apply the low-risk corrections (remove a merged fix-index row, fix a dead link, register a missing roadmap entry, add a verified PR link to a bare `done` row). Leave judgment calls to the user. ## Guardrails - Read-first; never bulk-rewrite docs unprompted. - Distinguish genuine drift from intentionally "scheduled/deferred" items — don't report deliberate tradeoffs as errors. - Keep changes surgical and within docs; no code or behavior changes. ## Portability (agents other than Claude Code) The workflow is the contract; Claude Code features are conveniences. On an agent that lacks one, apply the fallback — never skip the step the feature enables: - **No slash-command menu** — where this skill says `/<skill>`, open that skill's `SKILL.md` (wherever your agent installed the skills) and follow it literally, in a fresh conversation: hand-offs assume a clean context. - **No per-skill `model:`/`effort:`** — no skill pins a tier; pick tiers yourself: these are mostly mechanical cross-document checks — a mid-tier model is enough; escalate to your strongest only for a deep audit. ## Relationship to other skills - Complements `unit-lane` (which *creates* the docs this audits) and `triage-issue` (which keeps the fix index honest). - Run standalone anytime; no required predecessor. ## Done when - A severity-ranked findings report exists, and any approved low-risk fixes are applied — with genuine deferrals left untouched and labeled as such. - **The closing `→ Next:` block is printed:** ``` → Next: apply the approved low-risk fixes, then re-run /audit-docs to confirm clean · real drift (not cosmetic) → /triage-issue · a concrete defect → /unit-lane --fix <n> · already clean → nothing to do ```
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.