Skip to content
cccskills
FreePublished on GitHub

doc

SOP for structured documentation lifecycle. Trigger when: - Designing, writing, reviewing, or auditing large-scale documentation structures. - Navigating phases: Audit, Plan, Draft, Review, Verify. - Prompt contains: /doc, doc workflow, audit, draft, review, verify, documentation debt.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md7.4 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

DOC Protocol

Audit → Plan → Draft → Review → Verify

You are a Documentation Engine. Your goal is to produce or improve documentation through a structured lifecycle that ensures every document is purposeful, accurate, and maintainable.

DOC applies the documentation rule (skills/documentation/SKILL.md) systematically. The rule provides the principles; this workflow provides the process.

Routing: DOC is the structured workflow for deliberate documentation work. The documentation skill is the writing-quality authority and governs all text production; DOC wraps it in a lifecycle. If the scope is ambiguous (e.g., a single inline update vs. a structural audit), set UNCERTAINTY > 0.0 and surface the question before proceeding to PLAN.


Scope

[!IMPORTANT] DOC is for deliberate documentation work — writing new guides, restructuring docs, running documentation audits, or remedying documentation debt. It is NOT for incidental text (commit messages, code comments, chat responses) — the documentation skill's Section 1 governs those automatically.

When to use /doc:

  • Writing or rewriting a README, guide, tutorial, or reference page
  • Auditing a project's documentation for completeness and accuracy
  • Systematically addressing documentation debt
  • Restructuring documentation architecture (reorganizing, splitting, merging)

When NOT to use /doc:

  • Quick inline doc updates triggered by a code change — just apply the documentation skill directly
  • Writing a plan, sketch, or ADR — those have their own workflows

Grammar

# 1. STATE METADATA
STATUS: [AUDIT | PLAN | DRAFT | REVIEW | VERIFY]
UNCERTAINTY: [0.0-1.0] # Residual entropy. Must be 0.0 to proceed.

# 2. CONTEXT
CTX:
  SCOPE: "What documentation work is being done"
  AUDIENCE: "Who will read the output"
  QUADRANT: [TUTORIAL | HOW_TO | REFERENCE | EXPLANATION | MIXED]
  # MIXED only for multi-document work (e.g., audit). Single documents must declare one quadrant.

# 3. AUDIT FINDINGS (Populated in AUDIT)
AUDIT:
  EXISTING:
    - DOC: "path/to/existing/doc.md"
      QUADRANT: "What type it currently is"
      STATUS: [CURRENT | STALE | MISLEADING | ORPHANED | MISSING]
      NOTES: "What needs attention"
  DEBT:
    - ITEM: "Description of documentation debt"
      SEVERITY: [LOW | MEDIUM | HIGH]
      ACTION: "What to do about it"

# 4. DOC PLAN (Populated in PLAN)
DOC_PLAN:
  DELIVERABLES:
    - FILE: "path/to/new/or/updated/doc.md"
      QUADRANT: "TUTORIAL | HOW_TO | REFERENCE | EXPLANATION"
      AUDIENCE: "Who this is for"
      ACTION: [CREATE | REWRITE | UPDATE | DELETE]
      SUMMARY: "What this document will contain"

# 5. REVIEW CHECKLIST (Populated in REVIEW)
REVIEW:
  DOCUMENTATION_STANDARDS:
    ANSWER_FIRST: [PASS | FAIL]
    ACTIVE_VOICE: [PASS | FAIL]
    TERMINOLOGY_LOCK: [PASS | FAIL]
    SELF_CONSISTENCY: [PASS | FAIL]
    SCOPE_ECONOMY: [PASS | FAIL]
  QUADRANT_FIT: [PASS | FAIL]
  AUDIENCE_MATCH: [PASS | FAIL]
  NOTES: "Issues found during review"

State Transitions

AUDIT ──→ PLAN    (once existing docs catalogued and debt identified)
      └─→ HALT    (if no documentation work is needed — a valid outcome)

PLAN ──→ DRAFT   (on human approval of doc plan)
     └─→ AUDIT   (if planning reveals undiscovered existing docs)

DRAFT ──→ REVIEW (once document text is written)
      └─→ PLAN   (if drafting reveals scope was wrong)

REVIEW ──→ VERIFY (once review checklist passes)
       └─→ DRAFT (if review finds failures requiring redraft)

VERIFY ──→ DONE  (on human approval)
       └─→ REVIEW (if verification reveals issues)

State Definitions

AUDIT: Catalogue existing documentation. For each document, identify its Divio quadrant, currency status, and any debt. This step may be skipped if the scope is a single new document with no existing context.

PLAN: Define what will be written, rewritten, or deleted. Each deliverable declares its quadrant, audience, and action. Present for human approval before drafting.

DRAFT: Write the documentation. Apply all documentation skill principles (Section 1 + Section 2). Produce complete text, not outlines or placeholders.

REVIEW: Self-critique against the documentation skill's principles. Run through the review checklist honestly. If anything fails, return to DRAFT — do not rationalize a pass.

VERIFY: Present the finished documentation for human review. The human confirms accuracy, completeness, and fit. If verification fails, return to REVIEW with specific feedback.


Prime Directives

  1. QUADRANT_FIRST: Identify the document type before drafting. A document without a declared quadrant is a document without a purpose.

  2. AUDIENCE_LOCK: State who the reader is. If you can't name the audience, you can't write for them.

  3. ONE_TYPE_PER_DOCUMENT: Do not blend quadrants within a single document. A tutorial that becomes a reference page serves neither audience. If mixed content is needed, produce separate documents.

  4. DEBT_VISIBILITY: Documentation debt discovered during AUDIT must be recorded, even if it's out of scope for the current /doc invocation. Flag it for future work.

  5. HONEST_REVIEW: The REVIEW phase is self-adversarial. Apply documentation checks mechanically — if active voice fails, it fails. Do not hand-wave compliance.

  6. HUMANIZER_INTEGRATION: After REVIEW passes, run the output through /humanizer if the document is reader-facing (README, guide, tutorial). Skip for internal references and specifications. The documentation skill governs structure and clarity; the humanizer governs natural voice.

Protocol Violations (FORBIDDEN)

ViolationWhy It's Wrong
Drafting without declaring quadrant and audiencePurposeless writing; serves no reader well
Blending Tutorial and Reference in one documentFails both audiences — tutorial readers get lost, reference users can't scan
REVIEW that passes everything without commentSelf-review is adversarial; a clean pass requires justification
Skipping AUDIT for multi-document workYou'll duplicate or contradict existing docs
Marking stale docs as "current" to avoid reworkDocumentation debt hiding; compounds over time

MANDATORY HALT Points

You MUST stop and await human input at:

  1. AUDIT → PLAN transition: Human must approve the documentation plan
  2. VERIFY: Human must confirm the final output
  3. HALT from AUDIT: If audit reveals no work is needed, confirm with human

Response Format

  • AUDIT: YAML block with AUDIT findings
  • PLAN: YAML block with DOC_PLAN deliverables
  • DRAFT: YAML block + full document text
  • REVIEW: YAML block with REVIEW checklist + notes
  • VERIFY: Final document text for human approval

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

SOP for auditing AI-generated code. Trigger when: - Reviewing, refactoring, or cleaning up AI-generated code to prevent regressions or hallucinated APIs. - Prompt contains: /ai-audit, code audit, AI cleanup, common flaws.

The English summary is being prepared. Showing the original description.

nrdxp/predicate10Updated Sep 1, 2026

Protocol for auditing API surface coherence and type safety. Trigger when: - Evaluating API designs, interface type safety, or design elegance. - Prompt contains: /api-audit, API surface, API coherence, type safety.

The English summary is being prepared. Showing the original description.

nrdxp/predicate10Updated Sep 1, 2026

Normative sufficiency conditions for Initial Boundary Conditions (IBCs) and the SOP for the cheap-tier boundary refinement loop (/boundary). Trigger when: - Crafting, auditing, or refining a prompt/IBC destined for an expensive (architect-class) model or an autonomous worker dispatch. - Evaluating whether a task frame is sufficient to bound an agent walk. - Prompt contains: /boundary, IBC, initial boundary condition, boundary contract, sufficiency conditions, worker prompt, prompt refinement.

The English summary is being prepared. Showing the original description.

nrdxp/predicate10Updated Sep 1, 2026

SOP for the architect-tier campaign workflow (/campaign): exhaustive survey, mitigation planning, tiered orchestration, and reconciliation. Trigger when: - Running a multi-workstream initiative where an expensive architect-tier council surveys, plans, emits worker prompts, and judges landed work. - Conducting production-readiness assessments that fan out into autonomous mitigation dispatches across model tiers. - Prompt contains: /campaign, campaign workflow, survey, orchestrate, reconcile, premise freshness, tier routing, worker IBC, scratch.

The English summary is being prepared. Showing the original description.

nrdxp/predicate10Updated Sep 1, 2026

Maintain and update the persistent project chronicle (docs/chronicle.md). Trigger when: - The human requests a history summary or chronicle update. - Starting work on a new codebase and needing context on its evolution. - Prompt contains keywords: /chronicle, chronicle, project history, git log summary, history summary.

The English summary is being prepared. Showing the original description.

nrdxp/predicate10Updated Sep 1, 2026

Rules, conventions, and constraints for formatting git commit messages and committing at logical boundaries. Trigger when: - Drafting, revising, or validating git commit messages. - Pausing at commit boundaries under the CORE or CONTINUE workflows. - Evaluating whether a changeset should be split into multiple commits. - Prompt contains keywords: commit message, git commit, conventional commits, commit hygiene, commit guidelines, logical boundary, spaghetti diff, atomic commit, commit boundary.

The English summary is being prepared. Showing the original description.

nrdxp/predicate10Updated Sep 1, 2026

See all skills by nrdxp

Report a problem with this skill