Catalog
Yeachan-Heo/agent-doc-discipline

Yeachan-Heo

agent-doc-discipline

Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and carrying a why, steps before reference, one meaning in one home, no restating what the environment already says. Mandatory at drydock seed generation and the launch C5 sediment pass; opt-in for any other agent-facing doc edit. The companion of minimal-code-discipline: that one disciplines code, this one disciplines papers.

v1.0LATEST
NewUpdated Sep 22, 2026

Agent Doc Discipline

Use this skill to apply a writing-time discipline while creating or editing any document an agent consumes to act: the five surfaces (CLAUDE.md, CONTEXT.md, docs/standards/, design-system/, .omc/skills/), specs, tickets, and skill files. The test a document must pass: a fresh agent session can act on it by reading alone.

Mandatory when: drydock generates surface seeds, the launch C5 sediment pass writes a lesson into a slot. Opt-in for every other edit — but any edit to an agent-facing document should survive these rules.

When Not to Use

Documents written for humans only: docs/business/ narrative, ADR decision stories, READMEs for human onboarding. They may still follow the rules where it costs nothing, but they are not held to this discipline.

The Discipline

Write for a reader with no chat history. The document is self-describing: nothing leans on "as discussed", a prior session, or knowledge that lives in someone's head. Test: a brand-new agent session can act on the document by reading alone.

Every rule checkable and carrying a why. No "keep it clean" — write the observable condition and the reason. Test: an agent can decide pass/fail from the text alone, and the why is stated next to the rule.

One meaning, one home. Each rule or definition has a single authoritative place; duplication is drift waiting to happen. Test: changing a behavior is a one-place edit.

Never restate what the environment confesses. Package scripts, directory layouts, --help output are lookups, not documents — a copied lookup goes stale. Document only what cannot be found by looking: the unwritten convention, the reason behind a choice, the gotcha. Test: every line survives "can this be looked up elsewhere?".

Steps first, reference behind, rare material behind a pointer. What to do, in order, at the top; consult-on-demand rules below; low-frequency material pushed behind a pointer whose wording names the branches that should trigger reaching it. Test: the next action is findable within the first screen.

Every step ends on a completion criterion. Done must be tellable from not-done — a vague bound invites premature completion. Test: for each step, "how do I know this is finished?" has an answer in the text.

A procedure longer than two steps is numbered. The numbers are stable references: a reader can name step 3, follow the order, and jump without re-reading. An unnumbered procedure of many steps makes the reader hold the order in their head. Test: every procedure of three or more steps carries its numbers.

A list is capped at what a reader holds in one glance. A list that outgrows the reader's grasp loses its point — nothing in it is findable. A longer enumeration becomes structure (a table, subsections) or splits. This governs the writing of documents; it never touches the machinery of a gate or a batched decision, which lives in the methodology, not the prose. Test: every list in the document fits in one glance, and any longer enumeration has become structure.

Deferred and scheduled work states when. A document that defers work to a later step, session, or release states that timing next to the work it defers — "when" is a fact the reader needs to act, and an unstated deferral reads as an unstarted one. The timing is stated in the prose only; it never rebinds a checkpoint the methodology pushes right deliberately. Test: every deferral in the document carries its when.

Close on a next action a reader can start now. A report, ticket, or session-close pointer ends not with a summary but with the one next step a reader can begin in under two minutes — the destination, the pointer, or the command. A close that only summarizes makes the reader re-derive what to do first. Test: the last line answers "what do I do next?" without scrolling up.

Re-state the position each time the reader rejoins. A document a returning reader touches mid-flight (a long spec, a run report, a map Notes section) opens the new material with where things stand — step, phase, or decision count — before adding anything new. Test: a reader arriving cold can locate the current state in the first two lines of the newest section.

Prompt the positive. State the target behavior; a prohibition is reserved for hard guardrails and is always paired with the positive target. Test: every prohibition in the document names the thing to do instead.

Scrape barnacles on write. When the document contains stale or redundant material, remove it in the same edit; when it does not, add only the required material and do not invent deletions. A sentence the model already obeys by default pays load for nothing — delete the whole sentence. Test: every line re-read earns its place against "does this change behavior versus the default?", and any stale or redundant material found during the edit is gone.

Verification

Before reporting a document change done, confirm:

  • a fresh session could act on it without asking a human anything
  • every rule is checkable and states its why; no rule restates a lookup
  • meanings live in one place; pointers name their trigger branches
  • stale or redundant material found during the edit was removed, while valid unrelated content was preserved
  • closes end on a next action the reader can start now; rejoining readers find the current state stated before new material
  • procedures of three or more steps are numbered; lists fit in one glance; every deferral states its when
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

87/100

Grade

A

Excellent

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

95

Quality

85

Clarity

88

Completeness

82

Summary

This skill provides a comprehensive set of writing discipline rules for documents that AI agents consume and act upon. It emphasizes self-contained documentation, checkable rules with stated rationales, eliminating redundancy, and clear action sequences. The skill is intended to ensure agent-facing documents are readable and actionable without external context or prior session history.

Detected Capabilities

document analysiswriting guidanceediting verificationspecification review

Trigger Keywords

Phrases that agents use to match this skill to user intent.

document disciplineagent-facing specsskill file reviewspec clarityrule verificationdoc redundancywriting standardsagent readability

Use Cases

  • Write surface documentation (CLAUDE.md, CONTEXT.md) that agents can act on independently
  • Author agent-facing specs and tickets with clear, checkable rules
  • Create or edit .omc/skills/ files following disciplined writing standards
  • Ensure skill documentation survives drydock seed generation and sediment passes
  • Validate documents for completeness before agent consumption
  • Review design system and standards documentation for redundancy and clarity

Quality Notes

  • Excellent structural discipline: the skill enforces its own rules in its own text—rules are numbered (12 core rules), lists are sized appropriately, every rule carries observable verification criteria
  • Clear scope boundaries: explicitly defines what documents are in scope (agent-facing surfaces, specs, tickets, skills) and what are out of scope (human-only docs like business narratives and READMEs)
  • Each rule is checkable and carries its 'why': every discipline point includes a test condition and rationale, enabling agents to verify compliance without interpretation
  • Strong pedagogical design: opens with mandatory vs. opt-in contexts, defines the anti-pattern (restatement of environment state), and closes with a verification checklist
  • The skill models the discipline it teaches—no barnacles, pointers name their trigger branches, next actions are explicit
  • Potential for improvement: the skill does not include worked examples of compliant vs. non-compliant documents, which would strengthen clarity for edge cases like list sizing and deferral timing
Model: claude-haiku-4-5-20251001Analyzed: Sep 22, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Use Yeachan-Heo/agent-doc-discipline in your dev environment

Command Palette

Search for a command to run...