agentleFS
hushh-labshushh-labs/hushh-research/.agents/skills/docs-governance/SKILL.md

docs-governance

Skill40 starsChanged 4 days agoApache-2.0View on GitHub

Use when reorganizing docs, deciding documentation homes, consolidating redundant docs, updating diagrams or doc maps, or changing documentation verification policy in this repo.

8 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use writing-for-agents and domain-modeling.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    writing-for-agents

    Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

    Also in 3 projects that use this

  • GoogleSkill

    domain-modeling

    Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Avoid overlap with repo-context, frontend, backend, and repo-operations.

    line 12
  2. Distinctive:

    Use the authoring contract for policy.

    line 13
  3. Distinctive:

    Verify substantive claims against current source.

    line 60
  4. Distinctive:

    Run affected checks, keep audit evidence ignored, and release through repo-operations.

    line 71

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Documentation governance

Purpose and Trigger

  • Primary scope: docs-governance-intake
  • Trigger on documentation structure, canonical homes, consolidation and verification.
  • Avoid overlap with repo-context, frontend, backend, and repo-operations. Use the authoring contract for policy; use this skill to execute the change.

Coverage and Ownership

  • Role: owner
  • Owner family: docs-governance

Owned repo surfaces:

  1. docs
  2. consent-protocol/docs
  3. hushh-webapp/docs

Non-owned surfaces:

  1. frontend
  2. backend
  3. repo-operations
  4. contributor-onboarding

Do Use

  1. Moving, consolidating or retiring documentation and repairing its consumers.
  2. Reconciling source truth, module diagrams and current versus future claims.
  3. Updating documentation navigation and its existing verification tools.

Do Not Use

  1. Product implementation merely because documentation accompanies it.
  2. Release-policy or deployment changes owned by repo-operations.
  3. Broad orientation before the owning surface is known; begin with repo-context.

Read First

  1. docs/README.md
  2. docs/development/documentation.md
  3. docs/architecture/README.md
  4. docs/operations/brand-and-compatibility-contract.md

Workflow

  1. Inventory first-party Markdown and inspect runtime, generator and package consumers.
  2. Classify current guides, technical contracts, future designs, active peer work, history, and imported/generated/legal/runtime assets before changing them.
  3. Choose the canonical Product, Architecture, Development, Operations or Roadmap home. Keep standalone package references local and root entrypoints useful.
  4. Verify substantive claims against current source. One is the implemented root private agent; Kai is its finance specialist. Do not turn source evidence into deployment or installed-owner acceptance. Current chat Markdown remains in PKM.
  5. Lead with purpose and behavior. Retain exact commands and identifiers where readers need them for implementation, custody, recovery or provenance.
  6. Reconcile unique durable facts before retirement. Preserve active peer work and unresolved recovery facts. Use Git history for prior versions, not duplicate trees.
  7. Move links, anchors, images, manifests, inventories and generators together. Required package assets and runtime Markdown retain their existing contracts.
  8. Review navigation and source truth independently for cross-system migrations. Render changed diagrams and verify both valid and broken-link behavior.
  9. Run affected checks, keep audit evidence ignored, and release through repo-operations. Source-only downstream syncs preserve branch content and never deploy.

Handoff Rules

Route implementation to frontend/backend owners, release operations to repo-operations, and explicitly requested executive artifacts to founder-brief-curation. Ordinary product documentation has no default Founder/CTO audience. Preserve literal compatibility identifiers and the approved Hussh personal-agent identity.

Required Checks

./bin/hushh docs verify
python3 .agents/skills/docs-governance/scripts/doc_inventory.py inventory
python3 .agents/skills/docs-governance/scripts/doc_inventory.py stale-candidates
python3 .agents/skills/docs-governance/scripts/doc_inventory.py folders

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.