agentleFS
Diviner-DojoDiviner-Dojo/agent_framework_template/.claude/skills/syncing-framework-docs/SKILL.md

syncing-framework-docs

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Checklist for keeping downstream docs (FRAMEWORK_SPECIFICATION, presentation HTMLs) in sync when framework-defining files change. Use when editing .claude/agents, .claude/rules, .claude/commands, CLAUDE.md, PHILOSOPHY.md, or the project version — and during /review and /ship of framework changes.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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. Distinctive:

    When the trigger fires, review and update these three artifacts:

    line 23
  2. Very specific:

    During /review: When reviewing framework changes, verify that affected sync points have been updated.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Framework Documentation Sync

Ensures downstream documentation artifacts stay in sync when the framework evolves. Prevents the recurring problem of framework version bumps leaving specs and presentations stale.

Trigger

This rule activates when any change touches framework-defining files:

  • .claude/agents/ — agent definitions (count, roles, model tiers)
  • .claude/rules/ — auto-loaded standards (count, new rules)
  • .claude/commands/ — slash commands (count, new commands)
  • CLAUDE.md — project constitution
  • PHILOSOPHY.md — framework philosophy
  • pyproject.toml — project version

Documentation Artifacts to Sync

When the trigger fires, review and update these three artifacts:

ArtifactPathPurpose
Framework Specificationdocs/FRAMEWORK_SPECIFICATION.mdAuthoritative full specification
Framework Presentationdocs/diviner-dojo-framework-presentation.htmlPresentation deck for stakeholders
How-to-Use Presentationdocs/how-to-use-presentation.htmlDeveloper onboarding walkthrough

Sync Points

This table maps framework elements to the specific locations in each artifact that reference them. When an element changes, check every listed location.

Framework ElementSpecificationPresentation HTMLHow-to-Use HTML
Version numberFrontmatter version, title, executive summary, footer<title>, version badge, footerFooter
Agent countSection 5 heading, roster table, implementation statusSlide 5 heading, directory treeStats card
Agent model tiersRoster table, model-tier table, directory listingSlide 5 agent cards (badge + tier class)—
Leadership hierarchySection 5 leadership subsectionSlide 5 heading and agent cards—
Rule countImplementation status, directory listingDirectory tree slide—
Command countSection 6, implementation status—Stats card, cheat sheet
Collaboration modesSection 4Slide 6—
Hook countSection 7, implementation statusSlide 8—
PrinciplesSection 2Slide 3—

Enforcement

  • During /review: When reviewing framework changes, verify that affected sync points have been updated. Flag stale documentation as an advisory finding.
  • During /ship: The ship workflow checks for FRAMEWORK-type changes and verifies documentation sync before release.
  • Steward gate: The Steward evaluates framework evolution proposals. Documentation sync is part of the completeness check.

What This Rule Does NOT Cover

  • Content accuracy of the documentation (that's the author's responsibility)
  • CLAUDE.md updates (covered by the documenting-decisions skill)
  • ADR creation for architectural changes (covered by the selecting-review-gates skill)

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.