agentleFS
Sign inStart free
JetXu-LLMJetXu-LLM/DocMason/skills/canonical/adapter-sync/SKILL.md

adapter-sync

Skill152 starsChanged 4 months agoApache-2.0View on GitHub

Generate or refresh the local Claude adapter surface for DocMason from canonical committed sources.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 5 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the task is to generate or refresh the currently supported adapter artifacts.

    line 8
  2. Distinctive:

    If the agent cannot write local generated files, stop and explain that adapter synchronization cannot proceed.

    line 20
  3. Very specific:

    Treat AGENTS.md, canonical SKILL.md files, and canonical workflow.json sidecars as the authored source of truth.

    line 24
  4. Very specific:

    Use claude as the default target unless the user explicitly asks for another target.

    line 25
  5. Very specific:

    Run docmason status --json when you need to confirm whether the generated adapter is missing or stale.

    line 26
  6. Distinctive:

    If adapter sync fails because canonical sources or workflow metadata are missing or invalid, stop and return that failure to the main agent …

    line 28
  7. Very specific:

    If adapter sync succeeds, run docmason status --json when you need to confirm the adapter is now fresh.

    line 29
  8. Distinctive:

    If the requested target is not implemented, stop and report the current deferral clearly.

    line 34
  9. Very specific:

    If the generated adapter is stale after canonical source changes, rerun sync-adapters instead of hand-editing generated files.

    line 35
  10. Distinctive:

    Use this workflow when the chosen agent ecosystem actually depends on generated adapter files, not as a reflex before every workflow.

    line 48

≈ “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

Adapter Sync

Use this skill when the task is to generate or refresh the currently supported adapter artifacts.

This is an explicit adapter-maintenance workflow. It is not a universal prerequisite before every ordinary ask turn. For non-native compatibility targets such as Claude Code, this is the first adaptation step once workspace bootstrap has determined that generated adapter guidance is needed.

Required Capabilities

  • local file access
  • shell or command execution
  • ability to regenerate derived files instead of editing them manually

If the agent cannot write local generated files, stop and explain that adapter synchronization cannot proceed.

Procedure

  1. Treat AGENTS.md, canonical SKILL.md files, and canonical workflow.json sidecars as the authored source of truth.
  2. Use claude as the default target unless the user explicitly asks for another target.
  3. Run docmason status --json when you need to confirm whether the generated adapter is missing or stale.
  4. Run docmason sync-adapters --json.
  5. If adapter sync fails because canonical sources or workflow metadata are missing or invalid, stop and return that failure to the main agent instead of improvising a manual adapter.
  6. If adapter sync succeeds, run docmason status --json when you need to confirm the adapter is now fresh.
  7. Return the final adapter status judgment to the main agent. Do not delegate adapter regeneration sign-off.

Escalation Rules

  • If the requested target is not implemented, stop and report the current deferral clearly.
  • If the generated adapter is stale after canonical source changes, rerun sync-adapters instead of hand-editing generated files.

Completion Signal

  • The workflow is complete when docmason sync-adapters --json succeeds or returns a clear unsupported-target or metadata-validation failure that the main agent can surface directly.

Notes

  • DocMason currently supports the Claude target only.
  • Generated adapters are local derived artifacts and should not be hand-maintained.
  • The committed .claude/CLAUDE.md is the sole Claude project-memory entry file in this repo.
  • Adapter sync refreshes the generated adapters/claude/project-memory.md and adapters/claude/workflow-routing.md files that .claude/CLAUDE.md can import.
  • Adapter sync also refreshes the repo-local .claude/skills/ thin shim layer instead of relying on a hand-created symlink to the full repo skills tree.
  • Use this workflow when the chosen agent ecosystem actually depends on generated adapter files, not as a reflex before every workflow.

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.

Check your setup, free