agentleFS
drivestream-labdrivestream-lab/prayog-skills/skills/forge/commit-workspace/SKILL.md

commit-workspace

Skill2 starsChanged 4 months agoMITView on GitHub

Publish includable workspace changes to the remote head for this run (human walker Forge tooling). Use after a content skill when pin forge.commit_workspace is optional or required. Orchestrators use ForgeClient instead — do not auto-invoke this skill.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 0 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

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

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

    Read pinned workflow.yaml for the content stage that just completed (forge.commit_workspace).

    line 18
  2. Very specific:

    If policy is disabled, stop and explain.

    line 22
  3. Very specific:

    If policy is required and there is nothing includable to publish, fail closed.

    line 23
  4. Very specific:

    If policy is optional and the tree is clean, report success with no-op.

    line 25
  5. Very specific:

    Never apply approval labels (*-lgtm).

    line 26
  6. Very specific:

    Use available Forge tooling in this environment (git remote APIs, gh, …) as examples — tool-neutral.

    line 27
  7. Very specific:

    When handoff_path is bound, overwrite that baton with the same envelope.

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Commit workspace

Human-walker equivalent of Gateflow ForgeClient commit workspace (forge.action / pin field: commit_workspace).

NON-NEGOTIABLE

  1. Read pinned workflow.yaml for the content stage that just completed (forge.commit_workspace). Do not invent policy.
  2. Bind the remote head from run / human context (wave PR, meta PR, spec branch) — not from a pin head enum.
  3. If policy is disabled, stop and explain; do not publish.
  4. If policy is required and there is nothing includable to publish, fail closed.
  5. If policy is optional and the tree is clean, report success with no-op.
  6. Never apply approval labels (*-lgtm).
  7. Use available Forge tooling in this environment (git remote APIs, gh, …) as examples — tool-neutral. Do not assume a specific CLI exists.

Inputs

  1. Latest content-skill handoff: (artifact and/or handoff_path baton)
  2. Pinned root workflow.yaml
  3. Workspace root with includable changes

Process

  1. Resolve prior stage + commit_workspace policy from the pin.
  2. Determine includable paths (respect .gitignore / harness norms).
  3. Publish to the bound head when policy allows.
  4. Report the result and emit handoff: for this forge step using references/output-template.md — artifact.path is null (this skill has no workspace artifact, including the justified no-op case); do not invent a note file to hold the result.

Workflow handoff

  1. Emit the envelope from references/output-template.md in chat. Stage id: commit-workspace. Prefer outcome: pass when publish or justified no-op succeeded. artifact.path: null — there is no workspace file to persist for this stage.
  2. When handoff_path is bound, overwrite that baton with the same envelope.
  3. Forge skills are not workflow graph nodes — do not invent next_candidates from a missing pin node. If continuing the programme, re-read the content stage handoff and pinned transitions.

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.