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.
In this repository22 other files it gives its agents.
- ground-specSkill
- initiative-feasibilitySkill
- learning-extractSkill
- loop-specSkill
- pre-implementSkill
- purge-initiative-artifacts-appSkill
- spec-draftSkill
- spec-implementation-planSkill
- spec-technical-reviewSkill
- ensure-repo-graphSkill
- post-product-questionsSkill
- prd-codebase-mapSkill
- review-product-questionsSkill
- create-board-ticketsSkill
- open-draft-prSkill
- prd-impact-mapSkill
- prd-qualitySkill
- prd-thinkSkill
- purge-initiative-artifacts-metaSkill
- review-findingsSkill
- update-documentsSkill
- validate-requirementsSkill
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
- Very specific: line 18
Read pinned workflow.yaml for the content stage that just completed (forge.commit_workspace).
- Very specific: line 22
If policy is disabled, stop and explain.
- Very specific: line 23
If policy is required and there is nothing includable to publish, fail closed.
- Very specific: line 25
If policy is optional and the tree is clean, report success with no-op.
- Very specific: line 26
Never apply approval labels (*-lgtm).
- Very specific: line 27
Use available Forge tooling in this environment (git remote APIs, gh, …) as examples — tool-neutral.
- Very specific: line 52
When handoff_path is bound, overwrite that baton with the same envelope.
≈ “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.
Files
Commit workspace
Human-walker equivalent of Gateflow ForgeClient commit workspace
(forge.action / pin field: commit_workspace).
NON-NEGOTIABLE
- Read pinned
workflow.yamlfor the content stage that just completed (forge.commit_workspace). Do not invent policy. - Bind the remote head from run / human context (wave PR, meta PR, spec
branch) — not from a pin
headenum. - If policy is
disabled, stop and explain; do not publish. - If policy is
requiredand there is nothing includable to publish, fail closed. - If policy is
optionaland the tree is clean, report success with no-op. - Never apply approval labels (
*-lgtm). - Use available Forge tooling in this environment (git remote APIs,
gh, …) as examples — tool-neutral. Do not assume a specific CLI exists.
Inputs
- Latest content-skill
handoff:(artifact and/orhandoff_pathbaton) - Pinned root
workflow.yaml - Workspace root with includable changes
Process
- Resolve prior stage +
commit_workspacepolicy from the pin. - Determine includable paths (respect
.gitignore/ harness norms). - Publish to the bound head when policy allows.
- Report the result and emit
handoff:for this forge step using references/output-template.md —artifact.pathisnull(this skill has no workspace artifact, including the justified no-op case); do not invent a note file to hold the result.
Workflow handoff
- Emit the envelope from references/output-template.md
in chat. Stage id:
commit-workspace. Preferoutcome: passwhen publish or justified no-op succeeded.artifact.path: null— there is no workspace file to persist for this stage. - When
handoff_pathis bound, overwrite that baton with the same envelope. - Forge skills are not workflow graph nodes — do not invent
next_candidatesfrom a missing pin node. If continuing the programme, re-read the content stage handoff and pinned transitions.
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
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.

