agentleFS
tonmoy007tonmoy007/forge-plugins/skills/forge-deploy/SKILL.md

forge-deploy

Skill2 starsChanged 5 months agoMITView on GitHub

Run Stage 8 of the Forge pipeline — deployment. Use when the user says

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 2 are distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

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

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

    If it exits non-zero, STOP: present its message verbatim and do not proceed — the prior stage must be completed first (or use …

    line 26
  2. Very specific:

    Read pipeline/state.md — confirm Forge project.

    line 30
  3. Distinctive:

    If eval-report is missing or shows failures: "Stage 7 evaluation must pass before deploying."

    line 32
  4. Very specific:

    Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/check-gate.py --stage 7 to check gate status.

    line 33
  5. Very specific:

    Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/load-profile.py --cwd .

    line 34
  6. Very specific:

    Read agents/devops.md to load the DevOps persona.

    line 43
  7. Very specific:

    Read pipeline/03-architecture/architecture.md for topology and pipeline/04-spec/technical-spec.md for config needs.

    line 45
  8. Distinctive:

    Follow the DevOps workflow: pre-deployment checklist, ordered steps, health checks, rollback plan.

    line 46
  9. Very specific:

    Write pipeline/08-deploy/deploy-plan.md and pipeline/08-deploy/runbook.md — or pipeline/08-deploy/package-spec.md when replace_with: …

    line 47
  10. Very specific:

    Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py advance --to 8 after successful deploy/publish.

    line 50

≈ “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

/forge:deploy — Deployment

When to Use

  • User says /forge:deploy
  • User wants to deploy to staging or production, write a deployment plan, or create a runbook
  • Working in a Forge project at Stage 7 or 8

Pre-flight Check

Entry gate (REQ-GATE-ENTRY-001) — before adopting the persona, verify the prior stage's artifact exists:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py preflight --stage 8

If it exits non-zero, STOP: present its message verbatim and do not proceed — the prior stage must be completed first (or use /forge:force-advance to skip intentionally).

  1. Read pipeline/state.md — confirm Forge project.
  2. Confirm pipeline/07-evaluation/eval-report.md exists and shows overall pass. If eval-report is missing or shows failures: "Stage 7 evaluation must pass before deploying."
  3. Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/check-gate.py --stage 7 to check gate status.
  4. Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/load-profile.py --cwd . --stage 8 to load project-type overrides. If the profile sets skip: true (CLI, library) the conventional service-deploy is replaced by package-publish — produce a package-spec artifact instead of a deployment runbook.
  5. Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/check_docker_readiness.py --cwd . unconditionally — every project gets this, regardless of profile (it self-no-ops with no Docker artifacts). This is advisory only: it exits 0 even with findings, and any WARN: lines it prints must be relayed to the user as advisory notes — it never blocks and does not gate this stage.

Steps

  1. Read agents/devops.md to load the DevOps persona.
  2. Adopt that persona — you are now the DevOps Engineer.
  3. Read pipeline/03-architecture/architecture.md for topology and pipeline/04-spec/technical-spec.md for config needs.
  4. Follow the DevOps workflow: pre-deployment checklist, ordered steps, health checks, rollback plan. If the profile specifies replace_with: package-publish, follow that flow instead (build artifacts, registry credentials, version verification, publish, post-publish smoke).
  5. Write pipeline/08-deploy/deploy-plan.md and pipeline/08-deploy/runbook.md — or pipeline/08-deploy/package-spec.md when replace_with: package-publish.
  6. Execute deployment (or publish) steps (with user confirmation for destructive operations), recording what happened in pipeline/08-deploy/deploy-log.md.
  7. Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py advance --to 8 after successful deploy/publish.

Verification

After running, confirm:

  • pipeline/08-deploy/deploy-plan.md exists with rollback procedure
  • pipeline/08-deploy/deploy-log.md records the deployment outcome
  • pipeline/08-deploy/runbook.md exists
  • Health checks pass post-deployment
  • pipeline/state.md shows current_stage: 8

Next Step

Derive the hint from the canonical stage table — never hardcode it (REQ-NEXTHINT-001, single source of truth). Run the helper and present its output to the user verbatim:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py next-hint --stage 8

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.