agentleFS
sasuketoriisasuketorii/rev_harness_public/.agents/skills/rev-harness-lifecycle/SKILL.md

rev-harness-lifecycle

Skill0 starsChanged 3 months agoApache-2.0View on GitHub

rev_harness lifecycle: install/verify/repair/status/upgrade/uninstall; triggers: revharness入れて, doctor, repair, status, upgrade inspect. NOT: tmp掃除, packaging, session開始.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 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.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify: run the health check when the operator asks whether it works.

    line 13
  2. Very specific:

    Do NOT use this skill for .claude/tmp cleanup.

    line 30
  3. Very specific:

    Do NOT use this skill for client packaging or distribution readiness.

    line 31
  4. Very specific:

    Do NOT use this skill for session start or orchestrator wake-up.

    line 32
  5. Very specific:

    Use the facade subcommands exactly: install, verify, repair, status, upgrade inspect, or uninstall.

    line 40
  6. Distinctive:

    Keep destructive paths dry-run/checklist first unless the user gives a separate explicit apply instruction.

    line 41

≈ “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

Rev Harness Lifecycle

When to use

  • Install: set up RevHarness in a project with the canonical facade.
  • Verify: run the health check when the operator asks whether it works.
  • Repair: run the repair path after a broken or partial install.
  • Status: inspect current adoption phase and doctor state.
  • Upgrade inspect: review upgrade state without applying mutation.
  • Uninstall checklist: print the removal checklist; require explicit user intent for destructive apply.

Trigger phrases

User phraseCommand
revharness 入れて, 初回セットアップ, enable rev_harnessrev-harness install
doctor 回して, 動いてる?, verify rev_harnessrev-harness verify
壊れた、直して, repair rev_harnessrev-harness repair
状態, statusrev-harness status
アップグレード見て, upgrade inspectrev-harness upgrade inspect
アンインストール手順, uninstall checklistrev-harness uninstall

What NOT to do

  • Do NOT use this skill for .claude/tmp cleanup; use development-junk-cleanup.
  • Do NOT use this skill for client packaging or distribution readiness; use client-distribution-readiness.
  • Do NOT use this skill for session start or orchestrator wake-up; use orchestrator-bootstrap.

Invocation

bash scripts/rev-harness <subcommand> [options]

Use the facade subcommands exactly: install, verify, repair, status, upgrade inspect, or uninstall. Keep destructive paths dry-run/checklist first unless the user gives a separate explicit apply instruction.

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.