agentleFS
Sign inStart free
rpraharajrpraharaj/ai-sdlc/skills/plan-rollback/SKILL.md

plan-rollback

Skill0 starsChanged 16 days agoMITView on GitHub

Write a rollback plan that starts with one spoken sentence plus steps. Use when the user asks for a rollback plan, backout, or /plan-rollback. Do not invent environments. Do not perform the rollback.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not perform the rollback.

    line 18
  2. Distinctive:

    If there is no named artifact to undo, stop.

    line 33
  3. Distinctive:

    Read AGENTS.md if present.

    line 42

≈ “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

Plan rollback

Make rollback something a human can say and do. This is not cut-release and not incident-triage.

Do not perform the rollback. Do not invent environments.

Is this the right skill?

SignalDo this instead
Cut the releasecut-release after this exists
Incident in progressincident-triage then this if rollback is the mitigate
Diagnose stepswrite-runbook

Required inputs

  • What would be rolled back (tag, flag, migration slice)
  • context/environments.md and context/decision-rights.md

If there is no named artifact to undo, stop.

Human decisions (do not invent)

  • Who may run production rollback
  • Data rollback vs forward-fix when contract already contracted (default: say if data rollback is impossible)

Procedure

  1. Read AGENTS.md if present. Read environments and decision-rights.
  2. Find the home: docs/ops/rollback-<slug>.md.
  3. Open references/rollback-template.md. Copy every heading. Write n/a when unused.
  4. First line of the plan is one spoken sentence (“revert tag X”, “turn flag off”, “redeploy previous image”).
  5. Steps use commands this repo already has, or unknown.
  6. Agents do not run production steps.

Output

  • Path: docs/ops/rollback-<slug>.md
  • Template: references/rollback-template.md

Quality bar

  • One spoken sentence exists
  • Environment names come from context or unknown
  • No unattended prod by an agent
  • Unused headings are n/a

Done

  1. Path
  2. Spoken sentence
  3. Next skill: human go/no-go then cut-release; or incident 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