agentleFS
20030419zhanghongyi20030419zhanghongyi/AI-Software-Engineering-Workflow-Template/.agents/skills/plan-from-issue/SKILL.md

plan-from-issue

Skill0 starsChanged 6 months agoMITView on GitHub

Create a Plan Artifact before implementation starts.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Read the files above.

    line 38
  2. Distinctive:

    Check that the task is in Implementation Gate.

    line 39
  3. Distinctive:

    Test plan is missing

    line 52
  4. Distinctive:

    Do not automatically commit, push, merge, release, tag, or force-push unless the user explicitly approves that exact action.

    line 59

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 From Issue

Purpose

Generate a Plan Artifact for Implementation Gate.

When to use

  • A coding task is ready for planning
  • Allowed files and tests need to be defined
  • Implementation must wait for approval

Required files to read

  • AGENTS.md
  • AI_WORKFLOW.md
  • docs/11_stage_gates.md
  • docs/13_human_gate_and_rollback.md
  • .ai/artifacts/PLAN_ARTIFACT_TEMPLATE.md

Inputs

  • Current issue or task
  • Relevant files
  • Current constraints

Outputs

  • Plan Artifact

Steps

  1. Read the files above.
  2. Check that the task is in Implementation Gate.
  3. Define allowed files, forbidden files, test plan, and rollback plan.
  4. Generate the Plan Artifact.
  5. Require Human Owner approval before implementation and stop.

Human review

Human Owner must approve the plan, especially scope, tests, and rollback.

Stop conditions

  • Information is insufficient
  • File boundary is unclear
  • Test plan is missing
  • Rollback plan is missing
  • User has not approved the plan
  • There is any automatic commit / push / merge / release risk

Codex safety rule

Do not automatically commit, push, merge, release, tag, or force-push unless the user explicitly approves that exact action.

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.