agentleFS
developerz-aideveloperz-ai/gold-standards-in-ai/.claude/skills/plan-slices/SKILL.md

plan-slices

Skill2 starsChanged yesterdayMITView on GitHub

Plan a doc set with /planx into path-disjoint slices. Use for planx, doc plan, status.yml, plan dir, slices.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 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.

  • 3

    Very specific

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

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

    Write overview.md plus one <NN>-<aspect>.md per doc or cluster — never one big plan.md.

    line 9
  2. Very specific:

    Write status.yml in the plan dir: plan, title, status (not_started | in_progress | blocked | complete | superseded), created_by, worked_by, …

    line 10
  3. Very specific:

    No worktrees in the plan: never a git worktree step, never isolation: worktree — a docs repo is the one-checkout row of worktrees: when.

    line 12

≈ “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

House skill — owned by this repository's maintainers, and written from this repository's own evidence. Correct it in place; setup never overwrites a skill that exists.

  1. Resolve the plan path: date +%Y, date +%m, date +%d -> docs/plans/<YYYY>/<MM>/<DD>/; next number = highest 1NN-* + 1, else 101; slug = kebab-case, max 5 words.
  2. Explore read-only over docs/<section>/: which section owns the topic, what already covers it (file:line), new file vs revision vs delete, which READMEs need a row. fail -> stop: a duplicate needs a revision, not an addition.
  3. Write overview.md plus one <NN>-<aspect>.md per doc or cluster — never one big plan.md.
  4. Write status.yml in the plan dir: plan, title, status (not_started | in_progress | blocked | complete | superseded), created_by, worked_by, owner, percent, current_focus, slices, evidence, notes, last_updated.
  5. Plan only — write nothing outside the plan dir; the executor needs nothing but the plan and the files it cites.
  6. No worktrees in the plan: never a git worktree step, never isolation: worktree — a docs repo is the one-checkout row of worktrees: when. Parallel slices = one doc per slice, disjoint paths; README index rows are edited last, by one agent.

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.