agentleFS
Sign inStart free
kiku-jwkiku-jw/codex-skills/justdoit/SKILL.md

justdoit

Skill0 starsChanged 4 months agoMITView on GitHub

Default execution-planning skill for almost any non-trivial repo task. Turn a raw task, feature request, PRD, or project brief into durable plan, status, and test-plan files, then hand back a concise ready-to-execute proposal.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not use when: the request is a trivial one-shot edit, pure discussion, or a factual answer with no execution surface.

    line 10
  2. Distinctive:

    Every meaningful milestone has copy-pasteable validation commands and explicit done criteria.

    line 23

≈ “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

justdoit

Metadata

  • Trigger when: the work is non-trivial enough to benefit from durable execution docs before or during implementation.
  • Do not use when: the request is a trivial one-shot edit, pure discussion, or a factual answer with no execution surface.

Skill Purpose

Turn messy task input into a durable execution pack that another Codex run can resume from without reconstructing scope, sequencing, or validation from chat.

Instructions

  1. Determine the target files first. Prefer existing repo conventions; otherwise default to docs/plans.md, docs/status.md, and docs/test-plan.md. Normalize scope, constraints, risks, validation commands, and assumptions before drafting.
  2. Build or update the plan, status, and test-plan files using the repo truth plus ~/.codex/skills/justdoit/references/plan-template.md, ~/.codex/skills/justdoit/references/status-template.md, and ~/.codex/skills/justdoit/references/test-plan-template.md when you need the baseline structure. Keep milestones dependency-ordered and validation-first.
  3. Finish with a short execution proposal that points to the written files, names what starts first, how validation will run, and what would stop the run. If the user only asked for planning, stop and wait for confirmation unless they already explicitly asked to execute immediately. If another skill is needed after planning, name it explicitly with a one-line reason.

Non-Negotiable Acceptance Criteria

  • The plan is the source of truth; status and test-plan must line up with it.
  • Every meaningful milestone has copy-pasteable validation commands and explicit done criteria.
  • Assumptions are explicit instead of buried in prose.
  • The skill does not paste huge file contents into chat unless the user explicitly asks for inspection.

Output

  • A short product-level summary.
  • The plan, status, and test-plan file paths.
  • A compact Ready to execute handoff plus either a confirmation question or a clear note that execution is already starting.
  • Next skill options (only if needed): $agx-orchestrator — dispatch bounded execution through AGX; $parallel-worktrees — split substantial work into isolated lanes; $continuity-ledger — preserve cross-session state when the run will be long; $adversarial-review — run a skeptical second pass after implementation.

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