agentleFS
monaccodemonaccode/astromesh-sdd/skills/sdd-tasks/SKILL.md

sdd-tasks

Skill0 starsChanged 29 days agoApache-2.0View on GitHub

Use when plan.md is approved and tasks.md does not exist yet, or the plan changed. Breaks the plan into small, ordered, independently verifiable tasks, each citing its requirements and naming the exact check that proves it done.

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Before anything else, read these if they exist.

    line 13
  2. Very specific:

    Write every artifact in language.

    line 24
  3. Very specific:

    Read plan.md and spec.md. Then:

    line 29
  4. Very specific:

    Write tasks.md from the template.

    line 39
  5. Distinctive:

    Add new tasks with the next free number.

    line 59
  6. Very specific:

    If tasks is in gates: show the user the artifact path and a 3–5 line summary, list any [NEEDS CLARIFICATION] items, and stop.

    line 64

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “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

SDD — Tasks

tasks.md is the checklist implementation follows. A good task is the smallest unit that can be reviewed on its own and has a check that proves it done.

Step 0 — Load project settings

Before anything else, read these if they exist. Missing files are normal; use the defaults.

  1. .sdd/config.yaml in the project, else ~/.sdd/config.yaml. Defaults: specs_dir: specs, language: en, ids: {requirement: REQ, task: T}, gates: [specify, plan, tasks], verify_command: "", phases: [constitution, specify, plan, tasks, implement, verify].
  2. Template: .sdd/templates/tasks.md, else ~/.sdd/templates/tasks.md, else templates/tasks.md next to this file.
  3. Extra rules: .sdd/rules/all.md and .sdd/rules/tasks.md (project, then global). They add to this skill; when they conflict with it, they win.

Write every artifact in language. Use the configured ID prefixes everywhere this skill says REQ or T.

Step 1 — Cut the plan into tasks

Read plan.md and spec.md. Then:

  • One task = one reviewable unit. Fold setup, configuration and docs into the task whose deliverable needs them instead of making them tasks of their own.
  • Tests live in the same task as the code they test, and are written first.
  • Order tasks so each one builds on finished ones. Mark tasks that can run in parallel (no shared files, no dependency) with [P].

Step 2 — Write tasks.md

Write tasks.md from the template. Each task is:

- [ ] T-n — <imperative title> (REQ-a, REQ-b)
  - files: `<path>`, `<path>`
  - check: `<runnable command>` → <expected result>
  - depends: T-m | —

check is a command whose output proves the task done (a test, a build, a curl). Only when no command can prove it, write a manual step with its observable outcome ("open /settings, the toggle is visible"). "Code compiles" is not a check for a feature.

Step 3 — Coverage

Fill the Coverage table: every non-removed requirement and the tasks that cite it. Every requirement appears at least once; every task cites at least one requirement.

When the plan changes

Add new tasks with the next free number; IDs are not reused. Do not untick finished tasks unless their check no longer passes.

Gate

If tasks is in gates: show the user the artifact path and a 3–5 line summary, list any [NEEDS CLARIFICATION] items, and stop. Do not start the next phase until the user approves. When they approve, set the artifact's status line to **Status:** approved · **Date:** YYYY-MM-DD and save the file — approval has to live in the file, so a later session or another agent can see it. If tasks is not in gates, set the status to approved yourself, say which phase runs next and continue.

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.