agentleFS
HyunKNHyunKN/harness-kit/skills/spec-writing/SKILL.md

spec-writing

Skill0 starsChanged 7 months agoMITView on GitHub

Use when a feature, refactor, or workflow change is still underspecified and a short written spec should exist before issue creation or implementation. Trigger when goals, boundaries, users, or success criteria are still unclear. Do not use only because work spans multiple files; use `planning-workflow` or `issue-driven-workflow` once the problem is already clear enough to execute.

17 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

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write a short working spec before coding when the request is still loose.

    line 8
  2. Distinctive:

    Write success criteria that can be validated later.

    line 16
  3. Very specific:

    Prefer docs/product/ for the spec and link it from the issue doc before implementation starts.

    line 21
  4. Distinctive:

    Stop once the work is clear enough to create an issue and a plan.

    line 22
  5. Distinctive:

    follow-up tasks that already have a clear issue doc and plan

    line 35

“Common” is measured: kept by at least 6 in 10 of the 15 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

Spec Writing

Write a short working spec before coding when the request is still loose.

This skill is for problem framing, not task tracking.

Default flow

  1. State the problem, affected user or team, and desired outcome.
  2. Surface assumptions and unanswered questions early.
  3. Write success criteria that can be validated later.
  4. Record boundaries:
    • in scope
    • out of scope
    • decisions that still need approval
  5. Prefer docs/product/ for the spec and link it from the issue doc before implementation starts.
  6. Stop once the work is clear enough to create an issue and a plan.

Good fit

  • new features with unclear shape
  • refactors with behavior constraints
  • architecture or workflow changes
  • requests that would otherwise rely on chat memory

Avoid for

  • typo fixes
  • obvious one-line changes
  • follow-up tasks that already have a clear issue doc and plan

Resources

  • See references/spec-checklist.md for a lean spec checklist.
  • Hand off to planning-workflow after the scope is stable and to issue-driven-workflow once execution should be tracked.

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.