agentleFS
prabhakar349prabhakar349/claude-ddd-redesign/skills/acceptance-criteria/SKILL.md

acceptance-criteria

Skill1 starsChanged 3 months agoMITView on GitHub

Defines the content and structure of a Slice's Acceptance Criteria. Reference when assembling or reviewing slices/<id>/acceptance-criteria.json.

16 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

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 0

    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. Very specific:

    If a criterion's exact boundary is still under discussion, write it as precisely as currently possible and flag the open question in the …

    line 28

“Common” is measured: kept by at least 6 in 10 of the 12 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

Acceptance Criteria

Defines what an Acceptance Criterion record contains. In v1 (characterization oracle), acceptance criteria restate what the characterization suite must prove; under a future specification oracle (seam S1.1) they would instead carry the scope directly.

Schema

schemas/acceptance-criteria.schema.json. One JSON object per criterion; slices/<id>/acceptance-criteria.json is a JSON array of these.

Required fields

id (AC-NNNN), slice (SLC-NNNN), statement (≥10 characters — a real assertion, not a restated Behavior summary), behaviors.

Content obligations

Every Slice needs at least one Acceptance Criterion, and every criterion should cite the Behavior(s) it proves — in v1 behaviors[] should be non-empty for every criterion, since there is no other oracle yet to carry the scope. Set failure_path: true for criteria specifically about failure, timeout, or partial-completion behavior, and make sure such criteria actually exist — a Slice whose acceptance criteria are all happy-path is under-specified before a single test is written.

Behavior-ID citation

behaviors[] is the citation. A criterion with an empty behaviors[] under oracle_strategy: "characterization" has nothing anchoring it to observed system behavior — it is closer to a wish than a criterion.

Unknowns

If a criterion's exact boundary is still under discussion, write it as precisely as currently possible and flag the open question in the accompanying PRD — do not leave the statement vague to avoid committing.

Minimal worked example

{
  "id": "AC-0009",
  "slice": "SLC-0004",
  "statement": "An order placement request with quantity <= 0 is rejected with the same error code and message the legacy system returns",
  "behaviors": ["BHV-0042"],
  "failure_path": true
}

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.