acceptance-criteria
Skill0 starsChanged 34 days agoMITView on GitHub
Write acceptance criteria and test scenarios for a user story or requirement in Given/When/Then (Gherkin), including edge cases, error paths and non-functional checks, so that a developer and a tester agree on "done" before work starts. Use when the user asks for acceptance criteria, test cases, test scenarios, Gherkin, BDD, definition of done, or QA handoff for a story.
18 other projects use a version of this.
Adopted by
Most recently taken up by
- jjdmev2/dme-skillstheir own version, first seen Nov 16, 2026
- roronoazoroshao369/vibe-coding-ostheir own version, first seen Nov 15, 2026
- Fili999/ai-hubtheir own version, first seen Nov 15, 2026
- celestialdust/achilles-skillstheir own version, first seen Nov 1, 2026
- MiguelSavignano/claude-code-systemtheir own version, first seen Nov 1, 2026
- Happy-Technologies-LLC/happy-platform-skillstheir own version, first seen Nov 1, 2026
Other versions18 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 18
- Happy-Technologies-LLC/happy-platform-skills★ 41same name
- jdm4pku/RE-Skills★ 26same name
- MiguelSavignano/claude-code-system★ 7same name
- Sunnyshinnny776/pm-agentic-cookbook★ 4same name
- HamzaSheikh768/Agents-Skills-Lap★ 3same name
- jjdmev2/dme-skills★ 3same name
- designedbythanh/ai-skills-library-product-design★ 2same name
- Fili999/ai-hub★ 2same name
- garthcodes/claude-skills★ 2same name
- celestialdust/achilles-skills★ 1same name
8 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- prioritizeSkill
- review-specSkill
- slice-storiesSkill
- stakeholder-updateSkill
- write-prdSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
1
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
- Very specific: line 29
Start from pm-skills template acceptance-criteria.
- Very specific: line 33
Use concrete example data (a cart of 3 items totalling 1,250 TL), not placeholders.
- Distinctive: line 34
Use the domain's words, not UI implementation details, unless the detail is the requirement.
- Very specific: line 35
If the team writes in Turkish, Turkish Gherkin keywords are fine: Senaryo, Diyelim ki, Eğer ki, O zaman, Ve.
- Very specific: line 39
Run pm-skills lint <file> --type criteria.
“Common” is measured: kept by at least 6 in 10 of the 14 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.
Files
Write acceptance criteria
Acceptance criteria are the contract for "done". Each one must be checkable by someone who did not write it, without asking the author what they meant.
CLI: node "${CLAUDE_PLUGIN_ROOT}/cli/pm-skills.mjs" (or ../../cli/pm-skills.mjs relative to this file). Below, pm-skills.
1. Understand the story
Read the story and its parent PRD if there is one. Identify the actor, the trigger, the expected outcome and the business rules involved. If a rule is ambiguous (what happens at exactly the limit? who sees what?), list it as a question rather than picking an answer silently.
2. Find the scenarios
Work through these, in order, and keep the ones that apply:
- Happy path: the main thing working.
- Business rules: one scenario per rule, including the exact boundary (
at 100,at 101). - Alternative paths: other valid ways to get the outcome.
- Errors and empty states: invalid input, missing data, no results, timeouts, the other system being down.
- Permissions: who must not be able to do this.
- Non-functional, only where they matter for this story: performance budget, accessibility, localisation, analytics events, audit trail.
3. Write them
Start from pm-skills template acceptance-criteria. Rules:
- One behaviour per scenario. One
Whenper scenario. Givensets up state, not actions.Thendescribes something observable: what the user sees, what is stored, which event is sent. Never "the system works correctly".- Use concrete example data (
a cart of 3 items totalling 1,250 TL), not placeholders. Use a Scenario Outline with an Examples table when only the data changes. - Use the domain's words, not UI implementation details, unless the detail is the requirement.
- If the team writes in Turkish, Turkish Gherkin keywords are fine:
Senaryo,Diyelim ki,Eğer ki,O zaman,Ve.
4. Check
Run pm-skills lint <file> --type criteria. Every scenario must have Given, When and Then; criteria using "should" without anything measurable are flagged; vague words are flagged.
Return the scenarios plus a short list of the questions you could not resolve, each with who should answer it.
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
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.

