modeled-information-formatmodeled-information-format/mif-docs-plugin/skills/ears-acceptance-criteria/SKILL.mdears-acceptance-criteria
Skill1 starsChanged 35 days agoMITView on GitHub
Turn a requirement, decision driver, or finding into an EARS-notation acceptance criterion that a human and an agent grade identically. Use when authoring acceptance criteria for a PRD, feature spec, architecture doc, ADR decision driver, or Kiro requirements document.
In this repository46 other files it gives its agents.
- academicSkill
- adrSkill
- ai-architecture-docSkill
- arc42-arch-docSkill
- audit-docsSkill
- briefingSkill
- business-planSkill
- c4-model-diagramSkill
- changelogSkill
- clinical-submissionSkill
- competitive-quadrantSkill
- compliance-auditSkill
- computing-paperSkill
- diataxis-explanationSkill
- diataxis-how-toSkill
- diataxis-referenceSkill
- diataxis-tutorialSkill
- doc-set-plannerSkill
- engineeringSkill
- exec-summarySkill
- feature-specSkill
- google-design-docSkill
- humanities-chicagoSkill
- humanities-mlaSkill
- kiro-designSkill
- kiro-requirementsSkill
- kiro-tasksSkill
- legal-memoSkill
- market-research-reportSkill
- mif-corpusSkill
- mif-frontmatterSkill
- mif-provenanceSkill
- mif-to-pdfSkill
- mif-validateSkill
- nist-spSkill
- playbookSkill
- prdSkill
- python-pepSkill
- regulatory-disclosureSkill
- rust-rfcSkill
- security-pentestSkill
- sre-runbookSkill
- sustainability-reportSkill
- svg-chartsSkill
- systematic-reviewSkill
- trend-analysisSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 32
Prefer the most specific template that fits.
≈ “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.
Files
ears-acceptance-criteria
Shared helper (not a standalone document genre). It encodes requirements in
EARS (Easy Approach to Requirements Syntax) so acceptance criteria are
machine-readable and unambiguous. Invoked by prd, feature-spec,
ai-architecture-doc, kiro-requirements, and the adr decision drivers.
The five EARS templates
| Pattern | Template | Use for |
| Ubiquitous | The <system> shall <response>. | always-true invariants |
| Event-driven | When <trigger>, the <system> shall <response>. | a stimulus causes a response |
| State-driven | While <state>, the <system> shall <response>. | behavior during a state |
| Unwanted | If <condition>, then the <system> shall <response>. | error / edge handling |
| Optional | Where <feature>, the <system> shall <response>. | feature-conditional behavior |
Rules
- One criterion = one testable sentence. No conjunctions hiding two requirements.
<system>is a concrete named component, not "the app". If the input doesn't name one, commit to a specific, plausible component name (e.g.the payment gateway,the auth service) rather than deferring the choice to the reader, and flag it as an assumption.<response>is observable and verifiable (a state change, an output, a code).- Prefer the most specific template that fits; do not default everything to Ubiquitous.
Example
When a request exceeds 600 requests/minute per API key, the gateway shall reject it with HTTP 429 and a
Retry-Afterheader.
(Event-driven: trigger = rate exceeded; system = gateway; response = 429 + header.)
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.