Skip to content
Agentmart
Submit a tool

acceptance-criteria

Turn a bounded user story, feature rule, or delivery requirement into explicit testable acceptance scenarios covering happy paths, edge cases, errors, state…

Skill by ThorStarlord

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/thorstarlord-acceptance-criteria

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Turn a bounded user story, feature rule, or delivery requirement into explicit testable acceptance scenarios covering happy paths, edge cases, errors, state transitions, integration effects, accessibility, performance, and other relevant constraints. Use for delivery_specification responsibility when detailed behavioral criteria are needed. Produce criteria_list; do not invent product rules or claim scenarios have passed.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/acceptance-criteria

What's inside

Skill name
acceptance-criteria
Description
Turn a bounded user story, feature rule, or delivery requirement into explicit testable acceptance scenarios covering happy paths, edge cases, errors, state transitions, integration effects, accessibility, performance, and other relevant constraints. Use for delivery_specification responsibility when detailed behavioral criteria are needed. Produce criteria_list; do not invent product rules or claim scenarios have passed.
License
MIT
Instructions
31 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • methodology.md · references/
  • output-contract.md · references/

SKILL.md (first lines)

# Acceptance criteria

Satisfy a `delivery_specification` responsibility by producing `criteria_list`.

## Inputs

Require one or more bounded stories/features plus known business rules and constraints. Prefer `story_list` and the source `prd` when available.

## Procedure

1. Read [references/methodology.md](references/methodology.md).
2. Identify the observable behavior actually required by the source story/feature.
3. Write scenario-oriented criteria using Given/When/Then where it improves precision.
4. Cover the happy path, relevant valid variations, error behavior, and consequential boundary conditions.
5. Add performance, accessibility, scale, persistence, security, or integration criteria only when the source requirement or domain evidence warrants them.
6. Trace each scenario to its source story/requirement.
7. Separate known requirements from open design/product questions. Do not resolve ambiguity by inventing rules.
8. Do not mark scenarios as passed, automated, QA-approved, or signed off without execution evidence.
9. Render [references/output-contract.md](references/output-contract.md) and return control.

## Stop or downgrade

- If the source story is not bounded enough to determine expected behavior, preserve the ambiguity as an unresolved question.
- If a criterion would introduce new product scope, identify it as proposed rather than silently incorporating it.
- If verification requires external systems or performance measurements not available now, specify the criterion but do not claim it passed.

## Boundary

`acceptance criterion != test result`, `scenario coverage != implementation`, and `specified quality threshold != measured performance`.

From ThorStarlord/sensemaking-skills, MIT.

More from ThorStarlord/sensemaking-skills

Signals

Stars
0
Forks
0
Open issues
7
Last commit (this folder)
Sep 10, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ThorStarlord

Cite this page

acceptance-criteria skill. Agent Mart. https://agentmart.dev/skills/thorstarlord-acceptance-criteria (last updated 2026-10-24)