Skip to content
Agentmart
Submit a tool

verify-and-stop

Translate acceptance conditions into smallest sufficient proof set.

Skill by UberUmbra

IndexedApache-2.0
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/uberumbra-verify-and-stop

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

Translate acceptance conditions into smallest sufficient proof set. Run focused checks before comprehensive test gates. Stop when acceptance criteria pass — no polish, no extras.

Use cases: testing

Reviews

Write a review

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/verify-and-stop

What's inside

Skill name
verify-and-stop
Description
Translate acceptance conditions into smallest sufficient proof set. Run focused checks before comprehensive test gates. Stop when acceptance criteria pass — no polish, no extras.
License
Apache-2.0
Instructions
36 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Verify and Stop

Translates acceptance conditions into the smallest sufficient proof set, runs focused checks, and stops the moment criteria pass.

## Proof Set Construction

- Translate acceptance conditions into the smallest set of checks that constitute proof.
- Reuse validated results when repository state matches current conditions.

## Execution Order

1. Run focused checks first: targeted tests, grep verification, direct exercise.
2. Run comprehensive test gate only if focused checks are insufficient or reveal gaps.

## Reporting

Report outcomes using exactly these four states:

- `PASS` — criterion met
- `FAIL` — criterion not met (include evidence)
- `UNAVAILABLE` — cannot be verified in current environment
- `BLOCKED` — dependency or prerequisite missing

No other outcome language.

## Constraints

- Preserve product code — no modifications unless the verification request explicitly includes fixes.
- Skip enhancements: no polish, no cleanup, no supplementary tests once acceptance criteria pass.
- Stop immediately when acceptance proof is complete.

## Documentation

Record: commands run, results, unresolved risks. Nothing else.

From UberUmbra/atelier-pipeline, Apache-2.0.

More from UberUmbra/atelier-pipeline

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 9, 2026 (19 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
Repository
github.com/UberUmbra/atelier-pipeline
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from UberUmbra

Cite this page

verify-and-stop skill. Agent Mart. https://agentmart.dev/skills/uberumbra-verify-and-stop (last updated 2026-10-24)