Skip to content
Agentmart
Submit a tool

implement-scenario

Implement one planned scenario until its system test passes, then mark it implemented.

Skill by sesigl

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/sesigl-implement-scenario

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

Implement one planned scenario until its system test passes, then mark it implemented. Use when a scenario and its failing system test exist.

Use cases: testing

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/implement-scenario

What's inside

Skill name
implement-scenario
Description
Implement one planned scenario until its system test passes, then mark it implemented. Use when a scenario and its failing system test exist.
License
Apache-2.0
Instructions
25 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Implement a scenario

## Steps

1. Confirm the scenario is `@status=planned` and its system test fails for the right reason.
2. Read the module's `AGENTS.md` and `README.md`. Read only the source files you need.
3. Implement the smallest change that makes the test pass. Keep ports and adapters separate: domain logic must
   not import an adapter.
4. Run the one test: `make test-scenario ID=SCN-PROOF-004`. Repeat until it passes.
5. Set `@status=implemented` on the scenario.
6. Run `make check`. Fix every failure in this module. Never weaken a check to make it pass; fix the cause.
7. Update the docs: `skills/keep-docs-evergreen`.
8. Run `make verify` and put the summary into the pull request.

## Rules

- One scenario per pull request when possible; at most one module per pull request.
- Do not add behavior that no scenario asks for. If you need it, stop and write a `planned` scenario first.
- Do not add a unit test unless the module's `AGENTS.md` allows it for this code.
- If the test can only pass by changing the scenario, replace the scenario (`skills/write-scenario`) and say why
  in the pull request.
- If a check fails outside the module you changed, stop and report it. Do not fix it in the same pull request.
- Retro at the end: write what did not work the first time into the pull request under "Friction".

From sesigl/open-software-factory, Apache-2.0.

Signals

Stars
0
Forks
0
Open issues
2
Last commit (this folder)
Oct 19, 2026 (10 days ago)
Last release
Oct 24, 2026 (5 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from sesigl

Cite this page

implement-scenario skill. Agent Mart. https://agentmart.dev/skills/sesigl-implement-scenario (last updated 2026-10-24)