Skip to content
Agentmart
Submit a tool

implement

Use when a bounded implementation task has settled requirements, declared ownership, and a credible behavior seam.

Skill by Rafcin

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/rafcin-implement

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

Use when a bounded implementation task has settled requirements, declared ownership, and a credible behavior seam.

Use cases: productivity, agent-building

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

What's inside

Skill name
implement
Description
Use when a bounded implementation task has settled requirements, declared ownership, and a credible behavior seam.
License
MIT
Instructions
21 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Implement

Execute the declared route through small, evidence-producing vertical slices.

## Entry conditions

Confirm the accepted requirement or plan, owned paths, public seam, working-tree boundary, and required verification. For delegated work, accept only a packet with objective, ownership, interfaces, exclusions, and evidence expectations.

## Scope limit

Write only owned files. Preserve concurrent changes, do not add speculative behavior, and do not make a reviewer repair its own finding. Use `tdd` for behavior changes; stop at a material decision or an ownership conflict instead of guessing.

## Exit evidence

Report changed paths, the behavior exercised, red and green evidence where applicable, focused commands and outcomes, remaining gaps, and any out-of-scope observation. The parent verifies from the diff and fresh commands rather than this report alone.

## Next gate

Run `ai-slop-cleaner` when the route requires it or concrete generated noise appears, then `verification`; a declared review route ends with fresh `code-review`.

From Rafcin/oh-my-codex-slim, MIT.

More from Rafcin/oh-my-codex-slim

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 26, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from Rafcin

Cite this page

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