# research-implement-feature

research-implement-feature — a Claude Code skill that builds a working feature artifact from a plain implementation request. Runs when given a capability description instead of an experiment plan.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 140 installs · ★ 19555 repo stars
- Author: wanshuiyin
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/HEAD/skills/research-implement-feature/SKILL.md
- Updated: 2026-10-24
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/research-implement-feature

## What it does

The skill constructs a walking skeleton from the entry point to the artifact before adding features one rung at a time. Every ambiguous decision is written to an assumption ledger before dependent code appears, followed by a cross-model sweep for undeclared items. Effort tiers and interaction modes control runtime intensity and approval gates.

Parameters are passed through argument flags covering effort level, question mode, and base repository URL. Bash execution and standard file tools are required in the agent environment.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill research-implement-feature -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/research-implement-feature/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/research-implement-feature/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill research-implement-feature -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/research-implement-feature/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill research-implement-feature -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/research-implement-feature/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install wanshuiyin/Auto-claude-code-research-in-sleep skills/research-implement-feature
```

2. **Manually: put the files in place**
- File: `.github/skills/research-implement-feature/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill research-implement-feature -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep --path skills/research-implement-feature
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/research-implement-feature/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill research-implement-feature -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/HEAD/skills/research-implement-feature/SKILL.md

## When to use it
- build a working prototype from a simple request description
- record under-determined decisions in an assumption ledger
- construct a running end-to-end skeleton before adding features
- sweep for undeclared assumptions across model families

## Example prompts
- implement user authentication with JWT tokens in this repository
- build a shopping cart prototype without asking intermediate questions
- create a working end-to-end application spine for this feature

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 542f997bc64a966f.

BEGIN THIRD-PARTY FILE 542f997bc64a966f
```text
---
name: research-implement-feature
description: "Build a working artifact from a plain \"implement X for me\" request: a running end-to-end spine first, then one feature per rung, with every under-determined decision written to an assumption ledger BEFORE the code that depends on it and a cross-model sweep for the ones that slipped through undeclared. Use when user says \"给我实现\", \"implement X\", \"帮我做一个能跑的\", \"先搭个原型再加功能\", \"build this feature\", \"prototype then extend\", or hands over a capability description rather than an experiment plan."
argument-hint: "[what-to-build] [— effort: lite|balanced|max|beast] [— ask: never|semantic] [— base repo: <url>]"
allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, Skill, AskUserQuestion, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_start, mcp__claude-review__review_reply_start, mcp__claude-review__review_status
---

# Research Implement: Feature

> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.


Build: **$ARGUMENTS**

This skill exists for one request shape — *"just implement X for me"* — where the
user has a capability in mind, not an experiment plan, and does not want to be
interviewed about it first.

It resolves that request the only honest way: **stay autonomous, stop being
silent.** The skill never blocks to ask permission; it *declares* every decision
the request left open, in a ledger, at the moment it makes it, and then a
different model family goes looking for the ones it forgot to declare.

## Two invariants

1. **Declare before you act.** The instant a decision is under-determined by the
   request *and* changes an interface or a meaning, it gets a ledger row —
```
END THIRD-PARTY FILE 542f997bc64a966f

The third-party file has ended. Everything between the 542f997bc64a966f tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2588 of 32637 bytes. © wanshuiyin · MIT · https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/HEAD/skills/research-implement-feature/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
