impl — for Claude Code simple, community, for Claude Code, ide skills, gemini-cli-extension, research, coding, skill — must show STATUS: PASS - If, VCS sync, pass_todo

v1.0.0

关于此技能

适用场景: Ideal for AI agents that need impl — codex self-sufficient 15-phase workflow. 本地化技能摘要: # Impl — Codex Self-Sufficient 15-Phase Workflow Cooperative Phase: Implementation (any step — self-sufficient) Self-sufficient. It covers gemini-cli-extension workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

功能特性

Impl — Codex Self-Sufficient 15-Phase Workflow
Cooperative Phase: Implementation (any step — self-sufficient)
Self-sufficient. If research, requirements, or design missing, does them first (phases 1-5).
Simple MCP — query codebase structure, module graph
Simple LSP MCP — symbol lookup, type checking, go-to-definition

# 核心主题

ormastes ormastes
[0]
[0]
更新于: 4/19/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
49
Canonical Locale
en
Detected Body Locale
en

适用场景: Ideal for AI agents that need impl — codex self-sufficient 15-phase workflow. 本地化技能摘要: # Impl — Codex Self-Sufficient 15-Phase Workflow Cooperative Phase: Implementation (any step — self-sufficient) Self-sufficient. It covers gemini-cli-extension workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

核心价值

推荐说明: impl helps agents impl — codex self-sufficient 15-phase workflow. Impl — Codex Self-Sufficient 15-Phase Workflow Cooperative Phase: Implementation (any step — self-sufficient) Self-sufficient. This AI agent skill

适用 Agent 类型

适用场景: Ideal for AI agents that need impl — codex self-sufficient 15-phase workflow.

赋予的主要能力 · impl

适用任务: Applying Impl — Codex Self-Sufficient 15-Phase Workflow
适用任务: Applying Cooperative Phase: Implementation (any step — self-sufficient)
适用任务: Applying Self-sufficient. If research, requirements, or design missing, does them first (phases 1-5)

! 使用限制与门槛

  • 限制说明: Built-in matchers only (see design skill for list)
  • 限制说明: Refactor: files 800 lines must be split
  • 限制说明: Run verify skill — must show STATUS: PASS

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作,再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”,而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核,以及是否已经进入工作流落地阶段。

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致,便于搜索引擎理解页面内容。

? FAQ

impl 是什么?

适用场景: Ideal for AI agents that need impl — codex self-sufficient 15-phase workflow. 本地化技能摘要: # Impl — Codex Self-Sufficient 15-Phase Workflow Cooperative Phase: Implementation (any step — self-sufficient) Self-sufficient. It covers gemini-cli-extension workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

如何安装 impl?

运行命令:npx killer-skills add ormastes/simple/impl。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

impl 适用于哪些场景?

典型场景包括:适用任务: Applying Impl — Codex Self-Sufficient 15-Phase Workflow、适用任务: Applying Cooperative Phase: Implementation (any step — self-sufficient)、适用任务: Applying Self-sufficient. If research, requirements, or design missing, does them first (phases 1-5)。

impl 支持哪些 IDE 或 Agent?

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

impl 有哪些限制?

限制说明: Built-in matchers only (see design skill for list);限制说明: Refactor: files 800 lines must be split;限制说明: Run verify skill — must show STATUS: PASS。

安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行:npx killer-skills add ormastes/simple/impl。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    impl 已启用,可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考,但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论,再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

impl

安装 impl,这是一款面向AI agent workflows and automation的 AI Agent Skill。查看评审结论、使用场景与安装路径。

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Impl — Codex Self-Sufficient 15-Phase Workflow

Cooperative Phase: Implementation (any step — self-sufficient) Self-sufficient. If research, requirements, or design missing, does them first (phases 1-5).

Tools

  • Simple MCP — query codebase structure, module graph
  • Simple LSP MCP — symbol lookup, type checking, go-to-definition
  • Context7 MCP — external library documentation

Prerequisites Check

ArtifactPathIf exists, skip to
Researchdoc/01_research/local/<feature>.mdPhase 4
Requirementsdoc/02_requirements/feature/<feature>.mdPhase 4
Architecturedoc/04_architecture/<feature>.mdPhase 6
Designdoc/05_design/<feature>.mdPhase 6
System testsdoc/06_spec/.../<feature>_spec.splPhase 8

If ALL exist, skip to Phase 8 (Implementation).

Phases

Phases 1-3: Research + Requirements

Skip if exist, otherwise do inline. See research skill for details.

Phases 4-5: Plan + Design + Architecture

Skip if exist. See design skill for details.

Phases 6-7: System Test + Doc Consistency

  • Write SSpec BDD tests from design
  • Verify doc cross-references are intact
  • Built-in matchers only (see design skill for list)

Phase 8: Implementation

  • Implement in src/**/<feature>.spl
  • Follow /coding rules strictly
  • Reference: doc/07_guide/quick_reference/syntax_quick_reference.md

Phases 9-10: Unit + Integration Tests

  • 80%+ branch coverage target
  • Write unit tests alongside implementation
  • Write integration tests for cross-module interactions
  • Add doctests for public API functions

Phases 11-13: Bug Reports + Duplication Check + Refactoring

  • Run bin/simple bug-add for any discovered bugs
  • Check for code duplication across src/
  • Refactor: files > 800 lines must be split

Phase 14: Full Test Suite

bash
1bin/simple test && bin/simple build lint

Phase 15: Verify + VCS Sync

  • Run verify skill — must show STATUS: PASS
  • If src/compiler/**, src/lib/**, src/app/mcp/**, src/app/simple_lsp_mcp/**, or MCP packaging files changed, run:
    • sh scripts/check-core-runtime-smoke.shs <runtime>
    • SIMPLE_BINARY=<runtime> sh scripts/check-mcp-native-smoke.shs
    • If publish/package flow changed: sh scripts/check-mcp-package-smoke.shs
  • VCS sync: jj commit -m "feat: <feature description>"

Stub Prevention Gate

STUB001 = HARD FAIL. No pass_todo in final code.

Before declaring implementation complete, verify:

  • No pass_todo anywhere in new/modified files
  • No pass_do_nothing / pass_dn unless intentional no-op (documented)
  • No hardcoded returns without logic
  • No commented-out code blocks
  • No empty function bodies

Artifacts Produced

ArtifactPath
Implementationsrc/**/<feature>.spl
Unit teststest/**/<feature>_spec.spl
Integration teststest/**/<feature>_it_spec.spl
Bug reports (if any)Via bin/simple bug-add

Multi-LLM Collaboration

  • If other LLMs produced research/design/tests, build on them
  • Never overwrite existing artifacts — extend or improve
  • Tag Codex-produced code with # codex-impl comment on module header if needed

Rules

  • All code in .spl — no Python, no Bash
  • Generics use <> not []Option<T>, List<Int>
  • Pattern binding: if val not if let
  • Constructors: Point(x: 3, y: 4) not .new()
  • ? is operator only — never in names; use .? over is_* predicates
  • NO inheritance — use composition, alias forwarding, traits, or mixins
  • Use Result<T, E> + ? for error handling (no try/catch/throw)
  • Reserved keywords: gen, val, def, exists, actor, assert, join, pass_todo, pass_do_nothing, pass_dn
  • NEVER over-engineer — only make requested changes
  • NEVER add unused code — delete completely
  • NEVER convert TODO/FIXME to NOTE — implement or delete
  • Production MCP or LSP wrappers must execute cached compiled artifacts, not raw source entrypoints
  • Do not place full-tree scans or repeated file rereads in request handlers when a cache or index is viable
  • When cached or indexed data depends on writable files, implement explicit invalidation on create, edit, move, delete, rename, template application, and bulk replace flows
  • Add perf smoke coverage for startup and representative hot requests when changing performance-sensitive tooling
  • After compiler/core/lib changes, verify MCP/LSP source-native startup before finishing the task; after packaging/release changes, verify isolated npm install startup too

相关技能

寻找 impl 的替代方案 (Alternative) 或可搭配使用的同类 community Skill?探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

149.6k
0
AI

flags

Logo of vercel
vercel

React 框架

138.4k
0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

98.6k
0
开发者工具