菜单
Autonomously develops a complete feature from priming through planning, execution, and commit by chaining the four core PIV-loop skills. Use when you want a full hands-off feature build from a single description.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/coleam00/skills --skill piv-run-full-loop命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | piv-run-full-loop |
| description | Autonomously develops a complete feature from priming through planning, execution, and commit by chaining the four core PIV-loop skills. Use when you want a full hands-off feature build from a single description. |
| argument-hint | ["feature-description"] |
Feature Description: $ARGUMENTS
This skill chains the 4 core PIV-loop skills for autonomous feature development.
Execute the priming workflow to understand the codebase.
Run the prime-codebase skill (.claude/skills/prime-codebase/SKILL.md).
Create a detailed implementation plan for the feature.
Run the piv-plan-implementation skill (.claude/skills/piv-plan-implementation/SKILL.md) with the feature description: $ARGUMENTS.
IMPORTANT: Note the feature name (and plan file path) that the planning step creates. You'll need it for the next step.
Implement the feature from the plan document.
Run the piv-implement skill (.claude/skills/piv-implement/SKILL.md) with the plan file path: .claude/plans/[feature-name].md.
(Use the feature name from Step 2.)
Create a git commit for all changes.
Run the piv-commit skill (.claude/skills/piv-commit/SKILL.md).
After completing all 4 steps, provide:
Original Request: $ARGUMENTS
Feature Name: [feature-name from planning step]
Steps Executed:
.claude/plans/[feature-name].mdOutputs:
.claude/plans/[feature-name].mdNext Steps:
git pushAuthor a working Claude Code hook from a plain-English description of what it should guarantee or do. You describe the behavior ("never let the agent edit my migrations", "don't stop until the tests pass", "log every command"); this skill picks the right lifecycle event, writes the hook script, and wires it into .claude/settings.json. Use when you want a deterministic guarantee or automation in your AI Layer and don't want to write the hook by hand. The meta-tool for the hooks primitive.
Take a PRD and build a dark factory around it - a repository that takes work in as an issue and ships validated code out with nobody at the keyboard - one component at a time, into the user's actual repo. Covers the five components in construction order - the guidance layer, the validation harness, the workflow-driven repo, deployment, and the trigger that makes it autonomous - and is agnostic about which coding agent runs underneath (Claude Code, Codex, Archon, the Agent SDK, Cline, Goose, Amp, Pi). It encodes the AI coding process the user already runs rather than replacing it. Requires a PRD as input and deliberately does not write one. Use when the user wants to build a dark factory, an autonomous or self-driving repository, a software factory, an agent that ships its own code, an unattended or overnight coding loop, or asks how to get to level 4 or level 5 of AI coding autonomy; and when they mention dark factory, lights-out coding, autonomous PRs, or a repo that maintains itself.
Scan how you actually work with your coding agent and surface what to encode next. Point it at ONE run's artifacts to find what would have prevented a specific failure (the reactive loop — 'that went wrong, what should change in the AI layer?'), or at a window of session logs to find recurring patterns worth building (the proactive scan). Agent-agnostic. Outputs a shape-only HTML report. Use to evolve your system from real usage.
基于 SOC 职业分类
