Autopilot
Use when the user says "autopilot", "build this", "make it", "ship it", "just do it", "do it", "implement this", or gives a vague idea, spec, task list, or bug fix and expects autonomous execution. Handles decomposition, agent coordination, and verification automatically. "build me end to end", "go from idea to code", "do everything", "run this autonomously". Follows the Spec-Driven Development workflow: specify → clarify → plan → tasks → analyze → implement.
Install
/plugin marketplace add npow/claude-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add npow/claude-skills --skill autopilotgit clone --depth 1 https://github.com/npow/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/autopilot ~/.claude/skills/autopilotPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Autopilot
The unified orchestrator. One skill that auto-scales from a single-agent one-file fix to a multi-agent staged pipeline with parallel fanout. The user never picks a topology — autopilot reads the task and selects one.
Follows the Spec-Driven Development (SDD) workflow: specifications are the primary artifact, code serves the spec. All non-atomic tasks produce structured artifacts in `specs/{feature}/` before any code is written.
## SDD Artifact Directory
For non-atomic tasks, autopilot creates and maintains:
```
specs/{NNN-feature-name}/
├── spec.md # Feature specification (Phase 1a)
├── checklists/ # Quality checklists (Phase 1a)
│ └── requirements.md # Spec quality validation
├── research.md # Technical research (Phase 1c)
├── plan.md # Implementation plan (Phase 1c)
├── data-model.md # Entity definitions (Phase 1c)
├── contracts/ # API/interface contracts (Phase 1c)
├── quickstart.md # Validation scenarios (Phase 1c)
└── tasks.md # Ordered task list (Phase 1d)
```
Feature numbering is sequential: scan existing `specs/` directories, take the next available 3-digit prefix. Feature name is derived from the task description (2-4 word kebab-case slug).
## Phases
### Phase 0: Task Analysis (always runs, <30s)
Read the input. Classify along three axes:
1. **Clarity**: vague idea → partial spec → full spec → single taskDetails
- Skill name
autopilot- Repository
- npow/claude-skills
- Path
autopilot/SKILL.md- License
- Apache-2.0
- Repo updated
- 20 August 2026
FAQ
What does the Autopilot skill do?
Use when the user says "autopilot", "build this", "make it", "ship it", "just do it", "do it", "implement this", or gives a vague idea, spec, task list, or bug fix and expects autonomous execution. Handles decomposition, agent coordination, and verification automatically. "build me end to end", "go from idea to code", "do everything", "run this autonomously". Follows the Spec-Driven Development workflow: specify → clarify → plan → tasks → analyze → implement.
How do I install the Autopilot skill?
Claude Code plugin: /plugin marketplace add npow/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Autopilot popular?
It lives in npow/claude-skills, which has 5 GitHub stars and 1 forks.
Related skills
Build Python Library
5npow/claude-skills
Implements pip-installable Python libraries from scratch using src layout, pyproject.toml, and pytest. Use when the user asks to build, create, implement, or scaffold a Python library, package, pip package, middleware, SDK, or wrapper. Covers project scaffolding, proxy/wrapper patterns, provider-agnostic interfaces, async/sync support, and test infrastructure.
Canon Design Review
5npow/claude-skills
Architecture-level design review evaluating 15 Tier 2 best practices drawn from DDD (Evans), POEAA (Fowler), Release It! (Nygard), DDIA (Kleppmann), Team Topologies (Skelton/Pais), How Buildings Learn (Brand), and Systemantics (Gall). Auto-invoke when a PR touches: - Service definitions, infrastructure code, API boundaries, or database schemas - Files matching **/architecture*, **/design*, **/api/*, **/schema*, **/migrations/* - Any directory named services/, infrastructure/, platform/, domain/, core/ Also invoke when the user says: - "design review", "architecture review", "review the design"
Canon PR Review
5npow/claude-skills
Review a PR against the top 20 Tier 2 LLM-enforceable best practices from 35 seminal software engineering books (Code Complete, Clean Code, A Philosophy of Software Design, Refactoring, Release It!, Designing Data-Intensive Applications, etc.). Produces a structured PR comment with four dimension scores (0-5 each), specific violations with line numbers, and an APPROVE / REQUEST_CHANGES / BLOCK decision. Auto-invoke when the user asks to: - "review PR", "canon review", "best practices review", "engineering standards review" - "score this PR", "check this PR against best practices" - Asks about
Ccr Run
5npow/claude-skills
Use when the user asks to run a task on a specific model, compare model outputs, or says 'run this on GPT/Gemini/Sonnet'. Routes tasks to any model via claude-code-router. Usage: /ccr-run [model] <task>
Validate Skill Functionality
8Freddy-CHEN-ux/00_claude_skills
Load when user says "validate skill", "validate this skill", "review skill execution", "check skill", or "skill validation" at the end of executing a skill. Post-execution review workflow for validating that a skill worked correctly, documenting findings, and identifying issues.
Loop Me
5GAGAA-HUE/ASHUO-claude-skills
Grill me about specs for the workflows I want to build, within this workspace.
Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.