autopilot
Drive a task from clarified objective through implementation and verification.
Skill by r3dlex
Chalk Labs
Need help deploying autopilot?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/r3dlex-autopilot-10aea0
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.
About
Use cases: productivity
Reviews
Write a reviewNo 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/autopilot
What's inside
- Skill name
autopilot- Description
- Drive a task from clarified objective through implementation and verification. Use when the user wants end-to-end autonomous execution.
- License
- MIT
- Instructions
- 32 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Autopilot Skill (oh-my-antigravity) ## Quick Start - Start from a clear objective, then move through planning, implementation, and verification without manual micromanagement. Use this skill when the user wants end-to-end execution with minimal supervision. ## Quick Start - The request is large enough to require planning, implementation, and verification - The user wants the agent to make reasonable assumptions and keep moving - A phased workflow is safer than ad hoc editing ## Workflow 1. Clarify the objective, constraints, and acceptance criteria. 2. Produce or refine a phased plan. 3. Execute the plan with minimal coherent changes. 4. Validate with typecheck, tests, and `omg verify` when relevant. 5. Return a completion summary, evidence, and follow-ups. ## Stop conditions - Missing requirements materially change the solution - Validation repeatedly fails without a credible next fix - The user asks to stop or switch to manual control ## Related surfaces - `omg skill plan` - `omg skill execute` - `omg skill verify` - `omg team run`
From r3dlex/oh-my-antigravity, MIT.
More from r3dlex/oh-my-antigravity
- 0.474score
hud-setup
r3dlex
Guide the user through enabling and tuning the oh-my-antigravity HUD surface.
SkillCFreshness: CClaude Code +9 - 0.474score
ask
r3dlex
Run a focused Gemini advisor prompt and save the reusable result artifact.
SkillCFreshness: CClaude Code +9 - 0.474score
cancel
r3dlex
Stop active workflow state safely and preserve resumable context.
SkillCFreshness: CClaude Code +9 - 0.474score
configure-notifications
r3dlex
Configure notification delivery for Slack, Discord, or Telegram.
SkillCFreshness: CClaude Code +9 - 0.474score
context-optimize
r3dlex
Analyze and compress context for higher signal-to-noise ratio.
SkillCFreshness: CClaude Code +9 - 0.474score
cost
r3dlex
Summarize token usage and spend-style session metrics across time windows.
SkillCFreshness: CClaude Code +9 - 0.474score
debug
r3dlex
Reproduce or inspect a failure, isolate root cause, and validate a fix.
SkillCFreshness: CClaude Code +9 - 0.474score
deep-interview
r3dlex
Run a structured Socratic interview that turns ambiguity into an implementation-ready brief.
SkillCFreshness: CClaude Code +9 - 0.474score
design-system
r3dlex
Extract, normalize, and sync design system tokens into DESIGN.md.
SkillCFreshness: CClaude Code +9 - 0.474score
doctor
r3dlex
Inspect setup, extension assets, runtime prerequisites, and state health.
SkillCFreshness: CClaude Code +9 - 0.474score
execute
r3dlex
Execute a concrete implementation task with concise progress updates and validation evidence.
SkillCFreshness: CClaude Code +9 - 0.474score
handoff
r3dlex
Produce a structured handoff document summarizing completed work and next steps.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 2
- Last commit (this folder)
- May 25, 2026 (5 months ago)
- Last release
- May 25, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/r3dlex/oh-my-antigravity
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from r3dlex
- 0.486score
ralph
r3dlex
Self-referential loop until task completion with configurable verification reviewer
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
swarm
r3dlex
Swarm orchestration with shared state for simultaneous sub-problem solving
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
omp-setup
r3dlex
OMP setup wizard for directory structure and MCP configuration
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
configure-notifications
r3dlex
Configure notification integrations for Telegram, Discord, Slack
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
ecomode
r3dlex
Token budget mode prioritizing task completion over exploration
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
trace
r3dlex
Evidence-driven tracing lane orchestrating competing tracer hypotheses
SkillCFreshness: C★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get autopilot running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
autopilot skill. Agent Mart. https://agentmart.dev/skills/r3dlex-autopilot-10aea0 (last updated 2026-10-24)