autopilot
Full autonomous execution from idea to verified working code: expand → plan → build → QA → review.
Skill by siddicky
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/siddicky-autopilot
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: testing
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
- Full autonomous execution from idea to verified working code: expand → plan → build → QA → review.
- License
- MIT
- Instructions
- 23 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# autopilot Run the complete lifecycle autonomously, one phase at a time. Do not start a phase until the previous one is done. 1. EXPAND — delegate to `analyst` to extract requirements, constraints, and edge cases. If the request is too vague to expand, ask one round of clarifying questions first. 2. DESIGN & PLAN — delegate to `architect` for a technical design, then `planner` for an ordered, milestone-based plan. Have `critic` stress-test the plan and fold in its blockers. 3. EXECUTE — work the plan with `write_todos`. Delegate each milestone to `executor` (or `debugger` / `test-engineer` / `designer` as appropriate). Run independent milestones in parallel. 4. QA — delegate to `verifier` to build, lint, and test. Fix failures and repeat, up to 5 cycles. If the same error persists 3 times, stop and report the fundamental issue. 5. REVIEW — delegate in parallel to `code-reviewer` and `security-reviewer`. All blockers and majors must be fixed and re-reviewed before completion. Report what was built with the evidence that it works.
From siddicky/oh-my-dcode, MIT.
More from siddicky/oh-my-dcode
- 0.471score
deep-interview
siddicky
Socratic requirements gate: interview the user in rounds, stress-test from multiple angles, and crystallize a spec before any planning.
SkillCFreshness: CClaude Code +9 - 0.471score
ultragoal
siddicky
Durable multi-goal execution: decompose a ratified plan into ordered goals and drive each to an all-pass checkpoint via rubric self-evaluation.
SkillCFreshness: CClaude Code +9 - 0.469score
ralplan
siddicky
Consensus planning gate: produce a plan, stress-test it from multiple perspectives, and converge before building.
SkillCFreshness: CClaude Code +9 - 0.469score
team
siddicky
Staged pipeline of coordinated agents: plan → spec → execute → verify → fix, on a shared task list.
SkillCFreshness: CClaude Code +9 - 0.469score
ultrawork
siddicky
Maximum parallelism: decompose the goal into independent units and fan them out across agents at once.
SkillCFreshness: CClaude Code +9 - 0.464score
ralph
siddicky
Persistent verify/fix loop: keep iterating on a single goal until a reviewer confirms it is done.
SkillCFreshness: CClaude Code +9 - 0.464score
deepship
siddicky
Full idea-to-shipped pipeline: deep-interview → ralplan → ultragoal → team, run as four gated phases.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 20, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/siddicky/oh-my-dcode
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from siddicky
- 0.471score
deep-interview
siddicky
Socratic requirements gate: interview the user in rounds, stress-test from multiple angles, and crystallize a spec before any planning.
SkillCFreshness: CClaude Code +9 - 0.471score
ultragoal
siddicky
Durable multi-goal execution: decompose a ratified plan into ordered goals and drive each to an all-pass checkpoint via rubric self-evaluation.
SkillCFreshness: CClaude Code +9 - 0.469score
ralplan
siddicky
Consensus planning gate: produce a plan, stress-test it from multiple perspectives, and converge before building.
SkillCFreshness: CClaude Code +9 - 0.469score
team
siddicky
Staged pipeline of coordinated agents: plan → spec → execute → verify → fix, on a shared task list.
SkillCFreshness: CClaude Code +9 - 0.469score
ultrawork
siddicky
Maximum parallelism: decompose the goal into independent units and fan them out across agents at once.
SkillCFreshness: CClaude Code +9 - 0.464score
ralph
siddicky
Persistent verify/fix loop: keep iterating on a single goal until a reviewer confirms it is done.
SkillCFreshness: CClaude 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/siddicky-autopilot (last updated 2026-10-24)