lead-project
Autonomous technical lead. Takes commander's intent and drives a project to completion through an OODA loop over implementation, refactoring, review, and bug-hunting skills. Has broad authority — creates tickets, commits, invokes any skill — and only escalates via andon cord for irreversible actions, public releases, or genuinely blocking decisions. User acts as product owner; skill acts as tech lead.
npx skills add majiayu000/claude-skill-registry --skill lead-project --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Lead-Project drives a project from an explicit commander’s intent to completion by repeatedly cycling Observe → Orient → Decide → Act. It can scope new tickets, implement features, refactor, run reviews, hunt bugs, and deliberate on hard decisions. It stops autonomously when the intent is fulfilled and quality is acceptable, or the andon cord is pulled if it hits a wall.
How it works
The skill starts with a startup protocol where the user provides a five-field commander’s intent (Purpose, Key tasks, End state, Constraints, Non-goals). It seeds a state document (LEAD_PROJECT_STATE.md) and may optionally run a health review. Then it enters OODA loops: Observe by snapshotting project state (git status, branch, tests, build, lint, recent commits, prior cycle results); Orient by checking intent alignment, drift, and termination conditions; Decide by selecting actions from a provided set (e.g., /scope, /implement, /refactor, various /review-*, /bug-hunt, /test-mutation, /release with explicit restrictions); Act by executing the chosen action, validating state after, and recording outcomes in a cycle log. Every 10 cycles, a Trajectory audit is performed to verify convergence to intent, using inputs like git logs, diffs, the pinned intent, and the state’s deferred-items.
When to use it
Use when a project needs autonomous technical leadership with a clearly stated commander’s intent and the ability to operate with minimal user involvement. It escalates only via the andon cord for irreversible actions, public releases, or genuinely blocking decisions.
What it can touch
The skill may create and modify branches (except main/master), commit, open tickets via /scope, refactor, invoke review skills, spawn subagents, run tests, install local project dependencies if required by the package manifest, and invoke a variety of sub-skills (e.g., /implement, /lead-refactor, /review-*, /bug-hunt, /release). It cannot push or merge to main/master, create public releases or tags without explicit permission, perform force-pushes, install global/system dependencies, or execute irreversible destructive operations without permission.
Caveats
The automation relies on the five-field commander's intent and explicit termination criteria. Termination requires mechanical end-state conditions to pass, no constraint violations, re-run of relevant review skills with no high-severity findings, and quiescence of the codebase. Subjective end-state conditions are reported rather than autonomously declared met. The andon cord remains the sole escalation path for blocking decisions.
# Lead-Project — Autonomous Technical Lead Drives a project from a stated intent to completion with minimal user involvement. The user provides commander's intent at startup and reviews at the end (or on andon cord). Between those points, the skill runs an OODA loop — observing project state, orienting against intent, deciding what to work on next, and acting by invoking other skills. It can scope new tickets, implement features, refactor, run reviews, hunt bugs, and deliberate on hard decisions. It stops autonomously when intent is fulfilled and quality is acceptable, or pulls the andon cord when it hits a wall. ## Philosophy This skill implements the autonomy discipline documented in [`references/autonomy.md`](../../references/autonomy.md) at the highest level of the orchestrator family. The shared discipline governs the five levers (altitude rule, pre-loaded options, pre-rebutted recommendation, commander's intent, risk budgets), the cascade rule, the shared handoff template, and the "log instead of escalate" pattern. Skill-specific extensions (the OODA loop structure, trajectory audits, mechanical termination gates) are layered on top of that shared discipline. ### Commander's
- Philosophy
- Commander's intent is the anchor
- OODA loop structures each cycle
- Autonomy is the default
- Broad authority, narrow gates
- Engineering judgment beats review compliance
- Workflow Overview
- Workflow Details
- 0. Startup
- 1. OODA Loop
- 2. Termination
- Commander's Intent — Field Reference
- Purpose
- Key tasks
What does the lead-project skill do?
Autonomous technical lead. Takes commander's intent and drives a project to completion through an OODA loop over implementation, refactoring, review, and bug-hunting skills. Has broad authority — creates tickets, commits, invokes any skill — and only escalates via andon cord for irreversible actions, public releases, or genuinely blocking decisions. User acts as product owner; skill acts as tech lead.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill lead-project --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.