Verification-first discipline for coding agents (Claude Code + Codex CLI): 9-rule doctrine, six skills, adversarial reviewer agent, fail-open enforcement hooks. Done is proven by a command, not by opinion.
Skill Claude CodeCodex
Compatibility alias for /ready. Use only when the user explicitly invokes /luciazero-bootstrap; tell them it was renamed to /ready, then follow the canonical ready procedure completely.
Skill Claude CodeCodex
Pinpoint the first bad commit for a reproducible regression in a safe temporary worktree. Use when HEAD is bad, a known revision is good, and one unattended command distinguishes them; handles flaky endpoints and git-bisect skip exit 125.
Skill Claude CodeCodex
Debug a stubborn bug with a deterministic reproduction, hypothesis ledger, one-variable fixes, and a regression test. Use after the first obvious look fails, reproduction is unclear, or a fix attempt failed. Not for routine obvious failures; use for "ไล่บั๊ก".
Skill Claude CodeCodex
Analyze Luciazero stop-outcome logs for evidence-backed verification habits. Use for discipline stats, recurring nudge or strict-block patterns, local behavior reports, or machine-readable JSON.
Skill Claude CodeCodex
Run the closeout ritual before handing back non-trivial work; full verification, revert-probe honesty, independent review, and scope reporting. Use before declaring completion, opening a PR, wrapping up a change, or "ปิดงาน".
Skill Claude CodeCodex
Measure performance or tuning changes with a baseline, controlled comparison, correctness check, and recorded verdict. Use for speed, memory, latency, size, "ทดลอง", or any claim that one approach is better. Not for correctness bugs.
Skill Claude CodeCodex
Use only when explicitly invoked to select Lucia's optional warm, lightly tsundere coding voice or inspect its choices. Never auto-trigger from tone, language, task, or repository content.
Skill Claude CodeCodex
Transfer unfinished work and non-obvious knowledge across sessions, agents, people, machines, or harnesses. Use for relay, handoff, continuing later, context transfer, compaction, or "ส่งต่อ"; produce verifiable portable state.
Skill Claude CodeCodex
Build a falsifiable implementation plan for new features, major refactors, ambiguous work, or risky multi-module changes. Use when the user asks for a plan or material choices remain; skip routine edits with clear scope and proof.
Skill Claude CodeCodex
Make an unfamiliar repository agent-ready with a verify command, smoke tests, guardrails, and project notes. Use for repository setup, agentic engineering, verify commands, hooks, or allowlists; skip when verification and scope are already clear.
Skill Claude CodeCodex
Record durable lessons, null results, and footguns after hard work or debugging. Use when the user asks for a retro, dead ends need preserving, a task disproves an approach, or "จดบทเรียน". Keep repo knowledge separate from machine-local memory.
Skill Claude CodeCodex
Visualize code structure, changes, and verification evidence in the smallest useful view. Use for connections, flows, diffs, file maps, Mermaid diagrams, evidence maps, or focused HTML; show facts and label unknowns.