cookys/autopilot
28 skills
$npx skills add cookys/autopilotSkillInstalls
auditCompare two existing implementations and find every difference.brainstormPre-code Socratic design exploration — when the options don't exist yet.ceo-agentFull delegation — you own the goal end-to-end, user just wants results.debugEvidence-first debugging for correctness issues. Invoke when diagnosing bugs, crashes, logic errors, data corruption, connectivity problems, intermittent…dev-flowStart here before writing any code — sizes task (S/L/H/Fix), sets up branch and session rules.distillDistill your recurring procedures and corrections from local conversation history into personal custom skills, routed into YOUR own skill dirs — never into…doc-syncAudit docs against actual code and find drift (wrong / stale / missing claims), report-only.engine-onboardingOnboard a new heterogeneous engine into the autopilot lifecycle.finish-flowClosing sequence forcing function — use at the END of any dev-flow workflow (L, H, Fix, S) to guarantee no step in the closing sequence gets silently…handoffWrite a standardized mid-work handoff doc for session continuation, and resume from one.harness-maintenanceAudit or refresh Autopilot harness capability state. Use when checking whether Codex, Claude Code, agy, Grok, MiniMax, Copilot CLI, or another harness…l3Terse CEO front-door — Level 3: full autonomy, CEO executes inline on this thread, escalate only at the DOA boundary.l4Terse CEO front-door — Level 4: dispatch ONE background, worktree-isolated sub-orchestrator "foreman" that runs dev-flow unattended and returns a verdict; CEO…l5Terse CEO front-door — Level 5: like /l4 (background worktree-isolated foreman, depth-0 control loop + authoritative qc) but the IMPLEMENTER is orchestrated by…l6Terse CEO front-door — Level 6: like /l5 (worktree-isolated hetero implementer + authoritative qc) but the VERIFICATION AUTHORING is also leaf-dispatched to a…learnSave a hard-won lesson or surprising fix so future sessions benefit.nextRecommend what to work on next by scanning all projects, plans, backlog, and proposals.onboardScaffold a consuming project's autopilot config (`.claude/*-config.md` DI) from its detected reality — the bridge from "fresh repo" to "autopilot-calibrated…profilingEvidence-first performance profiling — tool selection, methodology, interpretation. Use BEFORE guessing at performance issues.project-lifecycleBootstrap, organize, or archive project tracking docs. Use when: "archive this project", "bootstrap from plan", "set up project tracking", "clean up project…quality-pipelineRun pre-commit or pre-merge quality checks: tests, completeness scan (no stubs/TODOs/mocks), code review.research-to-shipPinned participatory pipeline — research industry best-practice → write a plan → bounded, rubric-frozen plan review (maximum two generations) → expand into a…retroEngineering retrospective from git history — velocity, test ratio, focus score, commit patterns.surveyResearch what the industry does — dual-agent (researcher + skeptic) tech investigation.teamTeam allocation and dependency-aware parallelization — decide when to use teams, select roles, dispatch parallel work safely.test-strategyTesting strategy and baseline management — test pyramid placement, baseline守則, failure investigation funnel, regression scoping, flaky-test systemic handling.think-tankMulti-role debate (architect, ops, QA, product, UX, finance) for strategic decisions.think-tank-dialecticHegelian dialectic (Thesis → Antithesis → Synthesis) for irreversible or high-stakes decisions with genuine stalemate — NOT a "better think-tank", a different…