Claude Skills by kookr-ai

Make Codex CLI behave more like Claude Code for Kookr by preserving the known fork, branch, build, deploy, daily upstream sync, and live-verification workflow for Claude-compatible skills, agents, settings, hooks, and related UX.

State management for codex-pr-lessons playbook — persist learnings and update tracking state

How to record, verify, export, and publish the Kookr demo video with optional TTS narration audio

Rate limiting and blocked-repo enforcement for OSS contributions — hook behavior, oss-gate CLI, ledger format, configuration

Verify the OSS contribution dashboard is accurate by comparing the store (GET /api/oss-attempts) against GitHub reality via gh CLI. Reports missing, phantom, and state-drifted PRs.

Find the best contribution opportunity in an external repository — scores issues by clarity, size, acceptance likelihood, competition, match, and local reproducibility

State management for oss-pr-lessons playbook — persist learnings and update tracking state for any repository

Analyze an open-source repository's contribution requirements — CONTRIBUTING.md, PR template, CI config, CLA, build system, key reviewers — before attempting any contribution

Repo delivery-cycle follow-through after push or PR creation — verify mergeability, checklist state, CI, and early feedback by composing pr-lifecycle and pr-review-triage.

Full PR lifecycle — creation, checklist tracking, CI monitoring, review resolution, body updates, and post-merge cleanup. Use together with post-push to finish PR follow-through.

Repo delivery-cycle entrypoint before git push or PR creation — compose the repo pre-push hook, pre-pr-review, reviewer specialists, and PR gate without duplicating them.

Start, observe, pause, resume, or cancel Kookr's first-class Ralph iteration loops for task-scoped repeated agent work

Kookr-internal extension to rfc-iterative-review that captures append-only critic traces for later meta-analysis of RFC reviewer subagents.

Analyze a Kookr supervision session to identify friction patterns and generate actionable improvements for agent behavior and anomaly detection.

Shadow detection system for validating new stuck-detection strategies against production traffic before activation

Where Kookr skills and agents live (.claude vs plugin) and how to name them. Repo-local Kookr work lives in .claude/ with `kookr-`; Kookr-distributed and general reusable skills live in plugin/. Use this skill before creating, renaming, or promoting a skill or agent.

Create a new Kookr task from within an agent session via the HTTP API

Autonomously monitor running Kookr agent tasks, advance them through permission prompts / idle states, and judge completion correctly (including treating CI Actions-budget failures as non-blocking). Use when the user asks to "supervise", "monitor", "babysit", or "auto-advance" running Kookr tasks.

How Kookr runs agent terminal sessions — TerminalBackend interface, dtach persistence, KOOKR_BACKEND env var, SessionBridge routing, legacy tmux paths. Use when touching adapter launch code, session I/O, stuck detection's paneContent, reconciliation, or the circuit-breaker-registry terminal entry.

Analyze an open question by casting 3-5 deliberately conflicting expert roles, running them in parallel and blind to each other, sharpening them in a debate round, attacking their consensus with a devil's advocate, then synthesizing a verdict that preserves disagreement instead of averaging it. Use for decisions, strategy, idea generation, hypothesis triage, experiment post-mortems, or any question where a single lens would return "it depends".

Analyze recent Claude Code and Codex CLI conversations for repeated inefficient tool calls, token waste, retry loops, avoidable errors, and recurring setup friction; rank improvements by benefit/ease, then implement the smallest durable guardrail after user approval.

Detect AI-induced architecture drift by measuring file-size distribution, layer-boundary violations, and dependency-graph corruption. Use to score structural health, spot drift hotspots, and produce a drift report.

Async flow control patterns - AbortController cancellation, async iterators for large datasets, worker thread selection, Promise combinator choice, stream backpressure in async pipelines

Run bounded autonomous implementation and independent-review correction cycles with durable accounting, exact-head merge safety, and periodic quality-preserving reflection.

Run a long-lived watch/janitor task that polls a system on an interval and acts on what it finds. Use for "monitor X all day and do Y", task sweepers, queue drains that wait on external state, deploy and CI watchers, and any loop that would otherwise ping the operator every cycle with a status line.

Claude Code hook system — all 25 event types, payloads, matchers, state machine, and integration patterns for agent monitoring

Analyze Claude Code telemetry, stats-cache, and history data from ~/.claude to identify UX friction, performance issues, workflow inefficiencies, and improvement opportunities.

Claude Code permission system — modes, allow/deny/ask rules, pattern syntax, settings precedence, and optimal configuration for minimal prompts with safety guardrails

Write clear technical prose everywhere — code documentation (docstrings, comments, module/API/reference docs, config comments), design docs and READMEs, PR bodies/changelogs/summaries, AND explanations of genuinely hard ideas (novel algorithms, subtle failure modes, non-obvious tradeoffs). Plain-language intent first, jargon defined, identifiers only after the human explanation; for hard ideas, build intuition with analogies that carry the real mechanism. Use for any writing a human must unde...

Critic phase for codex-pr-lessons playbook — analyze a PR and extract quality signals

Distillation phase for codex-pr-lessons playbook — compress raw learnings into patterns and update skills

Plan phase for codex-pr-lessons playbook — load state, determine next batch of PRs to analyze

Threshold verification for codex-pr-lessons playbook — determine if distillation should trigger

Dependency injection best practices - constructor injection, composition root, lifetime management, testability, circular dependency prevention, framework independence

DDD strategic and tactical patterns - bounded contexts, aggregates, value objects, domain events, ubiquitous language, context mapping, subdomain classification. Use when modeling domain logic, designing aggregates, or deciding where to invest in rich models vs simple CRUD.

Strategy for mocking Claude Code agents in E2E tests with canary validation against real behavior.

Error handling best practices - cause chaining, boundary validation, structured errors, fire-and-forget safety, retry discipline

Build reliable event pipelines with reconnect-safe subscriptions, idempotency, and contract fidelity.

Find the best code reviewers in a GitHub repository or for specific file paths — uses GraphQL to analyze PR review history, filters bots, weights review states, surfaces domain specialists

Git commit hygiene for AI agents - atomic commits, Conventional Commits, secret scanning, branch safety, history protection

Standard workflow for creating GitHub issues with assignment and worktree branch creation for immediate implementation. Includes branch strategy and worktree conventions.

Find and rank trending GitHub repositories by real activity signals (commit velocity, PR throughput, contributor growth) — filters out non-code repos and scores for contribution opportunity

Use Claude Code hooks as deterministic workflow enforcement — block-then-instruct pattern, CLI command surfaces for hook interception, when to prefer hooks over CLAUDE.md/memory

Before an autonomous self-merge, spawn a fresh-context reviewer (Codex lane, Claude fallback) that posts a machine-readable exact-head PR verdict; BLOCK and missing or stale verdicts start another correction cycle.

Structured logging best practices - Pino JSON output, log levels, correlation IDs, PII redaction, sampling, async context, canonical log lines

Explore the current system and generate or update multi-level architecture documentation using an MBSE-lite approach: system context, capability map, containers, runtime sequences, state machines, subsystem decompositions, and boundary-smell analysis.

TypeScript monorepo structure - module boundaries, dependency direction, god objects, abstraction discipline, configuration management, interface design. Use when creating packages, refactoring cross-package imports, or reviewing architecture.

Fork lifecycle management for open-source contributions — fork creation, clone, upstream sync, feature branches, PR creation targeting upstream

Analyze a PR from any repository and extract quality signals — description, reviews, scope, tests, CI, guidelines, outcome

Distillation phase for oss-pr-lessons playbook — compress raw learnings into repo-specific patterns and update shared general skill