bouob

Static risk review of a GitHub Pull Request — correctness, breaking changes, security, secret leaks, test/error-handling/type/comment risks. This skill should be used when the user asks to "review this PR", "review a pull request", "audit a PR", gives a PR URL or owner/repo#number, or wants a pre-merge risk check. Does NOT run tests/build/lint or modify files. For local uncommitted diff review use /review instead.

Security-vet a third-party GitHub repository BEFORE using, cloning into a project, or installing it. Clones to an isolated directory (never executes repo code) and statically scans for credential theft, hidden outbound connections, install-time attacks (malicious postinstall / setup.py), obfuscated payloads, supply-chain risks, leaked secrets, and dangerous CI workflows. Outputs a verdict report (BLOCK / CAUTION / PASS). Use this skill whenever the user asks "is this repo safe", "scan this repo", "can I trust this project", "會不會偷 key", "這個 repo 安全嗎", "掃描這個 repo", "幫我檢查這個專案可不可以用", or pastes a GitHub URL of an unfamiliar project they intend to install or run. Not for reviewing the user's own code (use /review) and not for auditing changes on the current branch (use /security-review).

Sync the Notion PAI second-brain (Projects, To-Do, Inbox, Knowledge Base) with the local gbrain knowledge graph. `pull` mirrors Notion into gbrain (down); `push` sends local gbrain edits up to Notion (up-only — a page changed on the Notion side is left for the next pull, never clobbered). Includes interactive first-time init. Use when the user says /notion-sync, init notion sync, sync notion, pull notion, push notion, refresh brain, notion sync status, notion sync conflicts, notion sync doctor, 初始化 notion, 同步 notion, 拉取 notion, 推回 notion, 雙向同步, brain 沒更新, 檢查 notion 同步, notion 衝突. Sub-commands: init, pull, push, conflicts, schedule, status, doctor. Do NOT use for: ad-hoc Notion page edits (use Notion MCP tools like notion-update-page), general gbrain queries (use mcp__gbrain__* directly), or installing gbrain itself (use gbrain CLI per RUNBOOK.md Step 1).

Enforce project-specific coding constraints that Claude does not apply by default: function length limits (50 TS / 60 Python), dependency injection over concretions, and structured data class selection. Auto-loaded by /write, /fix, /review, /refactor when designing interfaces or checking architecture. Do NOT use for refactoring (use /refactor) or bug fixes (use /fix).

Review local code changes for style, test quality, and architecture. This skill should be used when the user asks to "review code", "review my changes", "check code quality", "review the diff", or wants a pre-commit code review. Not for GitHub PR review — use /pr-review instead.

AI-era technology decision framework for tech selection, architecture choices, and build-vs-buy analysis. This skill should be used when comparing frameworks, services, tools, or libraries, evaluating architecture approaches (monorepo vs multi-repo, SSR vs SSG), deciding build vs buy, or assessing whether to upgrade or stay. Trigger phrases: "which should I use", "A vs B", "should I switch to", "build or buy", "upgrade or stay", "compare X and Y", "what is the best option for". Do NOT use for pure implementation tasks where the technology choice is already made.

Systematic diagnosis workflow — find root cause before proposing any fix. This skill should be used when encountering bugs, crashes, errors, test failures, unexpected behavior, build failures, stack traces, or performance problems. Do NOT skip to fixes before completing Phase 1.

Fix a bug using TDD. Diagnose root cause, write a failing test, then fix. This skill should be used when the user asks to "fix a bug", "debug and fix", "find and fix", or encounters a failing test, crash, or regression that needs a code fix. For diagnosis only without fixing, use /diagnose instead.

Use this skill whenever the user wants change-management paperwork (RFC, change request, change record, governance doc, rollback doc, CAB submission) for anything AI or ML. This is the correct skill — not a generic RFC skill — any time the subject of the change is a model, LLM, chatbot, AI agent, prompt, RAG pipeline, embedding, knowledge base, training data, or fine-tuning job. Common situations: swapping LLM providers or model versions, deploying or retraining an ML model, RLHF or fine-tuning runs, editing production prompts, refreshing RAG sources, granting an agent new autonomous actions or tools, and emergency rollbacks when an AI is hallucinating or producing harmful output. Rule of thumb: if the user is asking for approval/governance paperwork AND the thing being changed could shift an AI's behavior, this skill wins over any general change-request skill. Also use for questions about ITIL v5 AI Governance or the 6C model (Creation, Curation, Clarification, Cognition, Communication, Coordination).

ITIL change request and CAB review workflow. This skill should be used when the user asks to "create a change request", "write an RFC", "plan a change", "CAB review", "change management", "schedule maintenance", "server migration plan", "upgrade plan", "AI model deployment", "GitOps change", or describes any planned modification to IT infrastructure or services. Produces a complete RFC document following ITIL v5 Change Enablement.

Operations task verification gate before claiming work is complete. This skill should be used before closing incidents, finalizing change requests, sending resolution notifications, or when asking "is this resolved?", "can we close this?", "is the change complete?", or verifying SLO compliance after an incident. Evidence before claims — verify operational status first.

IT incident response workflow. This skill should be used when the user asks to "log an incident", "handle an incident", "create incident report", "document an outage", "incident response", "service is down", "major incident", or describes a service disruption requiring structured response. Also use when the user mentions SRE concepts like error budget impact, blameless review, or AIOps-detected incidents. Guides through the full ITIL v5 incident lifecycle: detect, classify, investigate, resolve, communicate, and close.

ITIL (Version 5) framework reference for IT service management and digital product management. This skill should be used when handling incidents, creating change requests, conducting CAB reviews, classifying priority levels, asking about ITIL v5 practices, AI governance, SRE integration, error budgets, or sustainability in IT operations. Provides Incident Management, Change Enablement, Priority Matrix, AI Governance (6C model), and SRE guidance.

Use this skill when the user wants help writing up a resolved production incident, outage, or failure. This is the go-to skill for any request that involves turning "something broke and we fixed it" into a written document — whether the user calls it a postmortem, post-incident review, post-incident analysis, PIR, incident retrospective, blameless review, no-blame writeup, lessons learned, or just describes what broke (deploy, database, auth, payment, storage, backup, replication, service outage) along with details like severity, duration, users affected, or rollback, and asks for help documenting it. Also use when the user's goal is team learning or capturing details before they're forgotten from a past incident. Output is a blameless document with timeline, contributing factors, what went well, and action items. Do not use for active/ongoing incidents, sprint or agile retrospectives, code reviews, general project retros, problem records for recurring issues, change requests, or meeting agendas.

Use this skill when the user wants to open a problem record, register a known error (KEDB), or run root cause analysis (RCA, 5 Whys, Fishbone) on an IT issue. Trigger on explicit phrases: "problem record", "problem ticket", "known error", "KEDB", "RCA", "root cause analysis", "systemic weakness", "latent risk". Also trigger when the user describes a recurring failure ("every Monday", "every Saturday night", "keeps happening weekly", "5 incidents this month all pointing at..."), wants to proactively track a trending risk before it becomes an outage ("disk trending to 100%", "capacity heading bad", "no smoke tests yet"), or needs to link a workaround to a permanent fix. The user's intent is to track and eliminate an underlying cause across multiple occurrences — not to fight a live outage, not to write a postmortem for a single past incident, and not to draft a change request. If they say "problem", "known error", "recurring", or "systemic" in an ITSM context, use this skill.

Stakeholder communication templates for IT operations. This skill should be used when writing incident notifications, status page updates, maintenance announcements, or any communication to users, management, or other teams about IT service events. Provides severity-based tone guidance and audience-aware messaging.

Autonomous multi-agent sprint: Planner decomposes spec → Generators implement in parallel via a Claude Code dynamic workflow (Agent-tool fallback when workflows are unavailable) → Evaluator verifies against acceptance criteria → iterates up to 3 times. Use when spec requires 3+ distinct tasks or multi-step implementation across files or domains. Do NOT use for: single-file edits, quick bug fixes, or tasks completable in one context window.

Plan, execute, and review multi-agent harnesses using the Planner-Generator-Evaluator pattern (Anthropic Engineering, 2026-04-04). Use when a task exceeds one context window, benefits from parallel subagents, needs Playwright MCP browser-level verification, or requires sprint-contract negotiation between Generator and Evaluator. Also use when routing work across Fable 5/Opus (orchestration/eval) / Sonnet (generation) / Haiku (collection), deciding inline-vs-subagent-vs-workflow, designing context reset vs compaction handoffs, or reviewing whether a knowledge unit belongs in a hook, skill, rule, reference, or prompt. Do NOT use for: single-file edits, simple Q&A, or work that /sprint already templates end-to-end.

Initialize agent-harness model routing for Codex. Writes Codex-only config under .codex or ~/.codex using inherit or explicit per-role routing.

Use when a user wants a Codex-ready plan for an agent-harness sprint before implementation. Produces a decision-complete Planner/Generator/Evaluator sprint plan without editing application code.

Use when a user asks Codex to run an agent-harness sprint with Planner, Generator, and Evaluator phases. Delegates parallel work only when task ownership is explicit and disjoint.

This skill should be used when the user asks to customize claude-statusline appearance, or mentions: change theme, switch theme, bar style, separator, statusline colors, dracula, nord, catppuccin, hide segment, show segment, rate-limit settings, rainbow settings, responsive.