TODO: เขียน description ที่มี trigger words เช่น \"bookmark\", \"save url\", \"save link\
Guide the design and maintenance of recordkeeping programs under SEC Rules 17a-3, 17a-4, and 204-2. Use when the user asks about document retention schedules, how long to keep…
CLI for AI agents to search and lookup books for their humans. Uses Open Library API. No auth required.
BookStack Wiki & Documentation API integration. Manage your knowledge base programmatically: create, read, update, and delete books, chapters, pages, and shelves.
BookStack Wiki & Documentation API integration. Manage your knowledge base programmatically: create, read, update, and delete books, chapters, pages, and she...
Run editing passes over completed sections for voice consistency, timeline verification, contradiction flagging, and citation coverage
Execute editing workflow orchestration - reviews and polishes completed sections
Generate writing tasks from BRD structure and corpus, creating chapter/section tasks with dependencies, pre-write queries, and consistency checks
Execute writing tasks autonomously by loading pending tasks, running pre-write queries, checking consistency, writing grounded content, and storing results
Execute writing workflow orchestration - writes sections sequentially from outline
Use the boolean() factory for toggle/checkbox fields. Use when defining Storyblok schema fields.
불티 AppTracker(Mixpanel) 이벤트 구현을 공식 컨벤션에 맞게 검증·제안한다. `AppTracker.view/click/impression/search/complete`, `Screen.X`, `Role.X` 등 트래킹 코드를 추가·수정·리뷰할 때, 또는 "트래킹 추가해줘", "이벤트 로깅",…
Booqable integration. Manage data, records, and automate workflows. Use when the user wants to interact with Booqable data.
Automate Booqable tasks via Rube MCP (Composio). Always search tools first for current schemas. — from general/automation
Boost integration. Manage data, records, and automate workflows. Use when the user wants to interact with Boost data.
Interactive prompt refinement workflow: interrogates scope, deliverables, constraints; copies final markdown to clipboard; never writes code. Requires the Joyride extension.
Configure Moodle Boost Union theme settings and customizations. Use when theming Moodle, configuring layouts, or customizing Boost Union features.
Boost.ai integration. Manage data, records, and automate workflows. Use when the user wants to interact with Boost.ai data.
Load project context efficiently (docs + structure, not all source code)
Start, watch, and restart a local stack of app processes together instead of juggling many terminals and ad hoc shell loops.
Draft booth rental agreement outlines for salons. TRIGGERS - Use when user needs help with booth-rental-agreement related tasks.
Scaffolds the minimum repository structure required by session-orchestrator. Invoked automatically by the Bootstrap Gate when CLAUDE.md, Session Config, or bootstrap.lock is…
Consistent agent behavior after restart — progressive identity loading, working context reconstruction from persistent artifacts, fresh-vs-continuation detection, calibration…
Inicializando repositórios sem contexto de IA com AGENTS.md, CLAUDE.md, camada do GitHub Copilot, docs lazy-loaded, memória de projeto e starter pack de skills.
GSD-OS bootstrap guide — from freshly unzipped directory to fully operational development environment.
Garante uso correto do Bootstrap 5 sem CSS customizado. Use quando criar ou modificar HTML, estilizar componentes, ajustar layout, ou o usuário mencionar Bootstrap, grid,…
Domain-agnostic knowledge acquisition — from zero to structured expertise through conversational learning
Construct the LLM synthesis prompt from project surface scan + optional tree-sitter context + optional Q&A answers. Call the LLM.
Write structured memory entries to the Cloud workspace via gaai_memory.store MCP tool with source='bootstrap'.
Bootstrap or guide a reproducible .NET solution with explicit F# or C# language choice, SDK selection, project layout, test project setup, and initial validation commands.
Provides comprehensive guidance for Bootstrap Vue 3 component library including Bootstrap components, grid system, utilities, and Vue 3 integration.
Bootstrap a new native Apple app project for macOS, iOS, or iPadOS when the user wants to start, begin, create, or bootstrap an Xcode app project.
Wires up an Airbyte connector for use in a PydanticAI or Claude SDK agent. Generates auth config, connector initialization, and tool_utils-decorated tool function.
Creates design document infrastructure including templates, workflows, and a specific design doc skill.
Prueft Korrespondenz auf Einklang mit der Berufsordnung der Rechtsanwaelte (BORA): Verschwiegenheit (§ 2 BORA), Sachlichkeit in Werbung und Aussenkommunikation (§ 6 BORA) sowie…
Automate Borneo tasks via Rube MCP (Composio). Always search tools first for current schemas. — from general/automation
Write Rust code in the style of Mara Bos, Rust library team lead and author of "Rust Atomics and Locks." Emphasizes low-level concurrency, atomics, and understanding the memory…
Advanced Boss orchestration patterns — Agent Teams leadership, 6-section delegation template, Skill vs Agent conflict resolution, Guardian pattern, and AI-slop detection.
BOSS 直聘 CLI 命令参考手册 — 34 个顶层命令，招聘者/求职者双模式。 本 Skill 是 boss-hr-auto 编排流程的参考引用，不应作为入口直接加载。
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals
BOSS直聘 CLI 工具，支持职位搜索、求职申请管理、聊天、发送招呼等功能。通过逆向 BOSS直聘 API 实现，支持多城市、多筛选条件。当用户需要搜索 BOSS直聘 上的职位、查看公司信息、管理求职申请、联系 HR 时触发。
Use when a Codex workspace needs BosskuAI routing, repo-local memory, skill selection, or quality gates without loading the full toolkit.
Use this for recommending which AI model fits a specific task based on reasoning depth, speed, tool use, coding needs, multimodality, cost sensitivity, and reliability tradeoffs.
Use this for bug hunts, regression analysis, suspicious changes, failure-path review, finding likely defects before shipping, and deep incident investigation using logs, DB state,…
Use this for workflow review, state transitions, approval and assignment design, edge cases, rule consistency, and finding hidden business logic flaws in products or systems.
Use this to analyze a repository and recommend Claude Code setup improvements, including CLAUDE.md, MCP servers, hooks, skills, commands, permissions, and onboarding configuration.
Use this to audit, maintain, and improve CLAUDE.md and Claude-specific rule files, including instruction quality, session learning capture, overlap control, and cross-tool…
Use this for tracing execution paths, mapping call chains and module boundaries, identifying side effects, and summarizing how code actually behaves at runtime.
Use this when a task risks hitting model context, token limits, or tight usage/quota mid-process. Stop cleanly, write progress into ai-assistant/memory/active-continuation.md,…
Use this after meaningful tasks, reviews, incidents, or repeated observations to decide the smallest durable artifact that should capture the lesson and keep future sessions from…
Use this for cloud/server/API/model cost control, token budgets, queue sizing, storage costs, vendor spend, and unit economics.
Use this when the current model is stuck, low-confidence, missing a capability, or repeating failed attempts.
Use this for version-specific framework or library documentation lookup through Context7, including API signatures, configuration options, breaking changes, and recently changed…
Use this for agent eval design, routing tests, retrieval tests, LLM quality cases, regression harnesses, scorecards, and continuous agent improvement.
Use this for financial modeling, revenue projections, ARR/MRR forecasts, runway, burn rate, unit economics, pricing model math, scenarios, sensitivity analysis, month-end close,…
Use this for GitHub workflow operations across issues, pull requests, Actions, releases, Dependabot, repository settings, and GitHub MCP-assisted project coordination.
Use this for GSAP animation work, including timelines, ScrollTrigger, responsive matchMedia motion, React useGSAP/context cleanup, SplitText/Flip-style interactions,…
Use this for rewriting copy, docs, README text, landing pages, posts, emails, UI microcopy, and responses so they sound specific, practical, and human instead of generic AI output.
Use this for Hyperframes video composition work, including HTML-based scene authoring, preview/render workflows, CLI commands, agent-friendly composition updates, and…
Use this for active incident triage, severity classification, escalation coordination, on-call communication, timeline reconstruction, and blameless postmortem facilitation.