design.md 기반으로 DB→백엔드→프론트엔드 순서로 코드를 구현하고 gate 에이전트로 자동 검증합니다. 사용자가 '개발', '구현', '코딩'을 언급할 때 사용하세요.
분석/설계 없이 바로 코드를 구현합니다. 버그 수정, 소규모 변경, 설정 수정 등 간단한 작업용. 사용자가 '빠른 수정', '버그픽스', '간단한 변경'을 언급할 때 사용하세요.
시장기회/실행가능성/수익성/차별성 가중 평가, 가정 검증, 시나리오 분석으로 Go/No-Go/Pivot 판단을 내립니다. 사용자가 '판단', '의사결정', 'Go/No-Go'를 언급할 때 사용하세요.
BMC 9블록, 가격전략, 단위경제학(CAC/LTV), 비용구조를 포함한 model.md를 작성합니다. 사용자가 '비즈니스 모델', '수익 구조', '가격 전략'을 언급할 때 사용하세요.
MVP 정의(MoSCoW), 3단계 로드맵, 리소스 계획, GTM 전략, 리스크 관리를 포함한 plan.md를 작성합니다. 사용자가 '실행 계획', 'MVP', '로드맵'을 언급할 때 사용하세요.
대화 로그, memory.md, CLAUDE.md, 태스크 산출물을 읽어 협업 패턴과 개선점을 회고 보고서로 정리합니다. 사용자가 '회고', '멘토링', '패턴 분석', '협업 리뷰'를 언급할 때 사용하세요.
GitHub Issue 생성(create), 태스크 시작(start), 상태 조회(status), 이력(history), 목록(list)을 관리합니다. 사용자가 '태스크', '이슈', '작업 시작'을 언급할 때 사용하세요.
작업 산출물과 대화/결정 기록을 바탕으로 workspace/wiki 내부 위키를 갱신합니다. 사용자가 '위키', '작업 기록', '이력관리', '내부 문서화', '히스토리', '작업 로그'를 언급하거나 작업 완료 후 지식 축적이 필요할 때 사용하세요.
Report real device usage from ActivityWatch. Covers per-app time, window titles, and active vs idle spans.
Use when asked to generate an FSM adversarial verification loop YAML that tries to break a feature via boundary values, malformed inputs, and failure modes.
Generate machine-specific AGENTS.local.md with host facts and system tool details
Generate AI design contract (AI-SPEC.md) for phases that involve building AI systems — framework selection, implementation guidance from official docs, and evaluation strategy
Combined knowledge base from \"The Algorithm Design Manual\" (Skiena) and \"Algorithms, 4th Edition\" (Sedgewick & Wayne).
Use when interrogating the codebase to understand an entity, its fields, relationships, and data flows.
Use when evaluating whether a technical approach is feasible against the current codebase. Use when user says 'analyze feasibility', 'is this feasible', 'evaluar factibilidad',…
A measurement-first decision discipline for choosing HOW to build something. Before pouring effort into one approach, operationalize a measurable fitness, sketch a few candidate…
Help fill out a job application form. Generates personalized answers for every field using your profile and evaluation. Never auto-submits.
Multi-agent code review using Agent Teams. Summons up to 8 built-in Ashes (plus custom Ash from talisman.yml), each with their own dedicated context window.
Hierarchical plan execution — orchestrates parent/child plan decomposition with dependency DAGs, requires/provides contracts, and feature branch strategy.
対応完了したハンドオフを docs/archive/ へ移動するスキル。/audit-handoffs で ✅ 判定が揃ったものを git mv でまとめてアーカイブし、関連ドキュメント（traceability.md・completion-summary.md）からの参照を洗い出す。
Answer questions about Claude Code CLI, Claude Agent SDK, and Claude API (Anthropic API). Use when the user asks about Claude Code features, settings, hooks, MCP, slash commands,…
Task Assignment Agent - Assigns Native Tasks to worker terminals, updates ownership, and syncs progress tracking.
Use when asked to audit Claude Code config, validate plugin settings, or diagnose plugin issues.
Use when asked to detect conflicting requirements or incompatible decisions across open issues.
Use when asked to assess loop effectiveness, audit goal achievement, or detect phantom success.
Close every autonomous run with a learning pass so the machine never repeats a mistake it already paid for: harvest the run's STRUCTURED artifacts (checkpoint register,…
Make code measurably faster without breaking it: metric + reproducible baseline FIRST, profile to the real hotspots, then per hotspot apply a change and re-benchmark — kept ONLY…
Reduce a change's complexity WITHOUT changing behavior, provably: find duplication/dead code/over-abstraction in the diff, apply the smallest clarifying edit, then prove behavior…
Turn a raw feature request into a grounded, TESTABLE spec — autonomously. It recons the real repo and domain to ground every claim, drafts a spec (objectives, user-visible…
Run the whole engineering lifecycle end-to-end from one request — spec → plan → build → simplify → test → review → performance → ship — as a single autonomous pass with ONE human…
bkit plugin help - list available functions. Use "/bkit" or "bkit help". Triggers: bkit, help, functions, 도움말, 기능, ヘルプ, 帮助, ayuda, aide, Hilfe, aiuto.
Browse installed bkit skills, agents, and evals via lib/discovery/explorer.js (filesystem scan, no subprocess).
Use when extracting user stories from a visual board. Use when user says 'extract stories', 'genera user stories', 'procesa scope', 'board to stories', or shares a board URL.
Initialize a new book project by creating a Book Requirements Document (BRD) through guided questions
Turn ideas into designs through collaborative dialogue. Use when user wants to brainstorm, design features, explore approaches, or think through implementation before coding.
Answer Engine Optimization (AEO) audit and SERP analysis for AI-generated answers. Analyzes pages for AEO readiness (structured data, FAQ patterns, heading hierarchy, meta…
The discipline that keeps an autonomous run from becoming a runaway: before any unattended loop or workflow, declare the five stop conditions — done-condition, hard cap,…
Build a distributable DMG for a macOS Xcode project by resolving the project, scheme, signing/export inputs, then running the local helper script that archives, exports, and…
Spin up an interactive local web console for FIRM-LEVEL scenario modeling over Carta Fund Admin data — a React app to reprice portfolio companies and model exits ACROSS MULTIPLE…
Open the Session Cartographer Explorer web UI for visual browsing of session history.
Multi-LLM consensus engine. Queries multiple AI models and synthesizes a single answer using strategies like voting, judge synthesis, and multi-round debate.
Добавить объект метаданных в конфигурацию 1С с формой, подсистемой и валидацией. Workflow: meta-compile → cf-edit → subsystem-edit → form-add → form-compile → validate.
Точечное редактирование конфигурации 1С. Используй когда нужно изменить свойства конфигурации, добавить или удалить объект из состава, настроить роли по умолчанию, поменя — from…
Анализ структуры конфигурации 1С — свойства, состав, счётчики объектов. Используй для обзора конфигурации — какие объекты есть, сколько их, какие настройки — from…
Создать пустую конфигурацию 1С (scaffold XML-исходников). Используй когда нужно начать новую конфигурацию с нуля — from Arman-Kudaibergenov/1c-ai-development-kit
Создать новую конфигурацию 1С с нуля — scaffold + объекты + подсистемы + роли + формы. Workflow: cf-init → meta-compile×N → subsystem-compile → role-compile → form-add → — from…
Валидация конфигурации 1С. Используй после создания или модификации конфигурации для проверки корректности — from Nikolay-Shirokov/cc-1c-skills
Заимствование объектов из конфигурации 1С в расширение (CFE). Используй когда нужно перехватить метод, изменить форму или добавить реквизит к существующему объекту конфиг — from…
Анализ расширения конфигурации 1С (CFE) — состав, заимствованные объекты, перехватчики, проверка переноса.
Полный цикл создания расширения конфигурации 1С (CFE) — от scaffold до валидации. Workflow: cfe-init → borrow → patch → form → validate. — from msrv-tech/skills
Создать расширение конфигурации 1С (CFE) — scaffold XML-исходников. Используй когда нужно создать новое расширение для исправления, доработки или дополнения конфигурации — from…
Генерация перехватчика метода в расширении 1С (CFE). Используй когда нужно перехватить метод заимствованного объекта — вставить код до, после или вместо оригинального — from…
Валидация расширения конфигурации 1С (CFE). Используй после создания или модификации расширения для проверки корректности — from Nikolay-Shirokov/cc-1c-skills
설정 파일 검증 스킬. YAML 구문, Pydantic 스키마 준수, 환경별 일관성을 검사한다. convention-config 스킬의 규칙을 기반으로 검증을 수행한다.
Use when analyzing a ticket for ambiguities, missing information, or unclear acceptance criteria. Use when user says 'clarify ticket', 'review ticket', 'analyze ticket', or passes…
Time-bounded autonomous Claude Code orchestration agent. Accepts user-defined directives (prompts) and a deadline, then executes tasks autonomously until the specified time.
Claude Code learning — configure and optimize Claude Code settings, tips, and workflows. Triggers: learn, setup, claude code, optimize, 학습, 설정, 최적화.
Установка и обновление рабочего окружения агента: скилы, правила и команды этого набора плюс связанные инструменты (MCP-серверы, плагин EDT, локальная транскрибация, конвертеры…
Bridge THIS Claude Code or Codex session to Telegram, Discord, Feishu/Lark, QQ, or WeChat so the user can chat with Claude from their phone.
Use when asked to clean up stuck loops, kill dead loop processes, or troubleshoot loop state.