Engenharia reversa de specs para sistemas legados. Use quando precisar extrair specs executaveis, regras de negocio, contratos de modulo, fluxos e ADRs retroativos a partir de…
Automatyczny pipeline: execute->review->fix per faza, potem complete i compound. Uzywaj przy 'uruchom autopilot', 'wykonaj caly plan', 'autopilot', 'odpal pipeline'.
Direct manual utility command reference for UI implementation workflows, including design feedback, QA checklist, screen-map updates, checks, scaffolding, and install commands.
Запуск разработки по analysis chain — prerequisite check, создание Issues/Milestone/Branch, переход WAITING → RUNNING.
Use when adding a new UI component to an existing module - handles templates, inputs, and test scaffolding.
Use when adding server state management or shared logic - creates an auto-imported composable with useFetch/useAsyncData.
Use when adding a signal-based store or utility service - creates injectable with inject() and Angular Signals.
Use when creating a new feature module with all layers - service, adapter, types, state, components, and tests.
Use when adding API integration to a module - creates types, contracts, adapter, and service layer.
Use when a module needs test coverage - creates tests for adapters, services, and components.
Tworzenie kompleksowego planu strategicznego z uporządkowanym podziałem na zadania.
Profile a tech company or developer's engineering culture from public sources and generate a develop-like- skill that makes the agent work the way they do.
Resume work from a previous session checkpoint. Uses `resume-context` CLI to load feature, checkpoint, git state, and session history in a single call, then synthesizes a focused…
Generate dev server lifecycle scripts (start/stop/status/ports) from detected project structure
[UDS] Guide for mapping software development phases to UDS commands and features
Review implemented code for quality, correctness, and style. Produces review comments and creates a commit. Sub-skill of the /dev workflow.
Create a PR, push to GitHub, wait for Greptile review, address comments, and push final. Sub-skill of the /dev workflow.
Review or outline a development agreement for obligations, triggers, public cost, and enforceability issues.
Oturumun devir notunu ("kaldığım yer") kasaya yazar; proje kartını, Kayıt.md'yi ve 01 Şimdi.md'yi günceller.
Creates a GitHub pull request with branch creation, commits, and detailed description. Use when you need to submit changes for review. — from tools-only/X-Skills
Diabetes management - blood glucose monitoring, HbA1c tracking, TIR analysis, hypoglycemia event logging, and complication screening
Use when an agent's performance is uneven and you want to understand where it excels or struggles. Produces a struggle profile for /challenge-gen or /active-learn.
Investigate unexpected behavior and mysterious bugs. Use when the cause of a problem is unknown and the user needs to understand WHY something is happening — symptoms like: sudden…
Routes a vague symptom or complaint to the most relevant Clairvoyance skill via a decision tree. Use when someone describes a problem but doesn't know which skill to reach for.
Deep autonomous diagnosis of a failed flow run. Provide environment, flow, and run IDs. Use when the user asks to diagnose or deeply investigate a specific failed flow run.
Run a staggered difference-in-differences / event-study analysis to the Sant'Anna practitioner standard — drives the canonical packages (R `did`/`DRDID`/`didFF`/`contdid`; Stata…
Record and track daily nutrition intake through food photos. Analyze nutritional content including calories, protein, fat, carbohydrates, vitamins, and minerals.
Builds a shareable HTML walkthrough of the current changes, highlighting risks, tradeoffs, and alternatives considered.
This skill should be used when the user asks to "compare files", "diff these files", "what changed between", "show differences between", "compare versions", or mentions keywords…
Use when deciding between two approaches and you need a structured tradeoff comparison. Produces a dimension-by-dimension table with a recommendation.
Analyze and edit Unreal Engine Blueprints via the digbp persistent server. Use when the user asks to inspect, export, search, understand, or MUTATE Blueprints — including editing…
Generate a daily or weekly digest of activity across all connected sources. Use when catching up after time away, starting the day and wanting a summary of mentions and action…
Build a rigorous world model with state, dynamics, uncertainty, and provenance. Use when creating digital twins, constructing system representations, building simulation…
Run the digital twin sync loop to synchronize real-world signals with a digital model. Use when updating digital twins, detecting drift, managing real-time state synchronization,…
Audit an existing codebase across independent quality areas, one reader each, and report findings the owner turns into orders.
Написание рекламных объявлений для Яндекс.Директ. Активируй когда пользователь просит написать, улучшить или проверить текст объявления, заголовки, или тексты для контекстной…
Specialist evaluation for direct-materials RFP responses — raw materials, components, packaging materials.
Non-negotiable architectural rules governing the jadecli ecosystem. Violations fail the build. Derived from cert exam + playbook.
Einen Community-Skill, der über den Hub installiert wurde, ohne Dateilöschung deaktivieren. Einsetzen, wenn der Nutzer einen Community-Skill vorübergehend stilllegen möch — from…
Save and structure discharge summary information. Extract from images or process text descriptions of hospital discharge records including diagnosis, treatment, and follow-up…
Use when: formalizing, routing, validating, promoting, or retiring an Arcanum discipline so a recurring cross-capability practice gets a card, catalog entry, and a hardening route…
Works out which documents you have to hand over to the other side in a civil case in England & Wales, and builds the formal list.
披露管理 — 从 [ERP] 监控应披露事项，核查是否及时披露，完成 [DIS] 披露。 适用情形：关联交易/担保/借款等应披露事项监控时执行， 从 [ERP] 获取数据，判断披露阈值，跟踪披露状态，输出披露管理报告。 核心：事项识别 + 阈值判断 + 披露跟踪 + 合规确认。
Claude Gateway Discord 환경에서 파일을 Discord 채널로 첨부 업로드합니다. 응답에 FILE: /절대경로/파일명 형식으로 파일 경로를 포함하면 게이트웨이가 자동으로 감지하여 Discord로 전송합니다.
Expand a ticket by linking or creating children for subsystems found in findings
Adaptive design interview — spawns design-discussant to gather decisions via one-question-at-a-time questioning. Writes D-XX decisions to STATE.md block.
Use this skill when gathering phase context through adaptive questioning before planning, clarifying implementation decisions, or exploring gray areas for a phase.
Создание документа дискуссии SDD с Clarify, генерацией разделов и валидацией. Используй при вызове пользователем "новой дискуссии", запуске нового "воркфлоу" и т.д.
Изменение документа дискуссии SDD — обновление контента, разрешение маркеров, принятие предложений, перевод DRAFT в WAITING. Используй при изменении существующей дискуссии.
Проверка документа дискуссии на соответствие стандарту SDD — frontmatter, именование, секции, нумерация, маркеры, зона ответственности.
Mega-skill de diseño frontend que combina lo mejor de 22 skills de diseño en una sola. Crea interfaces distintivas, production-grade con tipografía excepcional, color estratégico,…
Spawn a generic Agent wearing a project-specific agent's discipline (workaround for v0.1 runtime not discovering project agents)
Dispatches a long-running task to a maxv-* subagent in background via Claude Code's Agent View (`claude --bg`).
Step 8 of the forge workflow when the approved plan has ≥ 2 steps marked `Parallel-friendly: yes`. Dispatches one `forge-implementer` subagent per such step, each in an isolated…
Spawn and coordinate a pre-composed agent team from a team definition file. Reads team files from teams/, resolves agents and skills, picks the best spawning mode (peer or…
Produce display creative specs for Google Ads responsive display and Performance Max — image/aspect specs and a designer brief.
报销异常识别 — 在报销审核流程中主动识别高频异常模式和潜在风险。 适用情形：reimbursement-review 的各原子 Skill 执行后， 综合分析各节点输出，识别跨节点异常模式和潜在风险。 核心：不是替代其他 Skill，而是在其他 Skill 输出基础上做二次风险扫描。
Propose who on the team takes which SOBER node, by matching each contributor's role and focus against the board.
Build a dive end-to-end — dbt marts SQL + manifest + TSX component + DivesPage registration + rows in the shared verifications seed + methodology content wired into the dive…
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop