Şirket içi kayıt/delil muhafaza talimatı yayımlar, yeniler, kaldırır veya raporlar — .docx formatında iç bildirim taslağı hazırlar, _log.yaml'deki legal_hold alanlarını günceller…
Generate a response to a common legal inquiry using configured templates, with built-in escalation checks for situations that shouldn't use a templated reply.
Revisar um contrato contra o playbook de negociação da organização — sinalizar desvios, gerar redlines e fornecer análise de impacto de negócios.
Preparar e encaminhar um documento para assinatura eletrônica — executar checklist pré-assinatura, configurar ordem de assinatura e enviar para execução.
Triagem rápida de um NDA recebido e classificação como VERDE (aprovação padrão), AMARELO (revisão de assessoria) ou VERMELHO (revisão jurídica completa).
Verificar o status dos acordos existentes com um fornecedor em todos os sistemas conectados — int-evo-crm, Gmail, Notion e arquivos locais — com análise de lacunas e prazos…
특정 콘텐츠를 현재 L-레벨에서 목표 L-레벨로 올리기 위한 구체적인 작업 목록을 생성한다. 사용법: /level-up <콘텐츠명> <현재레벨> <목표레벨> [server|client|both]
Audits package dependency licenses using the Very Good CLI packages_check_licenses MCP tool. Flags non-compliant or unknown licenses and produces a compliance summary.
Complete Lightning Network lifecycle. Audits channels, routing, invoices. Plans capacity, executes rebalancing, verifies payments. Every run does all.
Полный цикл разработки фичи с последующей проверкой и дискуссией для повышения качества за счёт коллаборативной работы нескольких агентов.
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma.
Валидация ссылок между markdown-документами — проверка frontmatter-полей, якорных ссылок и путей. Используй после рефакторинга, переименования файлов или перед коммитом.
Submit AI agents to 35+ registries, directories, and community platforms for maximum discoverability.
Surfaces hidden design assumptions baked into the codebase before planning — pattern-based detection plus user-surfaced items.
Submit company profiles to 50+ online directories, business listings, and platforms for maximum visibility, off-page SEO boost, and brand authority.
List or search deal pipelines in live Sanka. Use when the user explicitly invokes /sanka:list-deal-pipelines.
List or search export jobs in live Sanka. Use when the user explicitly invokes /sanka:list-export-jobs.
Submit MCP (Model Context Protocol) servers to 50+ directories, registries, and marketplaces for maximum discoverability.
List or search orders in live Sanka. Use when the user explicitly invokes /sanka:list-orders.
List mise tasks grouped by namespace with dependency info. TRIGGERS - mise tasks, task list, show tasks, available tasks.
Submit SaaS products and AI products to 50+ online directories, review platforms, and marketplaces for maximum organic reach.
Поиск по всей документации проекта — инструкции, скиллы, агенты, правила, README и скрипты. Используй при поиске документов по ключевым словам, для навигации по проекту или перед…
Submit Claude Code skills, plugins, and slash commands to 30+ directories, registries, and communities for maximum discoverability.
List or search slips in live Sanka. Use when the user explicitly invokes /sanka:list-slips.
Submit tools to 50+ online directories, marketplaces, and listing platforms for maximum organic reach.
Complete guide for using the List and ListItem components. Covers all use cases—chat lists, settings menus, context menus, file managers, notifications, active states, dense mode,…
Génère une issues list (liste de points à négocier) à partir d'une analyse de contrat. Appelable directement OU comme composant interne par reviser-contrat / gap-review.
Use this skill when surfacing Claude's assumptions about a phase approach before planning, checking what Claude thinks, or validating understanding before planning.
Launch or resume Living Docs Builder independently. Generates comprehensive enterprise documentation from codebase analysis with AI-powered insights.
**DEFAULT for LLM/agent eval design — dispatches evaluator for AI/LLM-specific evaluation design (offline + online metrics, groundedness, hallucination, drift, cost, latency).**
Evaluate LLM models for cost/performance ratio. Fetches current pricing and recommends optimal model for your use case. Use during project init or when optimizing costs.
CI hook that refuses to ship if prompt-eval golden set regresses past threshold or prompt-injection-test fails on HIGH severity
Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements.
Run browser or terminal automation scenarios with video recording from natural language flow descriptions.
Generate an llms.txt file for any project or website following the llmstxt.org specification. Use when asked to create llms.txt, generate LLM-friendly documentation, make a…
Ingest new sources into the LLM Wiki. Reads unprocessed files from raw/, docs/, and notes/, creates source summaries, updates entity/concept pages, maintains cross-references, and…
Search the LLM Wiki using qmd (hybrid BM25/vector search). Finds relevant wiki pages, reads them, and synthesizes an answer with citations.
Capture volatile session state into a structured handoff document before context is lost. Use when ending a session, switching threads, approaching context limits, or at any…
Session lifecycle management with Serena MCP integration for project context loading
Log a technical insight to docs/insights-log.md immediately. Do not defer — sessions can clear. TRIGGER when the user says \"log this insight\", \"that's worth noting\",…
Neue Abwesenheit oder neuen Urlaubseintrag im Register anlegen – mit allen für die Fristenberechnung nach BUrlG, EFZG, MuSchG und BEEG notwendigen Informationen.
One-shot scaffold dropping in a structured logger for the project's primary backend language; wires JSON output, sensible defaults, example call sites
Analyse du régime juridique d'un logiciel sous droit d'auteur français (CPI Livre I + régime spécifique L.113-9) restructurée en V2 : titularité initiale, droits d'utilisation,…
CTA login attribution implementation skill for Django4Lyfe: guides adding new CTA sources, button/tab attribution, enum registration, and tests.
View token refresh logs. Triggered by "logs", "refresh history", "401 error", "token logs".
Show the current project status for the Claude long-running harness by reading progress, features, active feature, evidence, and git state.
Multi-year health-mcp pattern surface. Scans years of HealthKit + journal data, returns ONLY the strongest correlations (Briden noise filter).
Use when the user asks about ANY chargeback, dispute, reason code, payment dispute, or mentions Visa/Mastercard/Amex/Discover/ACH codes — even casually.
List all available help topics, optionally filtered by tag. Use to browse what's in the bundled templates or the project's .help/ directory.
Extract a selected code block into a named function. Primary path uses the language server's extract-function code action; falls back to manual extraction when no code action is…
Manage Magento order fulfillment documents via admin REST API. Covers invoices (search, get, create), shipments (search, get, create), credit memos, order email, and returns/RMA.
Reviews code changes through the MAGI council by reading the git diff (staged changes, or the latest commit as fallback) and composing a review topic.
Pure-filesystem inter-agent mailbox so any agent session can send a handoff document to another and pick up replies.
Transform text into Mainland China Mandarin （中國大陸普通話） — the everyday spoken and media register of the People's Republic of China.
Performs periodic cleanup — session log pruning, stale state files, orphaned worktrees, cache purge, trace archival. Use when performing routine housekeeping.
This skill should be used when the user asks to "create a changelog", "generate a changelog", "update my changelog", "fill in the changelog", "add a changelog", "CHANGELOG is…
This skill should be used when the user asks to "make a GIF", "convert to GIF", "create a GIF from this video", "export as GIF", "turn this clip into a GIF", "make an animated…
This skill should be used when the user asks to "create a README", "generate a README", "make a readme", "write a README for my project", "need a README", "add a README",…
根据 Maker App ID 拉取该应用的 chat 列表，并生成可直接打开的 maker/fuping URL 表格。当用户提供 Maker App ID（UUID 形式，如 99b00f3e-e64a-455a-b000-9ec2c95297d7）并想查看该应用下所有 chat 会话、复盘历史对话、获取带 bypassAuth…
Consult or define Critical Data Elements (CDEs) for a governed domain. Flow A: view current CDEs. Flow B: tag tables/columns as critical — manually, by agent recommendation, or…