Conçoit une stratégie d'upsell complète autour du produit principal : échelle de valeur (gratuit → premium), order bumps, upsells post-achat, downsells, cross-sells, séquences…
Veri işleme sözleşmesi, veri işleyen sözleşmesi, DPA veya kişisel veri aktarımı içeren tedarikçi/müşteri ekini Türk KVKK uygulamasına göre inceler.
Draft an offer letter with comp details and terms. Use when a candidate is ready for an offer, assembling a total comp package (base, equity, signing bonus), writing the offer…
Draft a professional customer-facing response tailored to the situation and relationship. Use when answering a product question, responding to an escalation or outage, delivering…
Проверка черновика в .claude/drafts/ на соответствие стандарту — frontmatter, структура, именование файла. Используй после создания или изменения черновика, перед коммитом.
Nightly memory consolidation — prunes stale entries, merges duplicates, resolves contradictions, rebuilds MEMORY.md index.
Управление вайб-код проектами. Протокол .drift/ для трекинга статуса, прогресса, заметок и целей по всем проектам.
Internal development tool that tests whether skill descriptions trigger correctly for different user inputs.
This skill should be used when the user asks to "compose DSPy modules", "use Ensemble optimizer", "combine multiple programs", "use dspy.MultiChainComparison", mentions "ensemble…
This skill should be used when the user asks to "bootstrap few-shot examples", "generate demonstrations", "use BootstrapFewShot", "optimize with limited data", "create training…
This skill should be used when the user asks to "evaluate a DSPy program", "test my DSPy module", "measure performance", "create evaluation metrics", "use answer_exact_match or…
This skill should be used when the user asks to "fine-tune a DSPy model", "distill a program into weights", "use BootstrapFinetune", "create a student model", "reduce inference…
This skill should be used when the user asks to "optimize an agent with GEPA", "use reflective optimization", "optimize ReAct agents", "provide feedback metrics", mentions "GEPA…
This skill should be used when the user asks to "integrate DSPy with Haystack", "optimize Haystack prompts using DSPy", "use DSPy to improve Haystack pipeline", mentions "Haystack…
This skill should be used when the user asks to "optimize a DSPy program", "use MIPROv2", "tune instructions and demos", "get best DSPy performance", "run Bayesian optimization",…
This skill should be used when the user asks to "refine DSPy outputs", "enforce constraints", "use dspy.Refine", "select best output", "use dspy.BestOfN", mentions "output…
This skill should be used when the user asks to "build a RAG pipeline", "create retrieval augmented generation", "use ColBERTv2 in DSPy", "set up a retriever in DSPy", mentions…
This skill should be used when the user asks to "create a DSPy signature", "define inputs and outputs", "design a signature", "use InputField or OutputField", "add type hints to…
Codebase-orientation session with the rubber duck — generate or refresh .claude/orientation.md with interactive exercises.
Уровень душноты (0-10) — насколько критично Claude челленджит твои решения. 0 = 'бро, делаем', 10 = полный душнила, ставит под сомнение всё. Алиас для /rigor на русском.
Calculate customs duties, taxes, MPF, HMF, and landed cost for imports using AskRosetta. Use when a user needs duty rates, tariff calculations, or total landed cost.
Validate Definition of Ready — fetch wiki checklist, evaluate story, post ADO comment. Use standalone at sprint start, in batch, or as part of /dx-req.
Initialize a hub directory for multi-repo orchestration. Discovers sibling repos, merges configs, validates CLI compatibility. Use when setting up hub mode for the first time.
Execute the next pending step — implement code, run tests, review against plan, and commit. Reads implement.md, finds the first pending step, implements it, tests, reviews,…
Autonomous execution loop — runs each plan step (implement + test + review + commit internally), with step-fix for failures.
Launch and stop Java applications in Eclipse. Run with program/VM arguments, capture stdout/stderr, or launch in background.
Migrate existing repositories to use Personal GitHub Ecosystem templates and patterns. USE THIS SKILL when user says "migrate to ecosystem", "adopt templates", "convert workflow",…
Run line-level editing across chapters. Catches spelling, grammar, awkward phrasing, and word echoes.
Edit Copilot Studio agent settings, instructions, or configuration. Use when the user asks to change agent instructions, display name, conversation starters, AI settings, or…
Top-level orchestrator: chains eeg-bids → eeg-preprocess → eeg-ica → eeg-epoch → (eeg-erp / eeg-tfr / eeg-connectivity / eeg-microstate / eeg-source) → eeg-stats → eeg-figure →…
Git知識ゼロでも使える全自動バージョン管理。 ユーザーはコマンドを知らない前提で、すべて提案→承認の形で進める。 Gitリポジトリでの作業中、またはGit環境がないプロジェクトで自動トリガー。 Triggers: git, セーブ, 保存, save, 合流, 完了, ブランチ, 作業場所, init, 環境構築, push, プッシュ, バージョン,…
Generates professional PDF documents using LaTeX with the Eifert Systems GmbH corporate template. Use when the user asks to create documents, reports, documentation, PDFs, or…
Generador de Evaluación de Impacto en Protección de Datos (EIPD) — genera una EIPD en el formato house configurado. Evalúa si es obligatoria según art.
Drive EL through a GENUINE runtime self-correction on real evidence and narrate it, for the Find Evil demo / "Interaction with EL" walkthrough.
Gerar os elementos pré-textuais de um projeto de pesquisa científica em português brasileiro: capa (folha de rosto), página de Informações Gerais (formato CEP/Plataforma Brasil),…
Dati elettorali siciliani da riga di comando — senza copiare tabelle HTML. Trigger phrases: `elezioni sicilia`, `risultati elezioni comunali sicilia`, `affluenza elettora — from…
Auto-review skill for expert agents. After coding, expert applies elicitation techniques to self-correct before sniper validation. Inspired by BMAD-METHOD.
Verify the Elsa codebase against selected constitution gates by inspecting references, extension-point catalogs, packages, tests, docs, stubs, and generated maps.
Write detailed embodiment descriptions for patent specifications. Use when user says \"撰写实施例\", \"write embodiment\", \"实施例描述\", \"detailed description\", or wants to describe how…
Map energy, focus, and mood across day & week from a 7-day log — surfaces what drains you, what restores you, and where to schedule the work that matters most.
Manage participant relationships - thank-yous, updates, re-engagement, and advocacy asks
工程控制论 (Engineering Cybernetics) 方法论——将控制论的系统辨识、目标分解、 前馈控制、执行-反馈回路、稳定性判定、收敛判定六阶段嵌入 agent 工作流， 使每次操作都形成可观测的闭环控制。 使用 "/engcyb <目标描述>" 手动调用。
Use when checking cross-file consistency: tools vs frontmatter, agent references, duplicate rules, contradictions.
Use when coordinating multiple enhancers for /enhance command. Runs analyzers in parallel and produces unified report.
Instant lead enrichment. Drop a name, company, LinkedIn URL, or email and get the full contact card with email, phone, title, company intel, and next actions.
Analyze TRD complexity and auto-configure team roles, agent assignments, and marketplace plugins (Codex skill for /ensemble:configure-team)
Analyze codebase and extract coding conventions into a standards/ directory with index.yml (Codex skill for /ensemble:discover-standards)
Implement a single beads task by ID through analysis, implementation, and PR creation (Codex skill for /ensemble:implement-bead)
Implement TRD with beads project management — persistent bead hierarchy, dependency-aware execution via br/bv, and cross-session resumability (Codex skill for…
Selectively inject relevant standards from standards/index.yml into agent context based on current task (Codex skill for /ensemble:inject-standards)
On-demand requirement satisfaction report — scans bead comments for req-verified tokens (Codex skill for /ensemble:requirement-status)
ICM workspace: Reference toolkit for quality gates, checklists, metrics, playbooks, and test examples. Non-sequential reference workspace — browse by topic, not pipeline stages.
Türk şirketler hukuku için tüzel kişi ve şirket kayıt takip skill'i. MERSİS, ticaret sicili, faaliyet belgesi, imza sirküleri, karar defterleri, pay defteri, VERBİS, vergi/SGK,…
Resolve entity ambiguity across data sources — produce canonical records, merge decisions, and sameAs link mappings for structured data
Map business domains to entity-relationship models with Schema.org types, JSON-LD @graph output, consistent @id structures, and sameAs connections
Ejecuta la entrevista inicial del hub constructor — aprende qué registros de skills comunitarios quieres vigilar, tus preferencias de instalación y tus criterios de calidad…
Questionamento socrático para clarificar requisitos de domínio regulado ANTES de pesquisar ou implementar.
Generate or refresh coverage manifest for a scanner — lists ALL items in scope so scans can track progress across sessions.
向 routes.json 添加环境监测（EnvironmentMonitoring）新观察点条目。使用时：新增 kite_station 观察点路线配置、适配新版本的环境监测任务、补全缺失的 MapPath / EnterMap 数据。会自动检测缺失任务，逐字段询问路线数据后写入 ROUTE_CONFIG。
Изтегля документацията на конкретна поръчка от eop.bg, анализира изискванията и подготвя структуриран анализ. Използва се след избор на поръчка от eop-scan.