Use when designing or reviewing filesystem MCP access, path boundaries, allowed roots, method allowlists, and safe local file operations.
Identify, measure, and exclude bot / crawler / AI-agent traffic in PostHog web and product analytics using the traffic classification surface (the isLikelyBot / getTrafficType…
Build filtering query builder operations. Auto-activating skill for API Development. Triggers on: filtering query builder, filtering query builder Part of the API Development…
Finalize prompt file using the role of an AI agent to polish the prompt for the end user. — from general/ai-tooling
Finalize prompt file using the role of an AI agent to polish the prompt for the end user. — from majiayu000/claude-skill-registry
Comprehensive personal finance management system for analyzing transaction data, generating insights, creating visualizations, and providing actionable financial recommen — from…
Performs financial ratio analysis, DCF valuation, budget variance analysis, and rolling forecast construction for strategic decision-making — from majiayu000/claude-skill-registry
Determines whether to fine-tune vs. prompt-engineer, and if fine-tuning is justified, produces dataset requirements, training data format, pre/post eval plan, and cost-benefit…
Use when fine-tuning LLMs, training custom models, or optimizing model performance for specific tasks.
Use when fine-tuning LLMs, training custom models, or optimizing model performance for specific tasks.
Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training — from…
Claim the next safe agent-ready issue from Linear, implement it, and open a PR. Use when asked to run Finn-loop's builder, work the approved queue, or fix Finn-loop review…
FIPA standard for agent platform management including lifecycle, directory, and communication services
FIPA standard library of agent interaction protocols for structured multi-agent communication
FIPA standard library of communicative acts (speech acts) for agent-to-agent messaging semantics
Deep web scraping, screenshots, PDF parsing, and website crawling using Firecrawl API — from majiayu000/claude-skill-registry
Scrape web pages to clean markdown using Firecrawl v2 — handles JS-heavy pages, site crawls, URL mapping, document parsing (PDF/DOCX/XLSX), LLM-powered extraction, autonomous…
Multi-agent task orchestration pack. DAG-based parallel task execution and team status monitoring. 2 orchestration tools.
Pyramid multi-agent orchestration for OpenClaw: routes objectives from a CEO agent down through departments, services and employees via sessions_send / sessions_spawn, collects…
Use before the five-agent-dev-team Captain Integrator merges, rebases, labels ready-to-merge, pushes main, or advances main build state.
Use when a five-agent-dev-team automation opens, updates, labels, or hands off a pull request.
Use before any five-agent-dev-team automation mutates files, opens PRs, updates branches, or performs Captain integration.
Use when updating five-agent-dev-team swarm state, ledger entries, blockers, or next-stage handoffs.
把一件要办的事按"五句话说清楚"补全成任务简报式提示词:我要做什么/给谁用/解决什么问题/基于什么资料/交付成什么样。全程零猜测——已说的按原文归位,没说的槽位出选择题问(末项"其他"可自由填写),明确跳过的槽位整行省略、绝不代填;最后按五行骨架纯拼装(跳过的行省略),零扩写零编造,并追加"直接执行/到此为止"交付选择。凡用户要布置一件任务、描述一个想做的项…
Sistema multi-agente especializado en renta fija global. ACTÍVALO ante cualquier mención de: bonos, TES, yield curve, curva de rendimientos, tasas de interés, duración,…
Local evidence retrieval (FlashRAG-style) for VCO/vibe: search protocols/config/skills docs and return citeable snippets with file+line anchors.
Use when creating, editing, inspecting, exporting, or troubleshooting Flato designs through Flato Design MCP tools such as flato_whoami, flato_get_design_context,…
Provision a remote Hermes agent with the Appie Kit (skills, workspace, SOUL.md preservation, knowledge doc transfer, and verification).
Decompose a large task into DISJOINT file-owned workstreams, fan out isolated full-power peers, collect structured reports, run ONE authoritative gate, and commit when green — the…
Flink Job Creator - Auto-activating skill for Data Pipelines. Triggers on: flink job creator, flink job creator Part of the Data Pipelines skill category.
Flottenleasing: Schadenmanagement, Minderwertabrechnung, Gutachtenprozess, Flottenvertrag-Besonderheiten und Regressprozesse im Leasingrecht.
Use when Claude Code needs to operate Flovart as an agent-native media runtime. Flovart generates and manages images/videos through deterministic CLI commands.
Orchestrate SDLC phase gate validation with multi-agent review and comprehensive reporting
Cách lái SEOSONA Flow (gen ẢNH/VIDEO/b-roll) qua Local MCP server (mcp-local/) — cho agent HOẶC SEOSONA Video AI V2 gọi.
Synthesize the current conversation context into a flow-next epic spec at `.flow/specs/.md` via `flowctl epic create + epic set-plan` — agent-native, source-tagged, with…
Image generation via flow_router OpenAI-shape /v1/images endpoint. Routes to active media providers (OpenAI, Stability, BFL, Gemini, etc.).
Guard long, ambiguous, or stateful AI-agent work from drift. Use when the user asks to run or continue a multi-step task, autonomous loop, bug fix, repo change, PR readiness…
Flowise visual LLM workflow builder — drag-drop chatflows, API endpoints, document loaders, tools. Use when working with flowise builder.
Configura e usa o flutter-mcp-toolkit no NixOS via Nix flakes sem instalação manual. Use quando precisar conectar um LLM a um app Flutter em modo debug no NixOS — inspecionar UI,…
F-MCP ile ilgili herhangi bir kullanıcı talebinin ilk giriş noktası. Kullanıcının niyetini analiz eder, hangi hedef SKILL'in çalıştırılacağına karar verir, o SKILL için gereken…
Invoke FORCE_MANAGER for task force assembly and team composition decisions. Use when complex tasks require coordinated multi-agent teams with proper staffing and lifecycle…
Forderung aus Werk-/Bauvertrag: Faelligkeit § 641 BGB, Abnahme/Abnahmewirkungen, Schlussrechnungspruefung, Sicherungseinbehalt, Maengelrechte als Einwendung.
Werklohnforderung § 631, § 641 BGB: Faelligkeit nach Abnahme, Schlussrechnung. Bauvertrag §§ 650a ff. BGB (seit 2018), VOB/B als AGB.
Forensische Prüfung Prompt-Injection-Risiko: Indirekte Prompt-Injection ueber hochgeladene Dokumente, RAG-Vergiftung, Datenexfiltration.
Forensische Pruefung Prompt-Injection-Risiko: Indirekte Prompt-Injection ueber hochgeladene Dokumente, RAG-Vergiftung, Datenexfiltration.
Writing self-contained subagent briefs. Four-part structure (goal, context, constraints, return shape), token budgets, autonomy bounds, hand-the-question vs hand-the-command,…
Structured completion-report contract for every dispatched Boss, validated by forge-report.cjs. Use when dispatching a subagent or ingesting its final report — completion…
Detects a dispatched agent gone silent mid-run from events.jsonl. Use during multi-agent runs or when a run feels quiet — silent agent, stalled run, heartbeat check, timeout.
Forge doctrine for using MCP servers as a client — opt-in, tiered, least-privilege. Use when a Boss needs an external tool grant or when installing/discussing an MCP server.
Exposing resources via MCP. URI scheme design, listing strategies, mimeType discipline, ranged reads, mutable resources via subscribe, when resources beat tools, multi-tenant…
Designing an MCP server LLM agents actually use well. Transport choice (stdio vs HTTP streaming), capability scoping, structured error responses the model can recover from, tool…
Designing individual MCP tools that LLMs use correctly on the first try. Naming, descriptions written for model consumption, JSON Schema discipline, error returns that the model…
Meta-guide for Forge's per-project pipeline skills: what Forge does with a skill at runtime, and the standard for authoring / customizing / shadowing one correctly and cheaply.
Evaluating subagent outputs before trusting them. Shape and budget validation, refusal handling, partial-result recovery, hallucination defenses (URL/quote/file verification),…
Form-Checker für Verträge und Willenserklärungen: Entscheidungsbaum — welche Form ist gesetzlich oder vertraglich vorgeschrieben, Konsequenzen bei Verstoß, empfohlene Formwahl,…
Formik form handling with validation patterns. Use when building forms, implementing validation, or handling form submission. — from majiayu000/claude-skill-registry
Branchen-Fachmodul für Formulararbeitsvertrag: prüft typische AGB-Risiken des Vertragstyps und erzeugt Klauselarchitektur, Red Flags und bessere Bedingungen im AGB-Recht.
Multi-agent framework — assign roles (PM, architect, engineer) cho GPT team, build software từ 1 requirement. Dùng khi cần orchestrate multi-agent pipeline phức tạp.
Ongoing development guidance for agentic web apps that pair a CopilotKit frontend with Microsoft Agent Framework agents on Azure AI Foundry hosted agents over the AG-UI protocol -…
Prüft Frachtvertrag, Frachtbrief, Haftung, Verlust/Beschädigung, Lieferfrist und Haftungsgrenzen. — from Klotzkette/claude-fuer-deutsches-recht