Каталог навыков агентов

Few-Shot Learning（少数例示学習）のパターンとベストプラクティスを提供するスキル。効果的な例示の設計、構造化、配置により、AIの出力品質を大幅に向上させます。 • The Pragmatic Programmer / 適用...

Use this skill when tool outputs exceed 2000 tokens, tasks span multiple conversation turns, sub-agents need to share st...

理查德·费曼的思维框架与表达方式。基于40+个一手来源的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用费曼的视角分析问题、审视决策、提供反馈。 当用户提到「用费曼的视角」「费曼会怎么看」「费曼模...

MANDATORY: Always Use Backslashes on Windows for File Paths

Operate FFT_nano coding delegation flows safely using /coder and /coder-plan, preserving main-chat-only policy, request-...

Optimización evolutiva y paramétrica basada en Fibonacci y el Número Áureo (phi).

Archive and retrieve field session data for cross-session memory continuity.

FiftyOne dataset visualization and curation tool via Podman Quadlet. Multi-container architecture with MongoDB sidecar f...

Manage filesystem context for offloading large context to files, persisting state between sessions, and reducing token u...

This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use...

Passthrough filter agent. Calls data sub-agents, validates responses, returns only clean data.

Finalize prompt file using the role of an AI agent to polish the prompt for the end user.

ML-driven financial analysis patterns. Price prediction models, portfolio optimization, risk metrics, technical indicato...

Build a grounded, verified long-horizon financial plan for a person - accumulation, financial-independence timing, drawd...

Klage vor dem Finanzgericht nach der FGO – Klagearten §§ 40, 41 FGO, Vorverfahren § 44, Sprungklage § 45, Untätigkeitskl...

Retrieves up-to-date documentation, API references, and code examples for any developer technology. Use this skill whene...

Journal recommendation engine for medical manuscripts. 2-pass matching against a curated public profile library plus any...

Discovers existing skills or creates new ones when the user asks for capabilities that don't exist.

Find and install skills from the Orthogonal skill library. Use when you need capabilities you don't have, want to discov...

ClaWHub skill discovery: search by capability, category, rating, compatibility, keyword matching

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is th...

Helps users discover and install capabilities from the open agent skills ecosystem. Use when users ask "how do I do X" f...

当用户提出诸如“我如何做X”、“为X找到技能”、“是否有可以……的技能”或表示有兴趣扩展功能等问题时，帮助他们发现并安装代理技能。当用户正在寻找可能作为可安装技能存在的功能时，应使用此技能。

Use when the user asks how to do something, wants a skill for a task, or wants to discover and install new agent capabil...

Search and discover available skills in the system.

Discover and install agent skills from the open skills ecosystem. Use when user asks "how do I do X", "find a skill for"...

Discover and recommend **combinations** of agent skills to complete complex, multi-faceted tasks. Provides two recommend...

Find fine-tuned model references and check base model deprecation status. Trigger: /finetune-deps

Fine-tuning pre-trained machine learning models for specific tasks using transfer learning techniques.

Training and tuning LLMs — Unsloth LoRA/QLoRA/full fine-tuning, GRPO reinforcement learning, VRAM sizing, hyperparameter...

LLM fine-tuning with LoRA, QLoRA, DPO alignment, and synthetic data generation. Efficient training, preference learning,...

Use when fine-tuning LLMs, training custom models, or optimizing model performance for specific tasks. Invoke for parame...

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B)...

Generates code that fine-tunes a base model using SageMaker serverless training jobs. Use when the user says "start trai...

Selects a fine-tuning technique (SFT, DPO, RLVR, or RLAIF) for the user's use case and validates it against the selected...

The terminal step of /feature and /sprint. Routed to once commit-gate has cleared, to decide the branch's fate — merge v...

Find the papers that answer a research query with Firecrawl Research, using semantic search, semantic and structural exp...

Compares fixed fee, time and materials, retainer, value-based and fixed-term handover for one piece of work, with what t...

Generate AI audio and synthesize voices with Fish Audio via AceDataCloud API. Use when creating text-to-speech audio, sy...

Host Fish Audio's open-weights voice models (Drama 3 and S2 Pro) on a serverless GPU (Modal, or fal) behind one small HT...

Design a model training pipeline — algorithm selection, cross-validation, and serialization. Use when asked to "train a...

Design a hyperparameter tuning strategy for a model — search space, method, and budget. Use when asked to "tune hyperpar...

Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit base...

Thoroughly address ALL PR comments using parallel Opus subagents. Each subagent invokes /task skill.

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/run...

This prompt instructs an AI image generator to produce a high-resolution, vertically framed, realistic fashion selfie th...

The Broomva fleet: every Claude Code and Paseo session, PR and loop the coordinators drive, and the workflows that manag...

How the architect creates Architecture Decision Records — capturing the context, options, and rationale behind design de...

Post structured, formatted task comments to Mission Control. Use for acceptance, progress, completion, and blocker updat...

Manage Letta AI agent fleets declaratively with kubectl-style CLI. Use when creating, updating, or managing multiple Let...

Use when the user asks to check on agents, manage their fleet, babysit panes, see what needs attention, get a status rep...

Parallel agent fleet dispatch with progress tracking and result aggregation. Launch N agents, monitor completion, merge...

Run a medium or large request on the main thread: parallel research, interview, build in slices, oracle review. Use befo...

Intelligent skill orchestrator that compiles natural language requests into secure, reusable workflows

Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus

Optimise a learning activity for flow by balancing challenge level, skill, clear goals, and immediate feedback. Use when...

Generate flowcharts from YAML/JSON definitions or Python DSL. Supports standard flowchart shapes, swimlanes, and PNG/SVG...

MUST USE whenever writing, revising, or reviewing Korean text, or when replying to a user in Korean. Produces clear and...

Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations includi...

Build reliable Flutter apps avoiding state loss, widget rebuild traps, and async pitfalls.

Use when a FLUX 3 video must be built from supplied images or video. Covers keyframes (i2v) and continuation (v2v).

Generate and edit images with Flux (Black Forest Labs) via AceDataCloud API. Use when creating images from text prompts,...

Generate images with FLUX models (Black Forest Labs) via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA with...

FLUX.2 Pro gorsel uretimi. Use when generating AI images for posts.

Security rules and behavioral guidelines for operating as Clawdstein in The Agent Flywheel Hub Discord server. This is a...

Convert a diffusion training plan into a flow-matching / rectified-flow config. Use when you need help with fm tuner.

Layer 5: Convergence to Equilibrium Analysis

Ask one hard interviewer-style follow-up about the current coding-interview attempt, then wait for the user's answer. Us...

Evaluate whether changes need CLAUDE.md, rules, or skill updates

足踝外科 (foot and ankle surgery) Master OS — automated mastery of foot and ankle surgery: top builders' mental models, tool...

Eight effects for footage you already have, each as tested ffmpeg filter chains plus HyperFrames and Remotion equivalent...

Zero-shot univariate time series forecasting using the Reverso foundation model (NumPy/Numba CPU-only inference). Activa...

Use this command to start babysitting a never-ending babysitter run.

Shape, refine, and stabilize human intent into a canonical prompt artifact without executing anything. Iteratively clari...

Create a persistent expert agent file. Use when "create an agent", "make an agent", "design an agent", "forge an agent",...

Manage dotforge v3 behavior governance — view status, toggle behaviors, adjust strictness. Use when the user asks about...

Use when context degrades (context vol, vergeet instructies) or before /compact.

Show all available Product Forge agents, skills, and commands

Use when recalling earlier work or a lesson (hoe deden we X eerder).

Reference definitions for the Agent Forge orchestration roles (lead, worker, planner, evaluator). Use when coordinating...

Regenerates FORGE_SNAPSHOT.md from real project sources so no session loses the mission across compaction. Use on /forge...

Branch off a conversation to handle tangents. Outputs context summary and ready-to-paste command for a new terminal sess...

Fork terminal with git worktree isolation for parallel development. Use when user says 'fork feature', 'parallel work on...

Create an isolated copy of the current project for parallel feature development. Use when the user wants to work on a fe...

This skill allows the agent to transform any raw content, analysis result, or synthesis into a polished, audience-approp...

Review MCOS phase work for Forsetti/CLU compliance.

Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, a...

FounderOS coach skill, usable at any stage and never a gate. Offers a small set of named thinking tools when a founder i...

FounderOS stage 8 coach, traction and product/market fit. Helps a founder pick the One Metric That Matters with a dated...

FounderOS stage 9 coach, fundraising, and optional. Helps a founder decide whether to raise at all from their stage 7 an...

Microsoft Foundry agent deployment, orchestration, and cloud-native AI service patterns

Build agentic retrieval solutions with Azure AI Search knowledge bases and Foundry Agent Service using the Python SDK. U...

Build agentic retrieval pipelines using Azure AI Search knowledge bases with the Python SDK.

Build AI applications using the Azure AI Projects Python SDK (azure-ai-projects). Use when working with Foundry project...

Create one continuous scene-first FPV flythrough of a supplied architecture, interior, venue, landscape, vehicle, produc...

Fractal decomposition — recursively split a complex task into orthogonal sub-specs, solve each leaf independently via su...