Каталог навыков агентов

Internal implementation skill invoked by /add-native for camera, image picker, barcode scanner, QR scanner, and camera/g...

Adds Dataverse tables to a Power Apps code app with generated TypeScript models and services. Can also create new Datave...

Internal implementation skill invoked by /add-native for app-generated PDF report workflows using expo-print and, when p...

Add phase to end of current milestone in roadmap

Add burned-in subtitles to a video the user uploads or points to on disk. Use when the user provides a local video file...

Add a properly formatted TODO item to TODOS.md. Use when you need to capture a new task, bug, or feature request during...

Add a todo item to track tasks

Create an automation workflow trigger that fires on entity events (lead created, deal stage changed, etc.) and executes...

Adds Work IQ (M365 Copilot Search) to a Power Apps code app via the Work IQ Copilot MCP connector (shared_a365copilotcha...

Support ADHD-style working memory, initiation, and attention patterns with external scaffolding and task design.

Time-blind friendly planning, executive function support, and daily structure for ADHD brains. Specializes in realistic...

Use when writing, restructuring, or reviewing technical documentation for lower working-memory demand. Apply ASD-STE100-...

Manually spawn a one-off teammate after listing available models and proposing the best provider, model, and thinking le...

Use when a task involves organizing in-silico ADMET screening results for a compound set with provenance and uncertainty...

Documenta ou organiza um processo/fluxo de trabalho interno da Creative Marketing em checklist ou passo a passo. Habilid...

Use when committing, pushing, creating PR, and resolving Azure DevOps ticket in one workflow. Also use when creating a n...

Use when starting work on an Azure DevOps ticket. Triggers on "start ticket", "work on ticket", ticket number with imple...

Use when working with Adobe Illustrator files, .ai brand assets, artboards, layers, vector exports, SVG/PDF/PNG renderin...

Brownfield audit — do existing artifacts actually work? Numbered migration plan. Unlike /project-stage-detect, checks co...

Builds one card for one AI task with five fixed fields (when to use AI, what to give it, what to check, what never goes...

Scaffold an architecture decision record in architecture/decisions/ using the repo's governed ID conventions. Use when a...

Use when the user asks to place an adsorbate molecule on a surface, find adsorption sites, or set up a surface+adsorbate...

Dispatch an independent, skeptical agent to re-derive whether a fix/claim/artifact actually worked, instead of trusting...

Interactive conversational guidance - user implements with step-by-step advice. Use when you want hands-on implementatio...

Navigate GitHub repositories, pull requests, issues, and settings through AetherBrowser tentacle routing. Use when tasks...

Operate AetherBrowser as the primary online task surface across search, GitHub, Codespaces, research, Notion, Hugging Fa...

Navigate Shopify admin and storefront pages through AetherBrowser for merchandising and operations tasks. Use when worki...

Create, update, or query Linear issues for project tracking. Use when creating new issues, updating issue status, managi...

Manage Linear issues for project tracking including creation, updates, and queries. Use when creating new issues, updati...

Manage work state, Linear issues, and task context across session boundaries. Use when updating current-task.md, trackin...

Recover work context after session restart, context compaction, or unexpected interruption. Use when resuming work, rest...

Use when setting up new AgentFlow projects or installing modules after Discovery. Covers minimal setup (always the same)...

Start work on a Linear issue by creating current-task.md and setting up context. Use when beginning a new task, initiali...

Start work on a Linear issue by creating current-task.md and setting up the work context. Use when beginning a new task,...

Use when managing work state, Linear issues, task context, or recovering from session/compaction boundaries. Covers curr...

Use when asked to set up AI agent templates with coordinator mode, implement persistent agent memory, compress context f...

Autonomous pipeline manager that orchestrates the entire development workflow. You are the leader of this process.

Use when designing an AI-native product, feature, or workflow where humans and AI agents share the work, to decide who d...

Expert financial analyst and controller specializing in financial planning, budget management, and business performance...

Expert in Git workflows, branching strategies, and version control best practices including conventional commits, rebasi...

Expert Model Context Protocol developer who designs, builds, and tests MCP servers that extend AI agent capabilities wit...

Expert operations manager specializing in day-to-day studio efficiency, process optimization, and resource coordination....

Expert process improvement specialist focused on analyzing, optimizing, and automating workflows across all business fun...

Agent skill for agent - invoke with $agent-agent

Design agent loops: planning, tool use, subagents, memory, RAG, evals, budgets. Use when building LLM features or multi-...

Expert en AudioCraft avancé (MusicGen text-to-music, AudioGen text-to-sound, fine-tuning)

科研自动化与长期记忆子 skill。用于把 AutoSci/OmegaWiki 的论文摄入、知识库、idea 生成、novelty 检查、实验设计、失败经验、论文计划、review/rebuttal、可视化和进化记录流程转化为本地 Code...

停止等待提示词，持续自主工作

Browser automation CLI for AI agents. Requires Node.js with agent-browser. Use when the user needs to interact with webs...

Use when a task involves automating an explicitly scoped browser task with a configured agent-browser tool or equivalent...

Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflo...

Operate an agent-browser CLI for auditable navigation, extraction, screenshots, and UI checks.

Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and networ...

Automates real browser interactions: navigating websites, clicking buttons, filling forms, taking screenshots, extractin...

Use Vercel agent-browser for browser automation through a persistent visible Chrome or Chromium CDP session. Trigger whe...

Browser automation CLI for AI agents. Use for opening pages, snapshots with @e refs, clicking, filling forms, testing we...

Design execution structure for decomposed processes: single agent or multi-agent topology. Load when user says "design a...

Expert en ComfyUI workflows avancé (install, custom nodes, model management, workflow design)

Multi-agent orchestration with model routing, category delegation, and sprint management. Use for coordinating Pantheon...

Create new Claude Code subagents (the .claude/agents/ kind, NOT skills). Use this skill whenever the user wants to creat...

Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suit...

Create or improve a Claude Code subagent definition under `.claude/agents/<name>.md`. Use when the user explicitly invok...

Use when a consequential decision has genuinely competing positions that need bounded adversarial review before a human...

Improve codebases so coding agents reliably do the right thing by default. Use for architecture, type/invariant, static-...

Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent...

Designs multi-agent system architectures with orchestration patterns, tool schemas, and performance evaluation. Use when...

Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), genera...

Use the built-in `Computer` sub-agent with `agent-desktop` for macOS desktop automation. Apply when a task needs applica...

Build dependency-aware, batched dispatch queues for parallel agent execution.

Use this skill when a user wants to decide, design, audit, or repair a coordinated multi-agent or expert-team workflow f...

Diagnose failed or unreliable agent workflows by classifying bad assumptions, missing observations, tool misuse, wrapper...

Food Tech Specialist IA — Expert en technologies alimentaires (recipe recommendation, allergen detection, supply chain,...

Agent skill for goal-planner - invoke with $agent-goal-planner

Package agent context and state for handoff between agents or sessions. Use when transferring work between agents, savin...

Hire an AI agent the way you'd hire an employee — a role spec with success criteria, a structured work-sample interview...

HR & Recruiter IA — Expert en recrutement RH (job descriptions, screening, ATS, onboarding, culture fit)

HR Tech Specialist IA — Expert en technologies RH (ATS, payroll, benefits administration, employee self-service, DZ labo...

Agent skill for issue-tracker - invoke with $agent-issue-tracker

AI UGC video production from the terminal using the `agent-media` CLI.

Define which findings an agent may persist to memory, with provenance, sensitivity filtering, staleness, and deletion ru...

Expert en édition PDF avancé (text/typos/titles via NL prompts, batch processing)

Expert en construction ERP no-code (Hercules, Ninox, Airtable-based ERP, CRM custom, contexte DZ)

Use when deciding whether a Cherry Studio change needs an Agent Note, authoring or reviewing a Spec, recording a durable...

Add lightweight local observability to Codex/agent workflows. Use when tracking local runs, traces, evals, cost, token u...

Interactive workflow guide. Use when user is unsure what to do next, needs help navigating AgentOps, or wants to underst...

Comprehensive project hygiene: archive issues, validate schema, clean clutter, align docs, check git, update ignores.

Handle failures and errors during workflow. Use when build breaks, tests fail unexpectedly, or agent gets stuck. Semi-au...

Create, refine, and manage issues. Use for creating new issues from loose ideas, refining ambiguous issues, bulk operati...

Coordinate Codex work across the current task, internal subagents, user-owned tasks, worktrees, handoffs, formal review...

> 外部 Agent（独立终端 TUI / 桌面 App / Web 等平台）协作指南。系统提示词已覆盖的（工具描述/annotation/Constitution）不重复，本技能只写外部 Agent 特有流程。

Resolve agent ownership and handoff design.

Use when multiple agent results must be checked for missing evidence, scope drift, contradictions, and merge conflicts b...

Use when reading, explaining, reviewing, comparing, or extending one or more AI agent, LLM agent, tool-use, planning, me...

Agent parameter passing and context management. Use when invoking agents with specific parameters or managing agent cont...

Agent skill for planner - invoke with $agent-planner

Design, initialize, audit, migrate, maintain, or evaluate a packaged Codex or Claude Code plugin's architecture across s...