Каталог навыков агентов

Automatically categorize emails by type, priority, and required action

Expert email management assistant for Apple Mail. Use this when the user mentions inbox management, email organization,...

Convert an email (or a whole thread) into real tasks — the actual asks extracted from the prose, each with owner, deadli...

AI-powered email triage that reads your inbox, classifies each message by importance and urgency (Eisenhower matrix), de...

Find and validate email addresses using Snov.io via Chrome DevTools MCP. Takes LinkedIn profile URLs and returns verifie...

Curated prompt examples for portfolio review, quotes, NFT discovery, prediction markets, and approval-gated wallet workf...

Create original short videos using the 情绪物证清空｜低谷表情、旧物处置与价值回报 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the u...

Emperor Time — CAPTURE / Chain Jail. Hunt, adapt, or author a missing skill, then pin, get consent, trial, register. Use...

Use this skill when developing, testing, debugging, or modifying code inside the Employee Portal frontend (apps/employee...

When the user needs to create or improve content that shapes how candidates and the public perceive the company as a pla...

Enable feedback capture hooks for the current project

Browser automation tool using Playwright - captures screenshots and extracts content from web pages

Finalize session by creating detailed log and syncing to cloud

End MARVIN session, save context, and commit changes. Use when user types /end or /quit. Creates session log, updates st...

End the current learning session. Use when done studying to generate summary, update learning plan, and log final entrie...

General SOP for common requests related to end, size, fs.

Use when the agent must execute or directly observe decisive live software acceptance through a real user-visible or run...

Geführter Gesamtworkflow mit 50-Skill-Routing: Pflicht, Datenraum, Portal, Freigabe, Aktualisierung, Kodex und Monitorin...

Energy Unit Conversion Pipeline - Convert between energy units and analyze: MeV to Joules, scientific notation, and erro...

Edit a portfolio case study for high signal, compact hierarchy, and fast scanning without losing evidence. Use when a dr...

Use when starting, planning, or running a multi-phase pentest or red-team engagement — to sequence the Cyber Kill Chain...

Add or audit allocator tagging and allocation tracing to attribute engine memory growth to subsystems and lifetimes.

Designs module and plugin boundaries for extensible engines. Use when separating runtime, renderer, physics, world gener...

Read, search, verify, and synthesize English frontier literature for engineering research and Chinese academic writing....

HIGHEST-PRECEDENCE engineering rulebook for ALL tasks (CANONICAL — DO NOT duplicate pure engineering rules anywhere else...

Draft, audit, or revise English response letters and revision plans for engineering papers from advisor, senior-author,...

Parent workflow: understand, inspect repo, requirements, research, design, plan, implement thin slices, test, review, se...

Implement a feature, review a change, delegate work, or resume a session in a Lacquer-managed project.

Audit and tighten agent/plugin surfaces with certainty-graded findings. Use when the user says "enhance my plugin", "imp...

Use this skill to resolve a gene symbol to Ensembl IDs and fetch a canonical Ensembl gene record. Do not use it for full...

B2B 大客户销售 (B2B 大客户销售 / 企业级复杂销售 (Enterprise B2B Sales / Complex Selling) — 面向企业客户的高价值、长周期、多干系人复杂销售的职业认知操作系统，从业者(AE/客户经理/S...

Captures institutional knowledge after solving problems. Documents what was solved, how, and how to prevent it. Searchab...

Scaffolds or audits Zod-validated environment variables for this Next.js service — src/lib/env.ts, .env.example, scripts...

container-use環境の状態管理のためのSingle Source of Truth（environments.json）の管理API、更新タイミング、復旧ロジックを定義

Use when the user runs /eod or says they're calling it a day. Scans configured project repos for uncommitted/unpushed wo...

Run a product sunset end to end — decide, align, plan, prepare, announce, close. Use when you need the whole EOL process...

Headless EPCI workflow for autonomous feature implementation via claude -p. Executes Explore-Plan-Code-Inspect without i...

Create comprehensive technical specifications from CDC (Cahier des Charges) or brief output. Decomposes features into 1-...

Epigenetics & Drug Response - Link epigenetics to drug response: gene regulation, variant effects, drug interactions, an...

Epigenomic Landscape Mapping - Map epigenomic landscape: overlapping features, regulatory elements, binding matrices, an...

EPUB ebook creation and processing — structure, metadata, validation — use when generating or parsing ebooks.

Plan, adapt, troubleshoot, and safety-gate cooking around kitchen equipment, appliances, vessels, heat transfer, capacit...

Track lab equipment calibration dates and send maintenance reminders

AI4L - Main Skill for Evidence Review Creation and Auditing using @AGENTS

Route and operate reusable Project Eris workflows in Claude Code for Ready, Status, Status & Fix, Create X Tasks, Finish...

(ePost) Use when operations fail transiently — timeouts, network errors, retries, circuit breakers, graceful degradation

RPA error handling patterns for resilient automation workflows.

Classify workflow failures and attempt automatic recovery. Use when sprint/feature fails during implementation to determ...

What to do when things break.

What to do when things break.

This skill provides comprehensive guidance on error handling patterns, recovery strategies, and debugging techniques in...

Packages a customer problem into a structured escalation brief for engineering and leadership: rates severity on custome...

Configure and troubleshoot Salesforce Case Escalation Rules: setting up time-based escalation entries, business hours co...

Configure and troubleshoot Salesforce Case Escalation Rules: time-based escalation entries, business hours configuration...

Create or refine a single increment. Smart stage detection — no active creates one, incomplete refines, ready waits for...

Show the current backlog of pending and active plans, sorted by priority.

Resume an interrupted session. Reads the active increment, assesses progress, and picks up where the last session left o...

Advance the current work stage. If in spec mode, derives an increment plan. If in increment mode, begins implementation.

Revise a plan, phase, or fix document based on your feedback. You comment, the agent edits. Supports multiple rounds of...

Update spec files to match shipped implementation. Records sync notes in the increment and finishes it when complete.

Implement all pending plans for the current phase automatically — commits at milestones, opens the phase PR when done. N...

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecat...

Use when an ethics committee or IRB application involves AI anywhere in the pipeline, when KVKK, GDPR, or EU AI Act duti...

Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each exa...

Evaluate technologies and competitive developments against Genesis architecture

Inspect software projects and evaluate application, database, and infrastructure deployment architectures across static...

Evaluate racking strategy options from load profile, selectivity, building constraints, MHE, throughput, and safety boun...

Customer event analytics across every GTM system — Intercom, Zendesk, Salesforce, HubSpot, Segment, Amplitude, Mixpanel,...

Append-only event log — the probabilistic record of everything that happened in the project. Use whenever something nota...

Find attendees at conferences/events, research their companies, qualify against ICP, and launch outreach

Set the active feature context for artifact organization. Creates subfolders in planning-artifacts and implementation-ar...

Manage significant changes during sprint execution. Use when the user says "correct course" or "propose sprint change"

Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says "c...

Sets up Python virtual environments using uv for each library, installs dependencies from project configuration files, a...

Create project-context.md with AI rules. Use when the user says "generate project context" or "create project context"

Analyzes what is done and the users query and offers advice on what to do next. Use if user says what should I do next o...

Core PDDL planning solver that parses domain/problem files, invokes pyperplan with optimal search configuration (GBFS +...

Build multi-day travel itineraries from structured databases (cities, accommodations, restaurants, attractions, driving...

A comprehensive skill for extracting chapter indices from tutorial videos using FFmpeg audio extraction, OpenAI Whisper...

Compute Elastic Weight Consolidation's Fisher-weighted quadratic penalty, gradient, and additive multi-task quadratic te...

Build deterministic sequential-task protocols for Elastic Weight Consolidation recovery experiments where old-task data...

Automate Exa tasks via Rube MCP (Composio). Always search tools first for current schemas.

Generate practice tests, flashcards, study schedules, and timed simulations from any study material.

Execute Sprint 1 tasks for FASA optimization and trade analytics. This skill should be used when the user requests execu...

Demonstrate a reusable cross-platform skill without accessing external systems.

An example skill for testing diff-skill evaluation.

Set up notebook-connector configuration for Exasol AI workflows through the Secrets Python API. Covers secure config sto...

Deploy and use the Exasol Text AI Extension (TXAIE) with notebook-connector. Covers `deploy_license`, `initialize_text_a...

Deploy and use the Exasol Transformers Extension (TE) for NLP inference inside Exasol with notebook-connector. Covers `i...

Generate Excalidraw diagram files (.excalidraw) from a description. Use when the user mentions 'excalidraw,' 'diagram,'...

This skill enables advanced Excel automation using xlwings - a library that can interact with live Excel instances. Unli...

Perform a read-only spreadsheet data-quality audit that reports missing values, duplicates, types, formats, anomalies, a...

Plan the next incomplete step (or full phase with --phase flag) from the plan, then enter plan mode for user approval be...

Execute an existing docs/planning/phase-N plan sequentially by completing lettered sub-plans and roman numeral tasks, ap...

pending EARS 스펙을 선택하여 구현 실행

Reactant router — read a document, interpret its <@skill> annotations in context, and execute every actionable tag seque...