Каталог навыков агентов

Get a help or a second opinion from other agents. Bundle a prompt and a curated file set, then ask other LLMs for advice...

Five independent critic subagents in parallel on an idea, plan, design, R&R strategy, grant, or SKILL.md, then a synthes...

This skill activates when the user needs multi-perspective analysis, business decision support, risk evaluation, strateg...

Convene a cross-model council on a hard decision — five seats, each filled by ONE real agent (some Codex, some Claude),...

Convenes multiple agents to debate an important decision

Compare model perspectives for brainstorming, planning, validation, idea duels or interviews. Use when: independent prop...

/council — Deliberative multi-provider review. Use when the user runs /council.

High-stakes decision-making system with 5 advisors, anonymous peer review, and chairman synthesis. Activates on "council...

Use when the user runs /council [ticket-id]. Convenes a planning council on an issue tracker ticket. Erestor (subagent)...

The LAW a council SEAT is bound by — deliberation protocol, pact obligations, governance, and decision-ledger recording...

Convene a four-voice council for ambiguous

Use when the user asks for a council, second opinions, or parallel investigation. Not for cross-examination of existing...

Gathers N independent, decorrelated perspectives across model families (external CLIs when present, subagents when not)...

This skill should be used when the user says "/council", "council", "deliberate", "multi-perspective decision", "트레이드오프...

Run independent advisor passes and anonymized peer review for a consequential choice. Use when the user requests a counc...

Multi-agent debate system. USE WHEN council, debate, perspectives, agents discuss. SkillSearch('council') for docs.

曖昧な決定、トレードオフ、ゴー/ノーゴーの判断のために4つの声のカウンシルを召集します。複数の有効なパスが存在し、選択前に構造化された異議が必要な場合に使用します。

Use when user wants to ask the AI council a question, get multiple AI perspectives, or consult with both Codex and Gemin...

Use for code review and quality feedback from both Codex and Gemini. Triggers on "council review code", "council code re...

Use for multi-perspective analysis with both Codex and Gemini exploring different viewpoints. Triggers on "council persp...

Multi-perspective analysis methodology for complex decisions. Dynamically generates relevant expert viewpoints, consults...

Overview of 7 core perspectives with variable naming system. Use when need to understand the full council structure, ada...

Use for systematic debugging and root cause analysis with both Codex and Gemini. Triggers on "council debug", "council r...

Get multi-model AI consensus on complex questions using Claude, Codex, and Gemini

Quality gate using LLM Council multi-model consensus for CI/CD pipelines.Use for automated approval workflows and pipeli...

Runs a structured nine-seat council deliberation on an idea, project, business, startup, goal, or objective, then writes...

Spawn 5 Opus subagents with randomly-generated distinct personas to debate a problem from multiple angles. Use when expl...

Multi-model council planning for implementation and architecture decisions. USE FOR: "plan with council", "multi-model p...

Policy for the cross-model council: when to hand off to an installed sibling plugin's own slash command (`/codex:*`) ver...

Multi-model code review with structured feedback using LLM Council peer evaluation.Use for PR reviews, code quality chec...

Multi-model validation council — auto-validate plans, architecture changes, and PRs via validate-plan/review before exec...

Multi-model council review for diffs, pull requests, and risky changes — CRITICAL after non-trivial development. USE FOR...

Route a personal-life request to the smallest set of Council specialists that actually own it.

Use for deep multi-step investigation and analysis with both Codex and Gemini. Triggers on "council deep analysis", "inv...

Verify code, documents, or implementation against requirements using LLM Council multi-model deliberation.Use when you n...

Expert simulation for code guidance and style. Triggers on "code like [expert]", "what would [expert] say", "idiomatic",...

Hand a legal matter to qualified counsel with complete factual context, authoritative documents, timeline, business obje...

Fundamentals of therapeutic communication: Active listening, mirroring, paraphrasing, open questions, and validation.

Print your own north-star row from your own record, and nothing else. Reads .claude/harness/decision-log.md, the canvas...

This skill provides guidance for counting tokens in datasets using specific tokenizers. It should be used when tasks inv...

Quality control and exploration of RNA-seq count matrices before differential expression. Check for outliers, batch effe...

Countdown - pre-implementation validation. Runs oracle (Opus) for planning, then Go Poll with review agents (Haiku) to v...

Use before drafting sections or paragraphs to enumerate counter-arguments and draft resolutions that withstand peer revi...

Plan layered defense against unmanned aerial system threats across fixed and mobile formations. Use when integrating det...

Debug proof failures using counterexamples from Nitpick (Isabelle) or QuickChick (Coq) to identify specification errors,...

Explain why counterexamples violate specifications by analyzing formal specifications (temporal logic, invariants, pre/p...

Generate concrete counterexamples when formal verification, assertions, or specifications fail. Use this skill when debu...

This skill should be used when the user asks to "check my preferences", "show memory", "run /buff:counterfeit", "what do...

Decode a counteroffer after you resign — what the raise, promotion promise, or title bump really signals, the statistics...

Build a local business a list of its NEXT CUSTOMERS from public records (building permits, wrecking permits, business cl...

Guide counterparty credit risk measurement and management for OTC and securities trading, organized around three workflo...

Review a business counterparty, deal party, payment partner or other relationship subject using approved screening, regi...

Contrapuntal writing and analysis covering species counterpoint, fugue structure, canon types, and imitative techniques....

Apply the CV conventions of the country where the job is: length, photo, personal details, date and name order, spelling...

Use AgentPMT external API to run the published workflow Country Data Snapshot with wallet signatures and credits.

Load gene expression count matrices from various formats including CSV, TSV, featureCounts, Salmon, kallisto, and 10X. U...

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

Generate weekly relationship health report showing affect ratios and repair rates for both partners across 3 weeks (curr...

Interacting dynamical systems

Build a live Cowork artifact (persistent HTML widget) backed by a Coupler.io dataflow. Use this skill whenever the user...

Build a live Cowork artifact (persistent HTML widget) backed by a Coupler.io dataflow. Use this skill whenever the user...

OPTIONAL: Analyzes TaskMaster subtasks to determine if they are tightly coupled (share code/models) or loosely coupled (...

Optional analysis skill that identifies parallel task opportunities. Analyzes task coupling to determine which tasks can...

Receive and verify Courier outbound webhooks. Use when setting up Courier webhook handlers, debugging courier-signature...

Sets up a course, block, term or online course with all its material: asks for the syllabus, slides, readings, cases, da...

Process an online course into detailed vault notes — one per lecture, with slides and transcripts synthesized. Use this...

[Content] Use when a workflow step or the user asks for course material: Bloom objectives, modules, lessons, exercises,...

[Content] Build structured learning/teaching course material with Bloom taxonomy objectives, modules, lessons, exercises...

Create educational course content, lesson plans, and workshop materials. Use for building structured learning experience...

Customer purchased course but content is locked, unavailable, or not accessible as expected.

Design educational courses and curriculum with learning objectives and assessments

Design full online courses — learning objectives, module outlines, lesson scripts, quizzes, and assessment rubrics.

Interactive, step-by-step course creation assistant. Takes any idea (or YouTube video) and produces a complete, launch-r...

Experimental skill for creating, organizing, or reviewing a reproducible course or class-project data analysis package f...

Provides comprehensive guidance for course design including curriculum development, learning objectives, and course stru...

Validates narration text, generates audio via ElevenLabs, and synchronizes timestamps.

Customer expresses concern about course difficulty level or prerequisite knowledge needed.

Topic router for the AI Engineering from Scratch curriculum. Give it a topic, a question, or a bug you are fighting, and...

Help and navigation for Claude Code Course.Use when: user asks about the course, lessons, or progress.Triggers: "help",...

Use this skill to create course-style talking-head video edits with big lower-third kinetic text, champagne/gold highlig...

Write a 10-email sequence specifically for launching a course — 3 value/warmup, 2 cart-open, 2 social proof/objection ha...

Turn course PPTs, PDFs, handouts, screenshots, and lecture materials into Chinese guided learning and durable Obsidian l...

Create a full course structure from a topic and transformation goal. Output includes course name, tagline, target studen...

course-builder의 강의 섹션을 읽고 핵심 기술 내용을 추출하여 Gemini에서 고품질 슬라이드 이미지를 생성하기 위한 프롬프트를 작성합니다.

Write a course-specific sales page with headline targeting the transformation, "Is this for you?" section, full curricul...

Package an existing interactive course generated by the book-to-course skill (a folder with index.html, assets/ and cour...

Package an existing interactive course generated by the book-to-course skill (a folder with index.html, assets/ and cour...

Audit and fix course player UX against LMS best practices — layout proportions, progressive disclosure, progress psychol...

Generate educational videos from course audio and slide images using timestamp-based synchronization

Orchestrate course development workflow, track progress, and capture learnings.

Name | Type | Description | Notes

Put an idea on trial in front of a jury of 12 Claudes. A prosecutor Claude argues it fails, a defense Claude argues it w...

Put an idea on trial: a prosecutor and a defense Claude argue, 12 juror sub-agents vote independently, and a judge reads...

Claude가 판례 Markdown 파일을 직접 분석하여 JSON 메타데이터를 생성합니다.