Каталог навыков агентов

Meta-skill that generates domain-specific skills using advanced reasoning techniques. PROACTIVELY activate for: (1) Crea...

Advanced patterns for creating complex, multi-step skills with error handling and state management.

Engineer SSR caching strategies that preserve correctness under concurrent updates and streaming.

Implement AI-powered statusline with session tracking, plan detection, workspace emojis, and intelligent caching for Cla...

Comprehensive advanced table components skill for Next.js applications with TanStack Table v8, server-side operations, a...

Production-grade text search algorithms for finding and matching text in large documents with millisecond performance. I...

Context-efficient tool management via search, deferred loading, and programmatic calling

Explore advanced CS topics including advanced data structures, parallel computing, security, functional programming, and...

Advanced TypeScript patterns for TMNL. Covers conditional types, mapped types, branded types, generic constraints, type...

Comprehensive UX best practices including accessibility (WCAG 2.2), interaction patterns, user research methods, and usa...

Download and transcribe videos from YouTube, Bilibili, TikTok and 1000+ platforms. Use when user requests video download...

Advanced visual design techniques including typography systems, color theory, grid-based layouts, visual hierarchy, and...

Multi-tool orchestration patterns for complex Bluera Knowledge operations. Teaches progressive library exploration, addi...

Room-based exploration with narrative evidence collection

Story, quests, exploration, characters and growth.

Acts as AdventureGPT, an advanced text-based RPG engine and interactive fiction author. It generates immersive, non-line...

Multi-Agent Adversarial Analysis System for code security

Generative-adversarial coordination — locks a generator and critic agent in an escalating quality loop. The critic activ...

Routes adversarial engineering work to the right review or testing method. Use when the user asks to red-team, adversari...

Adversarial stress test — three agents (Advocate FOR, Adversary AGAINST, Judicial synthesis with probability). Trigger w...

Audit one Ergopti driver adversarially with reproducible evidence, without implementing fixes. Use for robustness audits...

Audits SaaS and usage-based web apps for adversarial usage patterns — accidental, opportunistic, and deliberate. Use thi...

Adversarial auditor that red-teams technical plans, asserts fail-closed factual provenance, decomposes cognitive token s...

Synthesize the single strongest EVIDENCE-BOUND reviewer case to reject a paper, built ONLY from the evidence ledger (cla...

Use when adversarially reviewing a document that makes formal or technical claims — math derivations, physics papers, st...

Review code through hostile perspectives to find bugs, security issues, and unintended consequences the author missed. U...

Committee of personas with opposing propensities forcing genuine debate

AGI: FREE-MAD adversarial debate protocol — three agents (Bull/Bear/Market) stress-test any investment thesis using hete...

Orchestrates a code task through two separate agents in an adversarial loop — an executor that implements and a strict e...

N-round adversarial review pipeline for empirical research output — the chain from data to LaTeX tables to a manuscript...

Generate adversarial inputs, edge cases, and boundary test payloads. Use when testing input robustness, finding edge cas...

JP's signature red-team pass — "how would I break this?" Argue against your own approach before proceeding. Trigger on a...

Put on the adversarial hat and systematically attack any document, plan, strategy, or idea to expose its weakest points...

当使用者说"帮我填词"、"按这个字数模板写歌词"、"用多Agent对抗式写词"、"这首副歌帮我想几句"时使用，前提是字数骨架和这首歌写什么都已经有了；只有主题、还没定写什么时先用 lyric-concept-builder。拿一份字数骨架和...

Two genuinely different models debate a plan before anything is built — Claude (Fable) drafts, Codex/OpenAI challenges,...

Adversarial multi-agent review of the diff BEFORE a pull request is opened (Mode A), and one bounded pass over bot revie...

Adversarial spec-compliance PR review — cross-references diffs against approved specs, verifies runtime claims against s...

Exploratory, adversarial QA: exercise a feature through whichever surface(s) it exposes — UI, API, or both — and surface...

Decide whether an article deserves publication through hard checks and skeptical comparison.

Fresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fres...

Independent second-pass review that tries to break the change: invariants, edge cases, error paths, concurrency, ending...

Adversarial code review using attacker mindset — trust boundary, attack surface, business logic, and defense evaluation

Use when Codex should ask the Antigravity agy CLI for an adversarial challenge review that pressure-tests implementation...

Use when Codex should ask Claude CLI for an adversarial challenge review that pressure-tests implementation direction, d...

Adversarial AI code review lenses challenging assumptions, testing edge cases, and verifying AI-generated code.

Run a bounded, evidence-based adversarial review of a DeepSeek Build change with the pinned GPT-6 Astra or Claude Opus 5...

Review a diff as an independent adversary rather than a collaborator: spec compliance, boundary coherence between produc...

Non-sycophantic code critique that finds concrete bugs, edge cases, silent failures and security issues with failing inp...

Runs a hostile review of a spec, plan, or code in a fresh subagent, then fixes what holds. Use when a spec, a plan, or i...

Adversarially review something just built — presume it is broken and find where. Use after implementing a feature, finis...

Challenge a proposal, architecture, or implementation through evidence-based failure scenarios. Use for a rigorous revie...

Run a seven-agent adversarial pipeline against a resume and cover letter before submission. Produces channel-conditional...

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for...

Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent...

Use when a plan, feature, or launch needs an explicit adversarial pass to find weak assumptions, abuse cases, or strateg...

Review an AI system's robustness against adversarial evasion attacks — covering input perturbation, semantic-preserving...

Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree. Use w...

Generates edge case, failure mode, and spec-driven test cases. Covers boundary values, nil inputs, concurrency, resource...

Adversarial audit system for SDLC phases. Finds problems that self-validation missed. Uses challenge mindset to identify...

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

Stress-test an implementation with adversarial inputs, boundary cases, contract violations, and security probes, then pr...

Pre-implementation red-team analysis. Use when a plan is high-risk, critical path, or expensive to reverse. Challenges p...

Use this skill when the user asks about FCRA adverse action procedures — what to do when a background check (MVR, crimin...

Generate CIOMS-compliant adverse event narratives for Individual Case Safety Reports (ICSR). Creates structured pharmaco...

Guide veterinary adverse drug event reporting through FDA CVM and query the openFDA animal adverse event database. Use w...

Search for negative news coverage, controversies, and reputational risks associated with individuals or companies across...

Objects announce what they can do — The Sims style

Use when running paid advertising campaigns on Xiaohongshu, setting up promoted posts, managing ad budgets, optimizing a...

Generic multi-channel advertising performance analysis patterns for Google Ads and Meta Ads. Use when monitoring CAC, RO...

Ask Codex a read-only question with explicit model, effort, budget, and compact results.

Get a senior-style review of code, a planned change, a library choice, or a fix idea -- without writing a spec document....

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

Reads what a session is for and advises which collaboration pattern it should open in and what agenda fits, from the cat...

Research and advise on the best way to approach a software project, including architecture, tech stack, implementation s...

Use when providing educational legal structure guidance for entrepreneurs. Covers business entity selection, liability c...

Instructions when acting as an Advisor to another Agent

A general-purpose advisor agent for planning, research, review, or orchestration.

Consult an independent GPT-5.6 reviewer (Terra by default; Sol on request, for a stronger but costlier review), matched...

Enforce a hard cap and a drift-check when a cheap executor model consults an expensive advisor model, and compute the ef...

Consult a stronger model mid-task for a second opinion before committing to an approach, when stuck, or before declaring...

Consult a separate model at a selected plan, fork, or completion decision while the current model retains execution owne...

Use when a task is too large for one model pass, needs parallel research or generation across many subtasks (like resear...

Use when Codex should create, update, audit, or consult a private long-lived profile for an academic advisor, supervisor...

Detects when user requests warrant critical analysis via /advise command

Recruit, structure, and manage advisory boards for strategic guidance

겟백 1:1 자문 세션(A 대표·B 원장)이 끝난 뒤 줌 녹화 전사록을 받아 노션 코칭 대시보드에 회의록을 올리고, 할 일 보드 등록·대시보드 문구 갱신·클라이언트 카톡 통보까지 처리할 때 읽을 것. "B 원장님 자...

Final critic gate before report emission. Use after detection to verify evidence and thresholds, enforce sample sufficie...

Turn happy customers into references, case studies, and referrals, on purpose instead of by accident. Reads who is happy...

Use when the user asks to "design an employee advocacy program", "set up founder-led sharing", or "build a share kit for...

Use when designing and scaling reference, story, advisory, or community programs.

Scoring and governance framework for managing reference customers and advocacy cohorts.

Use to identify, score, and prioritize customer advocates for programs.

Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medid...

Systematically challenge current assumptions before major decisions. Counters confirmation bias, groupthink, and overcon...

Advogado especialista em todas as areas do Direito brasileiro: familia, criminal, trabalhista, tributario, consumidor, i...

Guide creation of AI Developer Workflows (ADWs) that combine deterministic orchestration code with non-deterministic age...