Каталог навыков агентов

Quantitative options volatility, dealer gamma exposure (GEX), term structure backwardation, and market tide flow analysi...

Serve a quantized language model locally on an Apple Silicon Mac with mlx-optiq and an OpenAI-compatible endpoint. Use w...

When the user wants to tune metaheuristic or solver parameters with Optuna, including search-space definition, TPE sampl...

Optuna Study Creator - Auto-activating skill for ML Training. Triggers on: optuna study creator, optuna study creator Pa...

Create optuna study creator operations. Auto-activating skill for ML Training. Triggers on: optuna study creator, optuna...

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update...

Claude Opus 4.8 (claude-opus-4-8) protocol — prompting, effort/thinking config, fast mode, token discipline. Trigger whe...

Push Opus 4.8 toward Fable 5-grade working style — verification depth, outcome-first output, long-horizon discipline. Tr...

The OpusClip craft skill — turn long video (podcasts, webinars, interviews, streams) into publishable short clips with A...

Deep-audit chains in dom_reachable.jsonl (fallback hot.jsonl) via Sonnet→Opus advisor pipeline. Writes opus/<chain_id>.m...

Delegate substantial implementation, debugging, or independent review from Codex to Claude Opus when it can reduce the c...

Leverage Claude Opus 4.5's extended thinking capabilities for deep reasoning, complex analysis, and multi-step synthesis...

Standing operating model — Opus (and its glm-5.2 Opus-equivalent) orchestrates while spawned workers do the work across...

Find missing security controls — sibling functions that skip a control their peers call. Wraps gap_analyzer + cascade ga...

Direct and render films made entirely in JavaScript, from an idea to a frame-exact MP4, working like a film director. Ta...

Run a multi-model orchestration workflow with Claude Opus 4.8 as the lead, driven by ultracode (xhigh reasoning + dynami...

Turn long videos into AI-curated short clips with OpusClip: create clip projects, check status, list clips with virality...

Turn long-form videos into short clips and post them to social platforms using the OpusClip API. Use when the user wants...

Generate a voiceover, narration or text-to-speech, a music track or soundtrack, or short AI video clips with OpusClip MC...

Use this skill when accessing OQMD for open quantum materials data, phase stability, or DFT formation energies.

Oregon Corporate Activity Tax is a gross receipts tax (not an income tax) imposed under ORS Chapter 317A on persons with...

Tier 2 Oregon content skill for employer payroll compliance covering tax year 2025. Includes the OR PIT brackets up to 9...

Integrate ora spinners with consistent styling, promise handling, and status updates for CLI progress feedback.

Use oracle CLI to bundle prompts and files for second-model debugging, refactor, design, or review checks.

Оракул (Oracle) — Backend code reviewer. Reviews TypeScript/Prisma code for type safety, async correctness, schema sync....

GPT-5 Pro second opinion. Use when user says "consult the oracle", "ask the oracle", "oracle this". Run DETACHED with no...

Oracle Database specific features. Covers data types, sequences, synonyms, partitioning, and Oracle-specific SQL syntax....

Best practices for the oracle CLI (prompt bundling, engines, sessions, file attachment).

Oracle (神谕所) — Life crossroads deliberation room. Convene Sartre, Aurelius, Jung, Frankl, Nietzsche, and Kahneman for ma...

Personal AI Assistant CLI with multi-surface support - Rebranded from clawdbot

A built-in agent for querying complex knowledge bases, providing authoritative answers, and synthesizing multi-source in...

Gets a second-model review by bundling a prompt and selected repository files into one request for another AI (API or br...

Specialist agent for AI/ML design and evaluation. Covers prompt engineering, RAG design, LLM application patterns, AI sa...

Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.

Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation...

System architect and design expert - provides strategic technical guidance

Write Oracle SQL and PL/SQL with proper syntax, hints, and performance patterns.

Use when you want a second-model review through the `@steipete/oracle` CLI by bundling a prompt with a tightly scoped se...

Build compatibility adapters between Jarvis, OVOS, OpenClaw, and Oracle-native surfaces. Use when legacy triggers or old...

Build production agentic applications on OCI using Oracle Agent Development Kit with multi-agent orchestration, function...

Build production agentic applications on OCI using Oracle Agent Development Kit with multi-agent orchestration, function...

Design framework-agnostic AI agents using Oracle's Open Agent Specification for portable, interoperable agentic systems...

Design framework-agnostic AI agents using Oracle's Open Agent Specification for portable, interoperable agentic systems...

Provides comprehensive Oracle Cloud Infrastructure (OCI) guidance including compute instances, networking (VCN, load bal...

Shared vocabulary and principles for designing deep modules. Use when designing or changing a module's interface, decidi...

This skill should be used when the user asks to "use Codex", "ask Codex", "consult Codex", "use GPT for planning", "ask...

This skill should be used when the user asks to "use Codex", "ask Codex", "consult Codex", "Codex review", "use GPT for...

Use before invoking Oracle to ensure appropriate usage of this expensive reasoning resource

Disciplined debugging methodology. Triggers on bug reports, test failures, "debug this", "diagnose this", unexpected beh...

Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous langu...

This skill should be used when the user asks to "use Gemini", "ask Gemini", "consult Gemini", "Gemini review", "use Gemi...

Grill the user relentlessly about a plan, decision, or idea, maintaining the project's domain model (CONTEXT.md, ADRs) a...

Hand a question to an outside Oracle model (GPT-5.5 Pro or whichever the operator names) as one task document plus one z...

Track and nurture knowledge maturation. Use when user mentions "incubate", "mature", "grow knowledge", "promotion", "lev...

Build Oracle memory surfaces: session logs, durable notes, local context, and retrieval. Use when the task touches histo...

Guide newcomers through learnings with patience and context. Use when user says "mentor me", "guide me through", "I'm ne...

Create learning paths for topics. Use when user says "learning path", "how do I learn", "roadmap for", "curriculum", "wh...

Build Oracle registry surfaces for skills, packages, and installs. Use when the task touches local skill packs, discover...

Build Oracle task routing: session ownership, detached work, launch order, and handoff rules. Use when the task touches...

Expert technical advisor with deep reasoning for architecture decisions, code analysis, and engineering guidance. Master...

Generate learning materials from mature patterns. Use when user says "teach me", "explain this pattern", "create a guide...

Oracle audio-subsystem builder: STT, TTS, wakeword, call handoff, and audio routing for the Oracle shell. Invoke by name...

Prepare a lawyer for an adversarial proceeding the way Neal Katyal's "Harvey" prepared him for the SCOTUS tariffs argume...

生成小学数学口算出题器HTML工具。随机出题+自动计时+自动批改+错题本+难度分级。双击即用。当用户说"口算出题""计算练习""口算器""出题器"时触发。

分析口腔健康数据、识别口腔问题模式、评估口腔健康状况、提供个性化口腔健康建议。支持与营养、慢性病、用药等其他健康数据的关联分析。

Prepare oral-history projects and interviews, edit transcripts, review narrator access terms, and build contextualized e...

Historical argumentation, evidence-based writing, and oral history methods. Covers thesis development for historical arg...

Record a parent's or grandparent's life while they can still tell it — the question arcs that unlock real stories instea...

Help authors learn from exemplary ICLR, ICML, and NeurIPS papers through source-linked manuscript comparisons, concrete...

Select a reviewed orange liqueur lineup for named recipes under role, sweetness, base, proof, budget, availability, and...

Wibi Style 官方视觉风格：把一张照片转换成橙底蓝墨时装漫画。适合穿搭清楚的单人全身、半身与近景照片，重绘为橙底深蓝手绘时装插画；复杂多人和密集花纹仍可能不稳定。适用于用户要求橙底蓝墨时装漫画，或明确调用 $orange-navy-...

Audit brand AI visibility readiness and prepare OranGEO-style GEO, AEO, LLM SEO, and AI search optimization action plans...

orb is a machine learning force field (MLFF) based on graph neural networks (GNNs), designed as a universal interatomic...

[WHAT] Build animated SwiftUI orbs — Siri-style mesh gradients, particle spheres, and AI assistant visualizers. [HOW] 7...

Comprehensive guide to orb. Master the concepts, implementation, best practices, and real-world applications of orb in p...

Receive and verify Orb webhooks. Use when setting up Orb webhook handlers, debugging Orb signature verification, or hand...

Master dispatcher for Orbit — the WordPress plugin QA framework. Use when the user types "orbit", "/orbit", "orbit help"...

Builds a Canvas 2D swarm of twenty-six labelled multiplayer cursors riding an invisible sphere seen face on, its depth s...

Run the opt-in ORBIT planning lifecycle for one managed project without replacing ApexYard governance.

Autonomous loop runner for nexus-autoloop. Generates complete script sets for loop execution, designs operation contract...

Running autonomous loops for nexus-autoloop. Generates script sets from goals, designs operation contracts, audits live...

Audit a WordPress plugin for the new Abilities API + AI Client & Connectors API (WP 7.0, ships May 20, 2026). Verifies `...

WCAG 2.2 AA accessibility audit for a WordPress plugin's admin UI, block editor output, and frontend markup. Combines ax...

Discover every `wp_ajax_*` and `wp_ajax_nopriv_*` action in a WordPress plugin and fuzz-test admin-ajax.php endpoints wi...

Audit Block Bindings API usage — the WP 6.5+ way to bind block attributes to dynamic data sources (post meta, options, c...

Audit and test block patterns shipped by a WordPress plugin — pattern category registration, preview rendering, `block_p...

Audit block variations — alternative configurations of an existing block (e.g. core/group's "Row" variation), `transform...

JavaScript / CSS bundle analysis for a WordPress plugin — total weight, per-chunk breakdown, source-map-explorer visuali...

Verify WordPress plugin compatibility with object cache (Redis / Memcached) and page cache (W3 Total Cache, WP Rocket, L...

A single feature card orbits a dot sphere on approved Blender camera motion. HyperFrames block, 1920×1080, 10s, 4 variab...

Code-quality reviewer for WordPress plugins — finds dead code, complexity hotspots, error-handling gaps, type-safety iss...

ACF (Advanced Custom Fields) integration audit — get_field / the_field usage, ACF Blocks (Gutenberg), Field Groups loade...

Multi-version compatibility matrix for a WordPress plugin — runs the gauntlet against PHP 7.4 / 8.1 / 8.3 / 8.5 × WP 6.3...

Polylang compatibility audit — pll_register_string, pll_current_language, custom-post-type translation, language switche...

Coexistence audit with RankMath SEO — schema-output collision (RankMath's schema is more aggressive than Yoast), meta-ta...

WPML compatibility audit — translatable strings via icl_t / wpml_register_string, custom-post-type translation, taxonomy...