Каталог навыков агентов

Run the Parallel Autoresearch Engine — massively parallel SKILL.md optimization. Generates 10+ SKILL.md variants per gen...

Self-improving AI-driven workflow that continuously refines, reviews, validates and optimizes research tasks. Use for it...

Autonomous experiment loop: edit code, commit, run benchmark, extract metrics, keep improvements or revert, repeat forev...

Use when a research task must produce a bounded deliverable that passes an explicit validator, rubric, script, reviewer,...

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experim...

Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop be...

Scaffold and run Karpathy-style autoresearch loops in any git repo. This skill should be used when setting up autonomous...

Runs a bounded experiment loop under an approved budget: one change per iteration, scored by a declared metric or evalua...

Autonomous goal-directed iteration. Define a goal with a measurable metric, then modify-measure-keep/discard-repeat unti...

Autonomous iterative optimization. The agent modifies, executes, measures, and decides — looping in background to improv...

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agen...

Autonomous code optimization loop — modify, verify by benchmark, keep/revert against any metric (coverage, bundle size,...

Canonical autoresearch iteration protocol — Understand, Hypothesize, Experiment, Evaluate, Log loop; mechanical pass/sco...

Use when a research mission should be managed as a Codex goal with professor/critic-style validation, durable repo-local...

Domain-agnostic metric-driven improvement loop, generalizing Karpathy's autoresearch. Use when you want an agent to disc...

Autonomous LLM training optimization with GPU support. Runs 5-minute training experiments, measures val_bpb, keeps impro...

Autonomous ML training research loop (NVIDIA GPU required) — modify train.py, run fixed-budget experiment, parse val_bpb...

Autonomous literature-review loop (Tier 2, web-only, no Bash) — fetches papers, extracts structured summaries, builds li...

Autonomous research and experimentation toolkit with 10 commands. Core loop inspired by Karpathy's autoresearch — genera...

Dependency-aware, worktree-backed autoresearch for any repo. Use when the user wants to find what in a codebase can be o...

Create a feature-comparison run where each candidate implementation and a no-change control are tuned with equal budgets...

Create a deletion-comparison run that tunes the codebase with and without a part using equal budgets. Use when the user...

Show or plot recorded metric flow for an autoresearch-wrapper run. Use when the user wants the chronological metric sequ...

Report or keep an eye on an autoresearch-wrapper run's progress (status, rounds, best metric, stalls). Use when the user...

Start or resume a dependency-aware autoresearch-wrapper run in Git worktrees. Use when the target and metric are already...

Show dependency-aware autoresearch-wrapper state for the current repo. Use when the user wants the selected part, readin...

Scientific bug hunting using falsifiable hypotheses. Forms hypotheses, designs falsifying tests, eliminates candidates s...

Iterative error-crusher loop that auto-stops at 0 errors. Cascade-aware: fixes dependency errors before their dependents...

Feedback-driven self-improvement protocol for autoresearch-skill. Converts failed runs, confusing transcripts, bad outpu...

7-step setup wizard that produces a complete, ready-to-run research.md without executing the research loop. Walks the us...

Multi-perspective deliberation engine. Gathers independent positions from diverse personas, runs cross-examination and r...

Adversarial multi-round reasoning with blind-judge panel to reach rigorous conclusions. TRIGGER when: user wants rigorou...

12-dimension scenario exploration across user-specified domain modes. TRIGGER when: user wants to explore scenarios, edg...

Iterative security audit engine. Performs STRIDE threat modeling, OWASP Top-10 checks, attack surface mapping, and mitig...

Universal shipping workflow: 8-phase linear pipeline from verification to deploy. Reads type-checklists.md to select the...

Unattended multi-lens review of a plan, launch plan, spec, strategy doc, ADR or proposal. The autonomous counterpart to...

Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.

Structured Codex, Claude, Amp, Pi, or Kimi code review when explicitly requested.

Structured review engine of the review-phase Standards and Spec axes. Use when a review-phase Run Review axis subagent r...

Controle de acesso baseado em papéis (admin/editor/leitor/convidado) com verificação granular por recurso individual (pr...

Run the cards that do not need you. One `/super-bootstrap:autorun` turn = read every open card → admit the ones whose ne...

Expertise in maintaining, debugging, and deploying the autorun hook system for Claude Code and Gemini CLI. Use when the...

Implementa autosave com debounce, versionamento por snapshots e restauração de versões anteriores usando diff-match-patc...

See the main Infrastructure Sizing skill for comprehensive coverage of right-sizing and autoscaling strategies.

Every autoscaling decision is driven by one of three trigger types, and mature

CLI tool for automated changeset-based releases with AI-generated descriptions. Use when the user needs to release a pac...

Runs a changesets npm release through the version PR, CI publish, and registry verification. Use when asked to "release...

Use when the user says release this, publish this package, or cut a release for a changesets-based npm package. Not for...

Daily pipeline that picks one long video from a folder, transcribes it with Whisper, uses Gemini 3 Flash multimodal to f...

Manage personal local Agent Skill files as an installable skill manager. Proactively and periodically detect reusable us...

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-age...

Analyze coding sessions to detect corrections and preferences, then propose targeted improvements to Skills used in the...

扫描项目技术栈，自动安装最佳 AI agent skills。 用 autoskills CLI 从 skills.sh 安装匹配的 skills。 中文触发：自动技能、安装技能、技能扫描、装技能、autoskills

Iteratively optimize a formal specification through autonomous agent rounds. Compartmentalizes spec, runs improvement tr...

Add styled, burned-in captions to a video, let the user pick a style and fix captions in a small review window, and (wit...

Every Autotask entity at the command line, plus a local SQLite mirror that answers ticket-aging, workload, unbilled-time...

Autotask billing item retrieval, approval-level workflows, and invoice search — covering billing item types, approval st...

Autotask CRM entities - companies (accounts), contacts, and sites/locations - including field references, company type c...

Autotask quote structure and line items - quote item types (product, service, service bundle, labor, expense, shipping),...

Autotask ticket lifecycle: status/priority codes and transition rules, the ticket field schema, SLA calculation and cloc...

当设定个人或工作目标，希望目标本身能带来持续的内在动力和满足感时

Automatic exploratory data analysis and visualization with a single line of code - generates comprehensive charts, detec...

Skill for adding Stripe checkout and payment flows using Autumn.

Skill for adding feature gating and usage tracking using Autumn.

Skill for integrating Autumn - the billing and entitlements layer over Stripe.

Skill for setting up Autumn billing integration and creating customers.

This prompt directs an image-generation workflow to produce an 8K, photorealistic, cinematic fashion editorial portrait...

Automate desktop applications with AUV. Use for screenshots, OCR, mouse and keyboard input, reusable GUI workflows, or o...

Use this skill to generate well-branded interfaces and assets for AUV (the Moeru AI command-replay / inspect runtime), e...

Prepare, diagnose, and validate Linux GPU and Wayland environments for AUV rendering and capture through XDG Desktop Por...

Every Auvik endpoint as a command, plus the cross-client answers the Auvik UI and API cannot give you. Trigger phrases:...

Auvik alerts: severity tiers, status lifecycle, dismissal semantics, and the common alertName patterns that show up in M...

Auvik device records: device types, manageStatus and onlineStatus, lifecycle and warranty fields, and choosing between t...

Auvik network and interface entities: the network entity model, IP-range scoping, interface-to-device relationships, and...

A skill that uses only shell and config code blocks for testing contamination.

Audio/video studio production — multi-track editing, color grading, motion graphics, compositing, live streaming, screen...

AVA test runner - use when working on related tasks

Extract and organize styles from Avalonia AXAML files

Review AXAML files for Avalonia best practices

Available coder stacks for task planning. Maps agent names to technology specializations.

Assist with Avalanche C-Chain transactions, AVAX transfers, subnets, and cross-chain bridges.

Use when the agent needs the fundamentals of Avalanche L1s (formerly Subnets) — sovereign chains, custom gas tokens, cus...

Use this first for any Avalanche privacy request to decide between eERC (data privacy on a public chain) and a private/p...

Use when the agent wants the fastest way to start building on Avalanche — the Avalanche Starter Kit (Hardhat + ready Cod...

Use when working with Avalonia UI framework — building, styling, binding, animating, or deploying Avalonia apps with .NE...

Expert guidance for developing cross-platform desktop applications with Avalonia UI framework. Use when building, debugg...

Build cross-platform XAML desktop applications targeting Windows, macOS, and Linux using Avalonia UI and C#.

USE FOR: Building cross-platform desktop and mobile applications with XAML-based UI using Avalonia on .NET. Use when tar...

Avalonia UI development - XAML, MVVM, styling, and patterns

Use when setting up Avalonia app structure, resource dictionaries, application lifetimes, startup configuration, cross-p...

AvaloniaUI에서 CollectionView 대안 (DataGridCollectionView, ReactiveUI)

Use when working with built-in Avalonia controls. Routes to the correct sub-subskill for the control category needed.

Use when creating custom UserControls, TemplatedControls, basic drawing controls, custom panels, control libraries, atta...

'AvaloniaUI CustomControl를 활용한 AvaloniaUI Desktop Application Solution 기본 구조'

Use when writing data bindings, compiled bindings, converters, MultiBinding, collection views, validation, or binding to...