Поиск skills
Найдите подходящую возможность для вашего агента.
aws-account-management
Manage AWS accounts, organizations, IAM, and billing. Use when setting up AWS Organizations, managing IAM policies, controlling costs, or implementing multi-account strategies. Triggers on AWS Organizations, AWS IAM, AWS billing, Cost Explorer, SCPs, multi-account, AWS SSO, Identity Center.
shabbat-times
Access Jewish calendar data and Shabbat times via Hebcal API. Use when building apps with Shabbat times, Jewish holidays, Hebrew dates, or Zmanim. Triggers on Shabbat times, Hebcal, Jewish calendar, Hebrew date, Zmanim.
skill-library
Agent-native catalog and installer for armory packages across all 7 types: skills, agents, hooks, rules, commands, utilities, and presets. Browse, search, install, update, sync, and remove packages without leaving your agent session. Supports type filtering and profile-based bundles. Triggers on: "list available packages", "install skill", "install agent", "pull skill", "what packages are available", "update my skills", "search packages for", "package catalog", "armory list", "armory install", "armory search", "remove skill", "/library list", "/library use", "/library remove", "/library profiles", "show me armory packages". Use this skill when discovering, installing, updating, or removing armory packages within a session.
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with non-LCSC components, wants to compare PCBWay vs JLCPCB, or needs assembly with parts sourced globally rather than from LCSC only. For gerber/CPL export, stencil ordering, and BOM management, see the `bom` skill.
architecture-diagram
Generate detailed layered architecture diagrams as self-contained HTML artifacts with inline SVG icons, CSS Grid nested container layout, SVG path connection overlays, and color-coded connection legends. Triggers on: "architecture diagram", "infra diagram", "system diagram", "deployment diagram", "network diagram", "topology", "draw architecture", "visualize architecture", "system topology", or any request for visual representation of system components, containment hierarchy, and interconnections. For architecture reviews, audits, critiques, or design assessments, use architecture-reviewer instead.
concept-to-image
Turn any concept, idea, or description into a polished static HTML visual, then export it as a PNG or SVG image file. Use this skill when the user explicitly needs an image file output (PNG or SVG). This includes: concept diagrams, flowcharts, comparison charts, process visuals, educational diagrams, social media graphics, data visualizations, posters, cards, badges, icons, logo sketches, or any "make me an image of X" request achievable with HTML/CSS/SVG rather than photographic AI generation. Also trigger when the user has an existing HTML visual and wants to export/convert it to PNG or SVG. Trigger phrases: "create an image of", "export as PNG", "save as SVG", "concept to image", "turn this into an image", "screenshot this HTML", "design a graphic for export". For interactive HTML visuals opened in a browser, use static-web-artifacts-builder instead.
static-web-artifacts-builder
Build elaborate, self-contained static HTML artifacts opened in a browser — interactive diagrams, architecture visuals, data dashboards, HTML infographics, and rich interactive deliverables. Use this skill when the output is an HTML file viewed in a browser. Zero build toolchain — no React, no Vite, no Parcel. Pure HTML5 + CSS3 (Grid/Flexbox) + inline SVG. Triggers on: "interactive HTML", "self-contained web component", "open in browser", "interactive diagram", "visual dashboard", "HTML artifact", "HTML infographic", "interactive infographic". For image file output (PNG/SVG), use concept-to-image instead.
concept-to-video
Turn any concept into an animated explainer video using Manim (Python). Use whenever the user wants animated visualizations, motion graphics, or video output (MP4/GIF) for technical concepts. Covers: architecture animations, data flows, algorithm step-throughs, pipeline explainers, math proofs, comparisons, agent interactions, training loops, image embedding, multi-scene composition. Supports audio overlay via ffmpeg, parametric templates, and subtitles. Works headless — no browser or Node.js required. Also trigger for Manim scene edits or re-renders. Trigger on: "create a video", "animate this", "make an explainer", "concept to video", "manim animation", "show this as a video", "motion graphic", "visualize this process", "add voiceover to video", "animate with audio", or any concept + video/animation request. For branded motion graphics or React-based video, use remotion-video instead.
digikey
Search DigiKey for electronic components and download datasheets — primary source for prototype orders and the preferred API method for fetching datasheets. Find parts by keyword or MPN, check pricing/stock, download datasheets via API, analyze specifications. Sync and maintain a local datasheets directory — extract components from schematics, download missing datasheets, keep them up to date. Use when the user asks about electronic components, part specs, datasheets, pricing, stock, footprints, or needs to download a datasheet — even without mentioning "DigiKey". Also for "sync datasheets", "download datasheets for my board/project", or mentions a datasheets directory. DigiKey is the default distributor for prototyping. For BOM workflows, see the bom skill.
task-decomposer
Produces structured phased task boards from feature requests: dependency-mapped work items with parallelization flags, risk flags, edge case tables, and test strategy matrices. Triggers on: "decompose this feature", "task breakdown with dependencies", "phased implementation plan", "dependency map for", "break this into tasks with phases", "work breakdown structure". The differentiator is the structured output format (phased tables, parallelization flags, dependency chains) — use this skill when you need a formal task board, not ad-hoc decomposition the model handles natively. NOT for effort estimates, PERT calculations, or confidence intervals — use estimate-calibrator instead.
sql-optimizer
Analyzes SQL queries for performance issues: missing indexes, N+1 patterns, suboptimal joins, full table scans. Interprets EXPLAIN output, detects anti-patterns, recommends indexes, and rewrites queries with detailed explanations of each optimization. Triggers on: "optimize this query", "slow query", "query performance", "add indexes", "index recommendation", "explain plan", "query plan", "N+1 query", "fix this SQL", "SQL performance", "optimize SQL", "why is this query slow", "index strategy". Use this skill when given a SQL query that needs performance analysis or optimization.
gpu-optimizer
Expert GPU optimization for modern consumer GPUs (8-24GB VRAM). Use this skill when you need to optimize GPU training, speed up CUDA code, reduce OOM errors, tune XGBoost for GPU, migrate NumPy to CuPy, make a model faster, manage GPU memory, optimize VRAM usage, or benchmark PyTorch. Covers mixed precision, gradient checkpointing, XGBoost GPU acceleration, CuPy/cuDF migration, vectorization, torch.compile, and diagnostics. NVIDIA GPUs only. PyTorch, XGBoost, and RAPIDS frameworks.
remotion-video
Create production-grade motion graphics and videos using Remotion (React). Use whenever the user wants branded video content, product demos, data-driven video generation, or motion graphics with audio sync, web fonts, TailwindCSS styling, or media embedding. Covers: marketing videos, product launches, data visualizations, social media content, personalized video at scale, explainer videos with voiceover, animated charts, 3D scenes via Three.js. Requires Node.js and Claude Code environment. Trigger on: "create a Remotion video", "React video", "motion graphics", "branded video", "product demo video", "remotion", "video with audio", "TailwindCSS video", "data-driven video generation", "personalized video at scale", "video with voiceover". For mathematical animations, algorithm visualizations, or headless container rendering, use concept-to-video (Manim) instead.
local-llm-router
Route AI coding queries to local LLMs in air-gapped networks. Integrates Serena MCP for semantic code understanding. Use when working offline, with local models (Ollama, LM Studio, Jan, OpenWebUI), or in secure/closed environments. Triggers on local LLM, Ollama, LM Studio, Jan, air-gapped, offline AI, Serena, local inference, closed network, model routing, defense network, secure coding.
devils-advocate
Challenges AI-generated plans, code, designs, and decisions before you commit. Pairs with any other skill as a review layer. Uses pre-mortem analysis, inversion thinking, and Socratic questioning to find what AI missed — blind spots, hidden assumptions, failure modes, and optimistic shortcuts. The skill that asks "are you sure about that?" so you don't have to. Triggers on: "challenge this", "devils advocate", "stress test this plan", "what could go wrong", "poke holes in this", "review this critically", "second opinion on this design", "what am I missing". Use this skill when you need critical review of any AI-generated output, architecture decision, implementation plan, or code before committing to it.
manuscript-provenance
Computational provenance audit verifying that every number, table, figure, ordering, and terminology in a manuscript is derived from code and scripts — not manually entered. Cross-references LaTeX source against the codebase to detect hardcoded values, stale outputs, broken pipelines, and manual data entry. Companion to manuscript-review: that skill audits the document as prose; this skill audits whether the document is faithfully generated from code. Use when the user says "check provenance", "verify reproducibility", "audit my pipeline", "are my numbers from code", "check manuscript against scripts", "provenance audit", or any request to verify that manuscript content traces back to computational outputs.
research-critique
Critical analysis of research papers, academic manuscripts, preprints, and technical studies — evaluating methodology, claims-evidence alignment, contribution significance, and intellectual honesty. Produces coherent analytical responses (not checklists) that distinguish genuine weaknesses from standard field limitations. Governs intellectual posture: collegial reader, not adversarial reviewer. Triggers on: "critique this paper", "review this research", "what do you think of this paper", "analyze this study", "evaluate the methodology", "is this paper sound", "assess this research", "strengths and weaknesses of this paper", "does the evidence support the claims". Use this skill when the user provides a research paper, preprint, or technical study and asks for critical evaluation of its scientific merit, methodology, or contribution — not formatting, citation hygiene, or submission readiness (use manuscript-review for those).