Top Agent Skills

Manage email accounts from the terminal using IMAP and SMTP with the Himalaya CLI, supporting listing, reading, writing, replying, forwarding, searching, and organizing messages across multiple accounts.

Guides creators through a three-step process to combine personal creative expression with sustainable commercial value, from self-driven creation to sharing and productization.

当需要分析一个观念、文化现象或行为模式为何能广泛传播并被人接受时

在启动一个重要项目或关键行动之前，用于主动识别和防范风险

当考虑使用非常规、高风险手段（如极端外部压力、药物、未经充分评估的强效工具如AI）来强行突破个人发展瓶颈或加速进入“渠道”时

在启动高风险项目或重要决策前，需要预先识别潜在失败点以增强心理韧性和方案鲁棒性时

当需要进入高度专注、高效且愉悦的工作或学习状态时

当遇到令人情绪激动或陷入僵局的情境，需要跳出固有反应模式以做出更优决策时

当需要快速掌握一门新技能或知识领域，且希望通过实践而非单纯理论学习时

Perform comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates detailed report of issues with severity ratings and recommendations.

Improve interface performance across loading speed, rendering, animations, images, and bundle size. Makes experiences faster and smoother.

Score any piece of writing for AI-generation tells and produce a weighted 0-100 scorecard with flagged evidence and ranked fixes. Use this skill whenever the user asks "does this sound AI-written", "run this through the AI detector", "score this writing", "check this for AI tells", "would this pass as human", "humanize check", or wants any article, blog post, email, or copy audited for AI patterns before publishing. Also use it when the user pastes or points to text and asks how it reads, whether it's too "ChatGPT-ish", or wants a QA pass on generated content. Works on pasted text, files, and URLs.

Apply one logical code change with mandatory impact mapping, git snapshot, verification, and automatic revert on failure. Load when the user asks for a safe edit, verified change, one change at a time with rollback, or codespine-style edit loop. Also triggers on "safe change", "edit with verification", "don't break the build", "revert if tests fail", or any non-trivial code edit where blast radius matters. Always runs dependency-mapping first. Pairs with incremental-implementation for multi-slice work; this skill is one atomic verify cycle per invocation.

Author pull requests with intent-separated commits, blast-radius disclosure, and verification evidence. Load when opening a PR, writing a PR description, separating refactor from feature commits, or summarizing a change set for review. Also triggers on "write the PR", "PR body", "intent-separated commits", "split refactor from feature", "pr summary", or after safe-change cycles complete. Extends git-workflow-and-versioning — does not replace it.

Create handcrafted static SVG graphics and performant SVG animations — icons, illustrations, loaders, path-draw effects, morphing shapes, and motion paths. Load when the user asks to create SVG, draw an SVG icon, animate an SVG, make an SVG loader, path animation, shape morph, animated logo, line drawing effect, or improve trashy AI-generated SVG. Also triggers on "SVG animation", "SMIL", "stroke-dashoffset", "vector illustration", or "self-contained animated SVG".

Internal skill. Called by setup-evaluation after a PASS. Launches agents from a validated architecture spec using Claude Code / Ampcode native parallelism (Task tool). Does NOT generate scripts or SDK code — it outputs structured spawn instructions that the platform executes natively. Never invoked directly by the user. Never launches without a setup-evaluation PASS.

Gracefully retire a skill that is redundant, superseded, or no longer earning its place in the context window. Load when improve-skills finds a skill scoring 0-5/14 AND research confirms the domain is now handled natively by current models, when two skills have overlapping triggers and one subsumes the other, when the user asks to remove a skill, retire a skill, delete a skill, or clean up redundant skills, or when validate-skills flags a skill as a duplicate trigger risk. Handles removal cleanly: updates all callers, removes from AGENTS.md, updates README, and archives rather than deletes so the skill can be recovered if needed.

Score an unbuilt business idea on desirability, viability, feasibility, distribution wedge, why-now, founder-market-fit, market size, alternatives, defensibility, capital intensity, and regulatory/ethical risk — and return a GO / ITERATE / KILL verdict with kill criteria and a next kill test. Load when the user asks to evaluate a business idea, score a startup idea, screen an idea, decide whether to pursue this venture, do an idea review, or says "is this a good business idea", "should I build this", "evaluate this startup", "screen this idea", "go/no-go on this idea", "kill or pursue". Sub-skill of `venture-exploration`. Calls `fermi` for sizing, `assumption-mapping` for hidden beliefs, optional `pre-mortem` / `adversarial-hat` for high-stakes ideas. Does NOT evaluate built products — for that use `reality-check`.

Decompose tasks into structured, outcome-defined process entries with complexity triage. Load when user says "decompose this", "break this down", "what steps do I need", "plan this out", "what's the process for", "how do I approach this", or when any complex task needs structured execution planning. Includes a problem-understanding pass before complexity triage. Routes to `problem-to-plan` when the user needs planning deliverables (spec + plan + TODO). Does NOT replace brainstorming — brainstorming is design approval (upstream), this is execution planning (downstream).

Design and implement CI/CD pipelines and automation — fast checks on every PR, safe releases, and repeatable workflows. Load when setting up GitHub Actions (or similar), adding pre-merge gates, automating releases, or the user asks "add CI", "set up workflows", "automate checks", "CD pipeline". Not for one-off local scripts (use task-specific tooling).

Action (aeaz-action)

Use when a project's visual foundation — typography scale, color palette, spacing — needs establishing as canonical design tokens; the target has no design system yet (the 0→1 case), the A-Team design phase needs tokens for the lofi and the spec's design-system mapping, or a human runs the token flow standalone ("set up the design system", "pick fonts and colors", "define design tokens"). In the A-Team pipeline it is conducted by ateam-design in pipeline mode — no interview; inputs derive from context.md's

Use to CREATE or REVIEW a Job to be Done (JTBD) in Alan Klement's demand-side, progress-based sense — a job is the progress a customer is trying to make, never a task or feature. Trigger whenever someone wants to write or draft a JTBD, job statement, or job story; figure out the real motivation, struggle, or progress behind a feature, request, or product; understand why customers switch, adopt, or churn; turn interview notes or research into jobs; or pressure-test, sharpen, or rewrite existing JTBDs into proper jobs. Also trigger on "grill my JTBD", "is this a real job or just a task/feature", "what's the actual job here", "why would they switch". In an A-Team target repo, jobs are durable artifacts — this skill writes docs/product/jtbd/NN-<slug>.md per CONTRACT.md and never deletes or silently rewrites a job. Do NOT use for writing PRDs, roadmaps, tickets, or acceptance criteria (those consume a finished JTBD), or for implementation user stories.

Okr

Create and manage Zoom meetings and access cloud recordings via the Zoom API. Use for queries like "create a Zoom meeting", "list my Zoom meetings", "show my Zoom recordings", or "schedule a meeting for tomorrow".

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

Quantum physics simulation library for open quantum systems. Use when studying master equations, Lindblad dynamics, decoherence, quantum optics, or cavity QED. Best for physics research, open system dynamics, and educational simulations. NOT for circuit-based quantum computing—use qiskit, cirq, or pennylane for quantum algorithms and hardware execution.

Provides Gemini CLI delegation workflows for large-context analysis tasks, including English prompt formulation, execution flags, and safe result handling. Use when the user explicitly asks to use Gemini for a specific task such as broad codebase analysis or long-document processing. Triggers on "use gemini", "delegate to gemini", "run gemini cli", "ask gemini", "use gemini for this task".

Provides Qdrant vector database integration patterns with LangChain4j. Handles embedding storage, similarity search, and vector management for Java applications. Use when implementing vector-based retrieval for RAG systems, semantic search, or recommendation engines.

Sketch - Collaborative SVG Canvas

Provides astronomical data analysis capabilities including coordinate transformations, unit conversions, FITS file handling, cosmological calculations, time systems, and table operations.

A funnel and account-scoring diagnostic engine for any sales org. Connect a CRM and a product-analytics tool (plus optional enrichment, community, and meeting tools). Three modes. (1) FUNNEL DIAGNOSIS finds leaky conversion gates by channel with per-stage leakage, dollarized leverage points, and cohort velocity. (2) SPRINT PLANNING enriches qualified accounts into a ranked backlog with verified buying committees. (3) SCORING AUDIT finds where your scoring model is missing real ICPs. Trigger on 'funnel diagnosis', 'diagnose the funnel', 'where are we leaking', 'why is [channel] underperforming', 'conversion by channel', 'sprint planning', 'score these accounts', 'find missed ICPs', 'audit the scoring model', or any channel-level cohort-conversion, account-prioritization, or scoring-gap question.

Turn a pipeline target into a demand-generation plan that actually maps to the number. The ICP worth spending on, the offers by funnel stage, the channel mix that reaches them, the content that earns attention, and the pipeline math worked backward from the goal so you know if the plan can even hit it. Built for B2B marketing teams, customizable to your funnel and your channels. Trigger on "build a demand gen plan", "how do we hit our pipeline number", "what's our channel mix", "plan our content", "work the funnel math backward", or any demand-generation planning question.

>- Run automatic SPICE simulations on subcircuits detected from KiCad schematic analysis — validates filter frequencies, divider ratios, opamp gains, LC resonance, and crystal load capacitance. Supports ngspice, LTspice, and Xyce (auto-detected). Generates testbenches, runs batch mode, produces structured pass/warn/fail report. Use when the user asks to simulate, verify, or validate any analog subcircuit — RC filters, LC filters, voltage dividers, opamp circuits, crystal oscillators. Also for "simulate my circuit", "run spice", "verify with simulation", "check my filter cutoff", "does this divider give the right voltage", "what's the bandwidth of this opamp stage". Consider suggesting simulation during design reviews when the schematic analyzer reports simulatable subcircuits and a SPICE simulator is available.

Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity.

SKILL — Mobile UX

Web3 Frontend Integration

Configure s3 lifecycle config operations. Auto-activating skill for AWS Skills. Triggers on: s3 lifecycle config, s3 lifecycle config Part of the AWS Skills skill category. Use when configuring systems or services. Trigger with phrases like "s3 lifecycle config", "s3 config", "s3".

Nemotron-4 340B Technical Report

Towards Open-World Segmentation of Parts

SVIT: Scaling up Visual Instruction Tuning

DocVQA: A Dataset for VQA on Document Images

Training Compute-Optimal Large Language Models

Mantis: Interleaved Multi-Image Instruction Tuning

Gemini: A Family of Highly Capable Multimodal Models

LLaVA-NeXT: Improved Reasoning, OCR, and World Knowledge

MMBench: Is Your Multi-modal Model an All-around Player?

Senior SecOps engineer skill for application security, vulnerability management, compliance verification, and secure development practices. Runs SAST/DAST scans, generates CVE remediation plans, checks dependency vulnerabilities, creates security policies, enforces secure coding patterns, and automates compliance checks against SOC2, PCI-DSS, HIPAA, and GDPR. Use when conducting a security review or audit, responding to a CVE or security incident, hardening infrastructure, implementing authentication or secrets management, running penetration test prep, checking OWASP Top 10 exposure, or enforcing security controls in CI/CD pipelines.

Use CALL-E from Codex through the calle CLI. Use for CALL-E setup checks, authentication recovery, phone call planning, planned call execution, and call status checks.

Use Zotero Desktop from Codex to enable/probe the local API, search a local Zotero library, list items/collections/tags, export BibTeX, insert citation keys into LaTeX or Markdown drafts, read indexed full text when requested, and import BibTeX/RIS records into Zotero through the connector server. Use when the user mentions Zotero, citations, references.bib, BibTeX export, local Zotero API, localhost:23119, or adding citations from a Zotero library.

BOM (Bill of Materials) management for electronics projects — the primary orchestrator skill that coordinates DigiKey, Mouser, LCSC, element14, JLCPCB, PCBWay, and KiCad skills into a unified workflow. Create, update, and maintain BOMs with part numbers, costs, quantities stored as KiCad symbol properties. ALWAYS trigger this skill for any task involving component sourcing, pricing, ordering, distributor searches, BOM export, or fabrication preparation — even if the user names a specific distributor or fab house (e.g. "search DigiKey for...", "generate JLCPCB BOM", "order from Mouser"). This skill decides which distributor/fab skills to invoke and in what order. Also trigger on phrases like "what parts do I need", "order components", "how much will this cost", "export for JLCPCB", "find parts for this board", "cost estimate", "compare pricing", or "check stock".

Specialized agent for developing AIUI applications. Invoke when writing AIUI code, needing API references for jsui/wx, debugging AIUI applications, or aligning AIUI visual design with this Skill's design guidelines.

Guide for setting up vcpkg in C++ projects, managing dependency versions, and cross-compiling. Covers manifest initialization, CMake and Visual Studio integration, classic-to-manifest migration, version pinning, baselines, overrides, triplets, and cross-compilation. Use when a user is working with vcpkg project setup, installation, version management, or cross-platform builds. For specialized tasks, additional references cover custom registries and overlay ports (references/registries.md), CI/CD and binary caching (references/ci.md), and troubleshooting and dependency lifecycle (references/troubleshooting.md).

Generate draw.io diagrams as .drawio files and export to PNG/SVG/PDF with embedded XML

Skill for using the command-line tool pdftk (PDFtk Server) for working with PDF files. Use when asked to merge PDFs, split PDFs, rotate pages, encrypt or decrypt PDFs, fill PDF forms, apply watermarks, stamp overlays, extract metadata, burst documents into pages, repair corrupted PDFs, attach or extract files, or perform any PDF manipulation from the command line.

Edit existing video on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Wan 2.7 Edit-Video (general restyle / background swap / packaging swap, identity + motion preservation), Kling 2.6 Pro Motion Control (transfer precise motion from a reference video to a target character), or Lucy Edit Restyle (lightweight identity-stable restyle / outfit swap). Bundles each model's documented prompting patterns so the skill gets sharper edits without burning iterations on the wrong model. Calls `runcomfy run <vendor>/<model>/<endpoint>` through the local RunComfy CLI. Triggers on "video edit", "edit video", "restyle video", "swap video background", "motion control", "outfit swap video", or any explicit ask to transform a video.

Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. Routes across Wan 2-7 edit-video (default, prompt-driven region edits with spatial language), Lucy Edit Restyle (identity-stable region-aware restyle), and Seedream 4-0 edit-sequential (when treating the clip as a frame stack). Picks the right route based on whether the change is prose-driven, identity-locked, or needs frame-by-frame still inpaint chained into a video. Triggers on "video inpaint", "video inpainting", "remove from video", "mask region in video", "clean up video", "remove object from clip", "video patch", "frame-by-frame edit", "remove watermark from video", "remove passing person", or any explicit ask to edit a region across video frames.

Rigorous market researcher for Prodig Suites. Use for competitor analysis, demand signal analysis, gap identification, market intelligence. Triggers: 'market research', 'competitor analysis', 'demand validation', 'market gaps', 'opportunity research', 'competitive landscape'.

Executes the 6-phase SOSTAC marketing planning framework. Use when the user requests 'SOSTAC', 'marketing plan', 'situation analysis', 'marketing strategy', or 'marketing objectives'.

Builder of templates, prompt packs, kits, swipe files, and reusable digital assets. Trigger when user requests 'create template', 'build prompt pack', 'assemble digital kit', 'make swipe file', or 'produce reusable assets'.