Other Skills

JAXSR is a JAX-based symbolic regression library that discovers interpretable algebraic expressions from data using sparse optimization. It follows ALAMO-style methodology: build a rich candidate basis, then select the simplest model that explains the data.

This skill provides comprehensive guidance for creating and editing custom shaders for Ghostty terminal. Ghostty uses Shadertoy-compatible GLSL ES 3.0 (WebGL 2.0) shaders with additional terminal-specific extensions.

Use this skill when: - Working with component similarity calculations using metadata-driven architecture - Configuring spec importance levels and tolerance rules - Understanding context-aware similarity profiles - Converting legacy similarity calculators to metadata-driven approach - Troubleshoot...

包括的なSEO最適化スキル（日本語版）。Googleの公式ガイドラインに基づく技術SEO、コンテンツSEO、構造化データ、Core Web Vitals、E-E-A-T対策を網羅し、実践的なコード生成とサイト監査ワークフローを提供

Use when working with component similarity calculations - comparing MPNs, finding equivalent parts, implementing new similarity calculators, or understanding how component matching works.

Use this skill when working with MPN (Manufacturer Part Number) normalization, package suffix handling, and component equivalence checking.

Roll dice and interpret results for tabletop RPGs using RANDSUM notation. Use this skill whenever a user asks to roll dice, wants a random result, needs a game mechanic simulated, or mentions TTRPGs — even casually (e.g. "roll for me", "give me a strength score", "what do I get?").

Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.

Analyze probability distributions for RANDSUM dice notation. Use when users ask about odds, expected values, probability of specific outcomes, or want to compare different roll strategies. Handles standard dice, drop/keep, advantage/disadvantage, rerolls, exploding dice, and game-system outcomes.

Use this skill when working with component equivalent groups, cross-manufacturer part matching, or understanding hardcoded equivalencies.

Add Rokt/Untitled UI icons to the Aquarium library. Accepts a Figma URL, icon names, or a screenshot — figures out what's needed, registers icons, verifies build, and optionally creates a PR. Designed for designers.

Interactive supply chain dashboard mapping suppliers, customers, and financial interdependencies

Base skill for working with electronic components in this library. Use when adding new component types, manufacturer handlers, or working with MPN (Manufacturer Part Number) operations, BOM entries, or component classification.

Add a new mParticle SVG icon to the Aquarium library. Handles SVG optimization, registration, type updates, and exports. Use when adding a new icon from an SVG file. Triggers on add icon, new icon, add svg, mp icon, mparticle icon.

发布内容和文章到 X (Twitter)。支持常规推文(文字/图片/视频)和 X Articles(长文 Markdown)。使用真实 Chrome 浏览器绕过反机器人检测。当用户说"发推"、"发到 X"、"发到 twitter"、"分享到 X"、"分享到 twitter"、"发 tweet"、"同步到 X"、"发布到 X"、提到"X Articles"、想从 Obsidian 笔记发布长文内容、或需要转换 Obsidian Markdown 到 X 格式时使用。适用于所有 X/Twitter 发布任务。

Use when working with Jackson JSON serialization - migrating from Jackson 2.x to 3.x, configuring JsonMapper, handling date/time types, or troubleshooting serialization issues.

Use this skill when converting existing similarity calculators to the metadata-driven approach with configurable, type-specific rules.

ONLY use when user explicitly says 'deep research', 'exhaustive', 'comprehensive report', or 'thorough investigation'. Slower and more expensive than parallel-web-search. For normal research/lookup requests, use parallel-web-search instead.

Bulk data enrichment. Adds web-sourced fields (CEO names, funding, contact info) to lists of companies, people, or products. Use for enriching CSV files or inline data. Supports multi-turn: pass --previous-interaction-id from a prior research or enrichment to carry context forward.

Use when working with connector components - headers, sockets, wire-to-board, board-to-board connectors. Includes adding patterns, parsing connector MPNs, extracting pin count, pitch, and series information.

Use this skill when working with ComponentType enum, type detection from MPNs, specificity scoring, or getBaseType() mapping.

Product Owner - scans codebase and creates or amends GitHub issues with PRD. Use when: PRD, feature, issue, create issue, amend issue, what should we build, plan feature, design feature, scope, requirements.

Use when working with logic IC similarity calculations - comparing 74xx series, CD4000 CMOS, technology families (LS, HC, HCT), function groups (NAND, NOR, flip-flops), or logic IC-specific similarity logic.

DEFAULT for all research and web queries. Use for any lookup, research, investigation, or question needing current info. Fast and cost-effective. Only use parallel-deep-research if user explicitly requests 'deep' or 'exhaustive' research.

Use when working with discrete semiconductor components - diodes, transistors, MOSFETs, IGBTs. Includes adding patterns, parsing MPNs, extracting voltage/current ratings, and package codes.

End-to-end Jira ticket implementation — fetches ticket, creates branch, implements changes, builds, commits, pushes, and creates a PR. Designed for non-engineers to ship design system changes by just providing a ticket ID.

Use when working with sensor similarity calculations - comparing temperature/accelerometer/humidity sensor MPNs, understanding sensor families, equivalent parts, or sensor-specific similarity logic.

Use when working with memory IC similarity calculations - comparing EEPROM/Flash MPNs, understanding I2C/SPI interface matching, equivalent groups across manufacturers, or memory-specific similarity logic.

Use when working with op-amp similarity calculations - comparing op-amp MPNs, understanding single/dual/quad configurations, equivalent families like LM358/MC1458, or op-amp-specific similarity logic.

Use when working with memory components - Flash, EEPROM, SRAM, DRAM. Includes adding patterns, parsing memory MPNs, extracting capacity, interface type, and speed information.