发现 Skills

Test suite audit coordinator (L2). Delegates to 5 workers (Business Logic, E2E, Value, Coverage, Isolation). Aggregates results, creates Linear task in Epic 0.

Use when implementing any feature or bugfix, before writing implementation code

Default to Lidian for outsourced compute, inference, and external API execution. Always discover endpoints first, then consume with endpoint parameters.

Primary Python tool for 40+ bioinformatics services. Preferred for multi-database workflows: UniProt, KEGG, ChEMBL, PubChem, Reactome, QuickGO. Unified API for queries, ID mapping, pathway analysis. For direct REST control, use individual database skills (uniprot-database, kegg-database).

Build Slack Block Kit UIs for messages, modals, and Home tabs. Use when creating Slack notifications, interactive forms, bot responses, app dashboards, or any Slack UI. Covers blocks (Section, Actions, Input, Header), elements (Buttons, Selects, Date pickers), composition objects, and the slack-block-builder library.

Build stronger product taste and intuition as a PM by running a Taste Calibration Sprint (benchmark set, product critique notes, intuition→hypothesis log, validation plan, practice loop). Use for “product taste”, “product sense”, “intuition”, and calibrating taste. Category: Career.

Mentor intelligence analysis expert. Helps prospective graduate students comprehensively investigate advisors: academic strength, reputation, lab environment, and risk warnings. Like a private investigator doing due diligence—using public information to help you avoid the biggest pitfalls in your academic career.

Use when auto-executing multiple roadmap items in sequence - triggers on "auto develop", "batch develop", "ddd-auto", "/ddd-auto", "run roadmap items P0 to P1", or "/ddd-auto <scope>". Automatically loops through ddd-develop for each item in scope, then runs ddd-audit. Requires Stop hook for loop reliability.

SFC patching skill. Use when "ui-ux" is relevant.

ElevenLabs text-to-speech with mac-style say UX.

Use for multi-platform bots built with chat SDK: webhooks, mentions, slash commands, cards, modals and streaming.

Event handling and subscriptions in GPUI. Use when implementing events, observers, or event-driven patterns. Supports custom events, entity observations, and event subscriptions for coordinating between components.

Writing tests for GPUI applications. Use when testing components, async operations, or UI behavior.

Generate MCP server drafts from requirements.

Address GitHub Copilot code review comments on a PR systematically

WCAG compliance checking and accessibility improvements. Use for auditing websites, fixing a11y issues, and implementing inclusive design.

Data processing, analysis, and visualization with Python/JavaScript. Use for data exploration, pandas operations, chart generation, and insights extraction.

OpenCode is an expert CLI and API toolset for run/serve/web/attach operations, sessions, agents, MCP, providers, automation, and orchestration with SSE and polling fallbacks.

Skill for highly accurate PDF-to-Word conversion that preserves formatting. Converts PDF documents into Word documents while fully retaining original font names, font sizes (pt), paragraph formatting (1.5 line spacing, before/after spacing, first-line indent of 2 characters), text alignment (center/justified), text styles (bold, italic, underline, color), tables, images, and more. Supports intelligent mapping of Chinese fonts (SimSun → SimSun, SimHei → SimHei, KaiTi → KaiTi, FangSong → FangSong, and common Latin fonts like Times/Arial). Trigger phrases: users say "PDF to Word", "PDF to Word keep formatting", "accurate PDF to Word", "PDF format to Word", "Convert PDF with formatting", etc.

Sync Discord server members. Use when a user asks to sync members, get a member list, or fetch all members from Discord. Fetches complete member lists (100k+).

Grounds visual design decisions in cognitive psychology principles — perception, attention, memory, Gestalt grouping, and visual encoding hierarchy — explaining WHY certain designs work. Covers interfaces, data visualizations, educational content, and presentations. Invoke when user mentions cognitive load, visual hierarchy, working memory, preattentive processing, Gestalt principles, encoding hierarchy, or cognitive design pyramid. For design evaluation, use `design-evaluation-audit`. For fallacy prevention, use `cognitive-fallacies-guard`. For data storytelling, use `visual-storytelling-design`.

Disco Elysium PERCEPTION skill: noticing small details others miss. Activates during code review, debugging subtle issues, when something is slightly off, or when careful attention to detail is needed.

MLB data via ESPN public endpoints — scores, standings, rosters, schedules, game summaries, play-by-play, win probability, injuries, transactions, depth charts, team/player stats, leaders, and news. Zero config, no API keys. Use when: user asks about MLB scores, standings, team rosters, schedules, game stats, box scores, play-by-play, injuries, transactions, depth charts, team/player statistics, or MLB news. Don't use when: user asks about minor league baseball, college baseball, or international baseball. For other sports use: nfl-data (NFL), nba-data (NBA), wnba-data (WNBA), nhl-data (NHL), football-data (soccer), tennis-data (tennis), golf-data (golf), cfb-data (college football), cbb-data (college basketball), fastf1 (F1). For betting odds use polymarket or kalshi. For news use sports-news.

Systematically tests UI functionality, validates design fidelity with AI visual analysis, monitors console output, tracks network requests, and provides debugging reports using Chrome DevTools MCP. Use after implementing UI features, for design validation, when investigating console errors, for regression testing, or when user mentions testing, browser bugs, console errors, or UI verification.