发现 Skills

Database management and queries. Connect to SQL and NoSQL databases, run queries, and manage schemas.

AI-powered atomic habit tracker with natural language logging, streak tracking, smart reminders, and coaching. Use for creating habits, logging completions naturally ("I meditated today"), viewing progress, and getting personalized coaching.

Repository structure, settings, CI/CD, and team configuration — audit and setup. Use for repo health, branch policies, CI validation, or team onboarding.

Systematic evaluation (Evals) for LLMs and AI products. Design test cases, measure accuracy and quality, track regressions, benchmark models, and build continuous evaluation pipelines. Distinct from traditional software testing because outputs are probabilistic.

General-purpose Static Application Security Testing (SAST) skill for code vulnerability analysis. Trigger when the user asks to: "analyze code for vulnerabilities", "review code security", "find security bugs", "do a SAST scan", "check for [vulnerability type] in code", "audit source code", or requests a security code review of any language or framework. Covers 34 vulnerability classes across web, API, auth, mobile, and logic layers.

53-point conversion audit covering customer focus, narrative arc (Pain-Dream-Fix), copy quality, design, CTAs, and proof. Scored report with prioritized fixes.

Interactive plan and diff review for AI coding agents. Visual browser UI for annotating agent plans — approve or request changes with structured feedback. Supports code review, image annotation, and auto-save to Obsidian/Bear Notes.

Backtest, deploy, and monitor trading bots on Hyperliquid. Supports Grid, DCA, and Spot-Perp Arbitrage strategies across Native Perps, Spot markets (USDC/USDH), and HIP-3 sub-DEXes.

CLI tools for Svelte 5 documentation lookup and code analysis. MUST be used whenever creating or editing any Svelte component (.svelte) or Svelte module (.svelte.ts/.svelte.js). If possible, this skill should be executed within the svelte-file-editor agent for optimal results.

Inspect edited files, group them into logical commits, and create focused commits for this repo. Use when: the user asks to commit changes, split work into focused commits, or decide how the current diff should be grouped before committing.

Dedicated workflow for creating, running, and analyzing tests across all levels (unit, integration, e2e). Auto-detects the project's testing framework, provides templates by test type, and analyzes coverage gaps. Use when writing tests, improving coverage, setting up test infrastructure, or validating implementations. Triggers on "write tests", "add tests", "test this", "improve coverage", "testing strategy", "what should I test", "set up testing". Do NOT use for debugging test failures in CI (use gh-fix-ci) or for running tests as part of branch finalization (use finalize-branch).

Provides MoAI-ADK foundational principles including the TRUST 5 quality framework, SPEC-First DDD methodology, delegation patterns, progressive disclosure, and an agent catalog reference. Use this when referencing TRUST 5 gates, the SPEC workflow, EARS format, DDD methodology, agent delegation patterns, or MoAI orchestration rules. Do NOT use this for context and token management (use moai-foundation-context instead) or for strategic analysis (use moai-foundation-philosopher instead).

Electron 33+ desktop app development specialist covering Main/Renderer process architecture, IPC communication, auto-update, packaging with Electron Forge and electron-builder, and security best practices. Use when building cross-platform desktop applications, implementing native OS integrations, or packaging Electron apps for distribution. [KO: Electron 데스크톱 앱, 크로스플랫폼 개발, IPC 통신] [JA: Electronデスクトップアプリ、クロスプラットフォーム開発] [ZH: Electron桌面应用、跨平台开发]

Design themes built bottom-up through validated foundational layers. Each layer is applied and verified in isolation before the next is introduced. No layer references concepts from a later layer. Triggers: theme design, design layer, design init, design load, design enhance, design spec, export syntax, color palette, typography system.

Use criminal policy statistics and studies portal for crime trends, victimization studies, and justice-policy evidence.

Query Estonia Medicines Register for medicinal-product records, authorization metadata, and regulatory status context.

Use state port register sources for official port registry information and maritime infrastructure governance context.

Retrieve macro-financial and monetary statistics from the Bank of Estonia statistics portal for banking, external sector, and monetary analysis.

Router for Three.js post-processing effects domain. Use when implementing visual effects like bloom, glow, chromatic aberration, vignette, depth of field, color grading, or any screen-space effects. Routes to 3 specialized skills for bloom, effects, and composer setup.

This skill should be used when users ask to prepare MaxwellLink input files; it scaffolds a new `projects/YYYY-MM-DD-NAME/` folder from copy-ready templates and provides basic validation.

Daily website grammar proofreader. Crawls all pages of configured websites, checks for grammatical errors using AI, and emails a detailed report. Runs automatically at 6 AM IST via cron. Use 'run proofreader' to check manually or 'add website proofreader' to add new sites.

How this integration talks to Marstek devices via the local Open API over UDP (JSON messages) and how to handle errors safely

Competitive analysis framework with SWOT and market positioning

Report ground-truth Claude token consumption and estimated cost by parsing JSONL session files directly. Use when checking API spend, auditing token usage by project/session/model, generating daily/weekly/monthly cost reports, or diagnosing ccusage undercounting. Includes subagent files that ccusage ignores.