发现 Skills

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Obsidian Knowledge Architect based on Progressive Summarization. Generates three-layer structure: Index -> Summary -> Detail. Always appends, never overwrites.

Configure Alembic for async SQLAlchemy migrations with PostgreSQL

Alias corto para migracion Web a Desktop con Tauri en stack React + NestJS + Postgres en LAN. Usar para aplicar flujo de planificacion, implementacion, verificacion y release con sidecar y reglas de red.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Conduct comprehensive research on any topic by coordinating 2-4 specialized researcher agents in parallel, then synthesizing findings into a detailed report via mandatory report-writer agent delegation (Full workflow documentation at docs/workflows/research-workflow.md)

Set up Stripe CLI to forward webhooks to local development server for testing Stripe integrations

Generate story specification Markdown files for various fiction genres. Use when: (1) The user says "write a [genre] story" in pinyin (e.g., "tonghua", "wuxia", "kehuan"). (2) The user says a phrase like "策划/设计一个[类型]类别的小说" (for example: "童话故事" = fairy tale, "武侠江湖" = wuxia, "科幻小说" = science fiction). (3) The user wants to design or plan a new story before writing. (4) The user mentions story design, story spec, or story planning for fiction. Supported genres: tonghua / fairy tale, dushi / urban romance, gufeng / ancient-political (gufeng), kehuan / science fiction, keji / tech startup, kepu / popular science / documentary, kongbu / horror / paranormal, lishi / historical military, mori / post-apocalyptic survival, qingchun / youth / campus, wuxia / wuxia, xianyan / contemporary romance, xuanhuan / fantasy cultivation, xuanyi / suspense / detective, yiliao / medical & life.

Installs a championship execution state for high-stakes work: lawful non-linear breakthrough, decisive leverage, pressure stability, truth-cutting, and terminal-state contact. Use when the task is hard, high-pressure, ambiguous, competitive, or near the limit of current ability. Activates when the user asks for extreme standards, breakthrough performance, pressure handling, first-principles focus, or direct jumps from essence to end-state. Highest-priority triggers: `Champion Heart`, `Champion Heart.skill`. <example> User: "This is the key battle. Enter champion mode and find the shortest true path." Assistant: "I’ll use Champion Heart to locate the decisive leverage, test whether a lawful leap exists, and strike the shortest true path." </example> <example> User: "This has high stakes. Enable champion mode — don’t do window dressing, find the shortest true path directly." Assistant: "I will use Champion Heart: first find the decisive leverage, determine whether a lawful jump path exists, and then produce the shortest true path." </example>

TDD/BDD workflows for FastAPI + React stack with pytest, vitest, and integration testing. Use when writing tests, configuring test runners, or implementing test-driven development.

ZeroDB vector database best practices, semantic search patterns, RLHF workflows, and memory management. Use when working with ZeroDB APIs, vector search, or AI memory systems.

Designs retrospective or prospective clinical cohort study protocols for biomedical and clinical research. Always use this skill when the user needs a cohort-based study plan rather than a general study idea, evidence summary, or mechanistic experiment design. Focus on cohort appropriateness, enrollment logic, baseline time-zero definition, follow-up structure, endpoint definition, variable collection, confounding control, and a coherent primary statistical analysis line. Do not invent data availability, follow-up completeness, outcome ascertainment quality, sample size adequacy, or causal interpretability.

Generates complete FAERS-style pharmacovigilance disproportionality research designs from a user-provided drug class, comparator strategy, adverse-event domain, and patient-group stratification. Always use this skill whenever a user wants to design, plan, or build a spontaneous-report safety signal study using FAERS or a similar pharmacovigilance database, especially when the article logic includes product selection, indication-group stratification, MedDRA-based adverse-event extraction, serious-case filtering, suspect-drug and concomitant-exclusion logic, reporting odds ratio analysis, comparator-drug benchmarking, cross-drug comparison, and cautious signal interpretation without causal overclaiming. Covers five study patterns (single-drug disproportionality workflow, multi-drug class comparison workflow, indication-stratified workflow, comparator-controlled signal screening workflow...

Search FDA industry guidelines by therapeutic area or topic.

Retrieve the latest journal issue's table of contents and abstracts from URL/DOI/PMID/RSS/TOC sources, then generate Chinese key points locally (no external translation APIs) when a new issue needs quick review and archiving.

Generates a structured reading tweet from an academic paper (PDF, Word, or Text), highlighting specific product advantages. Use when the user wants to turn a document into a social media post or reading summary.

Context for ongoing migration from old Portfolio Buddy app. Use when: fixing bugs, adding migrated features, checking feature parity, or understanding why certain code exists. Contains list of 40 features being migrated and known issues.

Auto-detects project language and framework from package.json, pyproject.toml, Cargo.toml, go.mod, and other configuration files with comprehensive pattern matching based on 17,253+ production code examples.

Enterprise Clerk authentication platform with an AI-powered modern identity architecture, Context7 integration, and intelligent user-management orchestration for scalable applications.

Enhanced documentation generation with AI-powered features. Augmented by Context7 MCP for up-to-date documentation.

AI-powered enterprise document processing orchestrator with Context7 integration, intelligent document analysis, automated content extraction, multi-format support (docx, pdf, pptx, xlsx), and enterprise-grade document workflow automation

Audit Azure Policy assignments at management group or subscription scope, map to MCSB control domains, identify coverage gaps, detect conflicts/duplicates, and generate a remediation plan for missi...

Validate, lint, audit, or check Makefiles and .mk files for errors.