Loading...
Loading...
Found 2,175 Skills
Semantic skill discovery and routing using GraphRAG, vector embeddings, and multi-tool search. Automatically matches user intent to the most relevant skills from 144+ available options using ck semantic search, LEANN RAG, and knowledge graph relationships. Triggers on /meta queries, complex multi-domain tasks, explicit skill requests, or when task complexity exceeds threshold (files>20, domains>2, complexity>=0.7).
Structured paragraph curation for C5: **select -> evaluate -> subset -> fuse**, so drafts converge instead of only expanding. **Trigger**: paragraph curator, curation, select evaluate fuse, paragraph selection, 选段, 评价, 融合, 收敛, 去冗余. **Use when**: you are in C5, `sections/*.md` exist, and the writing loop drifts toward 'longer by accumulation' (repetition, redundant paragraphs, weak synthesis). **Skip if**: evidence packs are thin / `evidence-selfloop` is BLOCKED; or you are pre-C2 (NO PROSE). **Network**: none. **Guardrail**: do not invent facts; do not add/remove citation keys; do not move citations across subsections; keep section-level claims consistent with `output/ARGUMENT_SKELETON.md# Consistency Contract`.
Scout price discrepancies between Polymarket and Kalshi for discovery and comparison. Read-only; no execution.
TypeScript bot implementing dump-and-hedge arbitrage strategy on Polymarket 15-minute Up/Down prediction markets with CLOB order execution and simulation mode.
Alibaba Cloud Tablestore Agent Storage Skill. Use for building and managing Tablestore-based knowledge bases with the `tablestore-agent-storage` Python SDK. Capabilities: - Install and configure the `tablestore-agent-storage` SDK - Create, describe and list knowledge bases (with subspace and custom metadata support) - Upload local files or import OSS documents into a knowledge base - Query document status and list documents - Perform hybrid retrieval (dense vector + full-text) with metadata filtering - Set up local directory sync scripts and scheduled tasks for automatic knowledge base updates Triggers: "知识库", "tablestore", "ots", "表格存储", "agent storage", "knowledge base", "向量检索", "文档上传", "文档导入", "知识库同步", "tablestore-agent-storage", "AgentStorageClient"
Test coverage analysis, identify gaps, and generate missing tests to achieve over 80% coverage. Trigger conditions: user requests for test coverage analysis, test coverage improvement, and test writing.
Baidu Netdisk file management - supports upload, download, transfer, share, search, move, copy, rename, and folder creation. TRIGGER: Activated when the user mentions "百度网盘/bdpan/网盘/云盘/baidu drive" and the request involves file operations. DO NOT TRIGGER: For non-file storage operations, or when users are using other cloud storage services.
DigitalOcean storage services including Spaces object storage, Volumes block storage, NFS, Snapshots, and Backups. Use when selecting or managing storage for DigitalOcean workloads.
Analyze test coverage gaps and generate tests to improve coverage. Use when improving test coverage, finding untested code, or writing missing tests.
[Pragmatic DDD Architecture] Guide for creating tests. Use when creating unit tests, integration tests, or understanding test conventions. Covers our tightly coupled stack: Vitest (unit, integration, ui projects), file naming, transactional database integration tests (txTest) with testcontainers/node-postgres/drizzle, mock patterns (createMock*RepoWithAssertions), and neverthrow Result assertions.
[Pragmatic DDD Architecture] Guide for creating DDD Value Objects (VOs). Use when defining a new Value Object in a domain layer. Covers immutability patterns, private constructors, random/from builders, Railway-oriented error handling via neverthrow Result, TypeScript branded error types, and co-locating errors within the VO file.
[Pragmatic DDD Architecture] Guide for creating PostgreSQL tables and defining relations using Drizzle ORM. Use when creating new schemas, managing PostgreSQL indexes, enums, mapping column names to camelCase for the domain, and explicitly exporting constraint names.