Loading...
Loading...
Found 74 Skills
Expert in aggregating, processing, and synthesizing information from multiple sources into coherent insights. Use when building knowledge graphs, ontologies, RAG systems, or extracting insights across documents. Triggers include "knowledge graph", "ontology", "synthesize information", "GraphRAG", "insight extraction", "cross-document analysis".
Logic coherence pass for per-H3 section files: enforce a clear paragraph-1 thesis and surface paragraph-island risks (connector stats are diagnostic, not a quota) before merging. **Trigger**: logic polisher, section logic, thesis statement, connectors, 段落逻辑, 连接词, 论证主线, 润色逻辑. **Use when**: `sections/S*.md` exist but read like paragraph islands; you want a targeted, debuggable self-loop before `section-merger`. **Skip if**: sections are missing/thin (fix `subsection-writer` first) or evidence packs/briefs are scaffolded (fix C3/C4 first). **Network**: none. **Guardrail**: do not add new citations; do not invent facts; do not change citation keys; do not move citations across subsections.
Analyzes events through narrative lens using story structure, character arc analysis, dramatic tension, thematic development, and narrative theory (three-act structure, hero's journey, conflict-resolution). Provides insights on narrative coherence, character motivations, dramatic stakes, plot development, and thematic resonance. Use when: Complex human stories, leadership analysis, organizational narratives, crisis narratives, cultural moments. Evaluates: Character development, narrative arc, dramatic tension, thematic depth, symbolic meaning, narrative coherence.
Analyzes fundamental questions and concepts through philosophical lens using logic, epistemology, metaphysics, and critical analysis frameworks. Provides insights on meaning, truth, knowledge, existence, reasoning, and conceptual clarity. Use when: Conceptual ambiguity, logical arguments, foundational assumptions, meaning questions. Evaluates: Validity, soundness, coherence, assumptions, implications, conceptual clarity.
Combines search results from multiple sources into coherent, deduplicated answers with source attribution. Handles confidence scoring based on freshness and authority, and summarizes large result sets effectively.
Turn an engineering strategy into a written Technical Roadmap Pack (Rumelt-style strategy: Diagnosis/Guiding Policy/Coherent Actions, roadmap table, initiative briefs, and alignment cadence). Use for technical roadmap, tech roadmap, engineering roadmap, architecture roadmap.
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
Research and compile the latest AI news from across the industry. Use this skill when asked to find AI news, get AI updates, research what's happening in AI, check for AI announcements, or gather intelligence on AI companies. Triggers include requests for "AI news", "latest AI developments", "what's new in AI", "AI industry updates", or news about specific AI companies (OpenAI, Anthropic, Google, Microsoft, Meta, Amazon, Nvidia, xAI, Mistral, Cohere, Apple, Salesforce).
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
PostgreSQL-based semantic and hybrid search with pgvector and ParadeDB. Use when implementing vector search, semantic search, hybrid search, or full-text search in PostgreSQL. Covers pgvector setup, indexing (HNSW, IVFFlat), hybrid search (FTS + BM25 + RRF), ParadeDB as Elasticsearch alternative, and re-ranking with Cohere/cross-encoders. Supports vector(1536) and halfvec(3072) types for OpenAI embeddings. Triggers: pgvector, vector search, semantic search, hybrid search, embedding search, PostgreSQL RAG, BM25, RRF, HNSW index, similarity search, ParadeDB, pg_search, reranking, Cohere rerank, pg_trgm, trigram, fuzzy search, LIKE, ILIKE, autocomplete, typo tolerance, fuzzystrmatch
LaTeX Assistant for Chinese Academic Theses (PhD/Master's). Fields: Deep Learning, Time Series, Industrial Control. Trigger Words (call any module independently): - "compile", "compile", "xelatex" → Compilation Module - "structure", "structure", "map" → Structure Mapping Module - "format", "format", "GB/T", "national standard" → National Standard Format Checking Module - "expression", "expression", "polish", "academic expression" → Academic Expression Module - "logic", "coherence", "logic", "cohesion", "methodology", "methodology" → Logical Cohesion & Methodology Depth Module - "long sentence", "long sentence", "split" → Long & Complex Sentence Analysis Module - "bib", "bibliography", "bibliography" → Bibliography Module - "template", "template", "thuthesis", "pkuthss" → Template Detection Module - "deai", "de-AI editing", "humanize", "reduce AI traces" → De-AI Editing Module - "title", "title", "title optimization", "generate title" → Title Optimization Module
Audit-style editing pass for `output/DRAFT.md`: remove template boilerplate, improve coherence, and enforce citation anchoring. **Trigger**: polish draft, de-template, coherence pass, remove boilerplate, 润色, 去套话, 去重复, 统一术语. **Use when**: a first-pass draft exists but reads like scaffolding (repetition/ellipsis/template phrases) or needs a coherence pass before global review/LaTeX. **Skip if**: the draft already reads human-grade and passes quality gates; or prose is not approved in `DECISIONS.md`. **Network**: none. **Guardrail**: do not add/remove/invent citation keys; do not move citations across subsections; do not change claims beyond what existing citations support.