agent

research-synthesize — an installable skill for AI agents, published by ruvnet/ruflo.

Guides implementation of agent memory systems, compares production frameworks (Mem0, Zep/Graphiti, Letta, LangMem, Cognee), and designs persistence architectures for cross-session knowledge retention. Use when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph for agents", "track entities over time", "add long-term memory", "choose a memory framework", or mentions temporal knowledge graphs, vector stores, entity memory, adaptive memory, dynamic memory or memory benchmarks (LoCoMo, LongMemEval).

Orchestrate multi-phase deep research with web search, memory retrieval, pattern matching, and synthesis into structured findings

Create a detailed execution plan/spec/prd for implementing features or refactors in a codebase by leveraging existing research in the codebase.

Query knowledge artifacts across all locations. Triggers: "find learnings", "search patterns", "query knowledge", "what do we know about", "where is the plan".

Look up current research information using parallel-cli search (primary, fast web search), the Parallel Chat API (deep research), or Perplexity…

Technical documentation specialist and knowledge curator. Use when the user asks to talk to Paige or requests the tech writer.

Aggregate and display system metrics with anomaly detection for a time period

Extract entities and relations from source files to build a knowledge graph

Pathfinder traversal of the knowledge graph starting from a seed entity

Transforms research findings into executive-ready briefings. Automatically activated when user mentions 'executive', 'briefing', 'C-suite', 'board',…

Search across company knowledge bases (Confluence, Jira, internal docs) to find and explain internal concepts, processes, and technical details. When an agent…

Analyze year-over-year growth in income statement items and financial metrics using Octagon MCP. Use when retrieving YoY Revenue Growth, Cost of Revenue…

Correspondent for aibtc.news: claim a beat, research daily using live on-chain and market data, file quality signals, earn $25 sBTC per signal included in the…

Use when validating Stories, plans, or tasks through the evaluation platform with mandatory research, parallel evidence lanes, sequential merge, and bounded…

Generate OpenAPI documentation from source code. Analyzes repository to automatically discover API endpoints and create swagger.json and interactive HTML…

Explore-lane code adaptation skill for deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated…

验证研究报告中所有声明的引用准确性、来源质量和格式规范性。确保每个事实性声明都有可验证的来源，并提供来源质量评级。当最终确定研究报告、审查他人研究、发布或分享研究之前使用此技能。

Set up or update the agent-first engineering harness for any repository. Implements the complete scaffolding that makes AI coding agents effective: knowledge maps (AGENTS.md as a concise TOC), structured documentation, architecture boundaries, enforcement rules (.harness/*.yml specs), quality scoring, and process patterns for agent-driven development. Use this skill whenever someone wants to make a repo agent-ready, set up AGENTS.md or docs/ structure, define domain boundaries or golden principles, generate .harness/ configuration, audit agent readiness, or update an existing harness. Also trigger when a user reports problems with agent effectiveness, context management, or architectural drift — these are symptoms of a missing or stale harness. Trigger on: "harness this repo", "set up harness", "agent-first setup", "make this agent-ready", "update the harness", "assess agent readiness", "set up AGENTS.md", "organize for agents", or any discussion about structuring a codebase for AI agent workflows.

Trusted-lane training execution skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively…