Survey Generator
技能 已验证 活跃Compile a structured literature survey on any AI/ML topic. Agent curates a research bundle (taxonomy + sections + bibliography of real papers) from a public anchor resource, then a chosen LLM generates the survey artifact. Output target is a wiki page (markdown), not a one-off HTML — survey lands in `<wiki>/derived/surveys/<slug>.md` with full bibliography rows in `sources.md`. Provider-agnostic (Anthropic/OpenAI/OpenRouter/Fireworks/custom OpenAI-compat). Use when the user asks for a "survey", "literature review", "lit review", or "deep dive" on a technical topic.
To automate the creation of comprehensive literature surveys, serving as a knowledge base within a wiki for easy access and future research.
功能
- Generates structured literature surveys from a URL
- Creates research bundles (taxonomy, sections, bibliography)
- Outputs to wiki markdown pages and updates `sources.md`
- Provider-agnostic LLM integration (Anthropic, OpenAI, etc.)
- Integrates with pro-workflow's wiki and FTS5 indexing
使用场景
- Generating an initial overview of a new technical topic
- Creating a structured knowledge base for a research area
- Compiling survey artifacts for technical documentation
- Seeding the wiki for further automated research
非目标
- Generating standalone HTML survey files
- Inventing bibliography entries
- Performing deep analysis beyond survey compilation
- Directly editing wiki content outside of the generated survey and bibliography
Practical Utility
- info:Usage examplesThe SKILL.md provides detailed workflow steps and commands for generating surveys, but lacks end-to-end examples showing specific input, invocation, and claimed output.
- info:Edge casesThe SKILL.md outlines hard rules and potential iteration steps but does not explicitly detail failure modes, their symptoms, or recovery steps.
Execution
- info:ValidationThe script parses arguments and validates the bundle structure, but doesn't use a formal schema library for input validation beyond basic checks.
Errors
- info:Error HandlingThe script includes basic error handling with `die()` calls for critical failures, but lacks structured error reporting or specific recovery steps for LLM provider issues.
- info:Actionable error messagesError messages are provided for critical failures like missing arguments or files, but lack detailed remediation steps beyond suggesting checking usage.
Code Execution
- info:LoggingThe script logs progress and errors to stderr using `console.error`, but does not append to a persistent audit log file.
Protocol
- info:Idempotent retry & timeoutsThe script includes a timeout for the LLM provider call, but mutations like writing files are not inherently idempotent, and error handling for retries is basic.
安装
请先添加 Marketplace
/plugin marketplace add rohitg00/pro-workflow/plugin install pro-workflow@pro-workflow质量评分
已验证类似扩展
TradeMemory Protocol
100Evolution Engine 的领域知识 — 支持 LLM 从原始 OHLCV 数据中自主发现策略。涵盖生成-回测-选择-进化循环、向量化回测、样本外验证和策略梯度。在发现交易模式、运行回测、进化策略或审查进化日志时使用。由“evolve”、“discover patterns”、“backtest”、“evolution”、“strategy generation”、“candidate strategy”触发。
External Context
100Invoke parallel document-specialist agents for external web searches and documentation lookup
Understand Knowledge
100分析 Karpathy 模式的 LLM Wiki 知识库，并生成一个交互式知识图谱，包含实体提取、隐含规则和主题聚类。
Recursive Research
100深入的递归研究，具有自我调节的循环，可达博士级别。适用于任何领域（科学、技术、商业、艺术、人文学科）。使用 WDM + Munger 反演进行自主决策、可靠来源分级和磁盘检查点以克服上下文限制。
Trader Regime
100Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy
Trading Memory
100AI交易记忆的领域知识 — 结果加权记忆 (OWM) 架构、5种记忆类型、回忆评分和行为分析。用于记录交易、回忆相似的上下文、分析性能或检查行为漂移。在 "record trade"、"remember trade"、"recall"、"similar trades"、"performance"、"behavioral"、"disposition"、"affective state"、"confidence" 时触发。