将超长群聊日志转化为结构化知识图谱。采用滑动窗口增量提取,规避上下文限制,并确保实体与关系的沉淀与溯源
npx skills add https://github.com/cafe3310/public-agent-skills --skill im-wiki-extractor
本技能旨在将非结构化的聊天记录(如群聊历史)转化为存储在 memories-off Agent Skill 生成的仓库中的结构化知识图谱。
它强调「逐渐增量」的处理方式,通过 100 行一个的「滑动窗口」来处理超长日志,从而规避模型上下文限制。
该技能通过动态注入工具的 help 信息来确保子代理生成 100% 正确的 CLI 指令。
本 Skill 依赖 memories-off 库进行实体管理与长期记忆。在执行任何任务前,您必须先查阅并完整遵循当前目录下的 memories-off-declare.md 声明文档,以获取其定义的实体类型规范及封装的子过程操作细节。
提取任务应遵循用户给出的实体和关系规范。
在 templates/meta.md 中包含了一个示例定义,定义了实体的类型(Member, Opinion, Info 等)及其关系谓语(Propose, Discuss 等)。
用户可以根据实际需求进行调整。
templates/meta.md。templates/prompt_template.md。memories-off 仓库: 在用户指定的地方创建知识目录并执行 memocli init。templates/meta.md 的内容写入知识库的 meta.md;或根据用户之前的输入动态生成 meta.md。memocli init 创建的知识库中创建 chat_res 子目录,用于存储规范化后的原始语料;然后将原始日志复制到 chat_res,按顺序重命名为 YYYY-MM-DD_NNN_orig_name.md。python scripts/setup_workspace.py path_to_chat_res TASK_YYYY-MM-DD.md。该脚本会扫描语料并生成带有行号分片(100行)和前序上下文(50行)的 TASK 文件。针对 TASK 文件中定义的每个未完成分片([ ]):
TASK 文件中第一个 [ ] 状态的分片开始处理。python scripts/generate_prompt.py ...。该脚本现在会动态注入支持「组合操作」的 memocli 语法(如在追加内容的同时建立关系)。append-update --add-rel-out 等组合指令,减少工具调用次数。--path。TASK 文件,确认分片状态已更新为 [x]。memocli commit -r "processed chunk [ID]"。该命令会自动触发全库审计并生成标准的 Git 提交信息。memocli 的 --add-rel-out/in 参数。在 create-entity 或 append-update 时同步完成关系建模,提升提取效率。generate_prompt.py 会实时调用 memocli --help 以确保子代理使用的语法与当前环境安装的版本 100% 匹配。create-entity,通过 || true 忽略已存在错误。ls 或全局 search。append-update 必须包含 filename:line_range。scripts/setup_workspace.py: 初始化分片任务清单。scripts/generate_prompt.py: 动态组装包含权威 CLI 语法的子代理提示词。templates/prompt_template.md: 核心任务模板,包含元数据和工具操作占位符。templates/meta.md: 图谱本体定义模板。Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take cafe3310/im-wiki-extractor from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.