Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cafe3310/public-agent-skills --skill im-wiki-extractorgit clone --depth 1 https://github.com/cafe3310/public-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cafe3310/public-agent-skills/im-wiki-extractor)<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/im-wiki-extractor"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/im-wiki-extractor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/im-wiki-extractor"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/im-wiki-extractor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00048 | $0.01315 |
| Opus 5 | $0.00024 | $0.00658 |
| Sonnet 5 | $0.00010 | $0.00263 |
| Haiku 4.5 | $0.00005 | $0.00131 |
Grade A, and why
im-wiki-extractor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Skill: im-wiki-extractor (群聊知识图谱提取器)
1. 概述 (Overview)
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。
外部依赖与规范说明
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。
2. 提取定义 (Schema)
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。
3. 工作流阶段 (Workflow Phases)
第一阶段:准备与访谈
- 确认范围: 询问语料位置及目标知识库目录。
- Schema 确认: 引导用户确认
templates/meta.md。 - 目标定义: 确认
templates/prompt_template.md。
第二阶段:空间初始化
- 初始化
memories-off仓库: 在用户指定的地方创建知识目录并执行memocli init。 - 配置元数据: 用 cp 命令将
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。 - 复制语料: 在
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。 - 任务分解与状态追踪: 运行
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。
第三阶段:增量提取循环 (断点续传)
针对 TASK 文件中定义的每个未完成分片([ ]):
- 自动定位: 启动任务时,直接定位到
TASK文件中第一个[ ]状态的分片开始处理。 - 生成提示词: 运行
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)。 - 执行提取子任务 (原子化操作):
- 组合指令优先: 优先使用
append-update --add-rel-out等组合指令,减少工具调用次数。 - 路径自动探测: 默认在知识库根目录执行,无需显式传入
--path。 - 失败处理: 若执行中断,直接在下一次尝试时重新处理该分片。
- 组合指令优先: 优先使用
- 记录与提交:
- 检查
TASK文件,确认分片状态已更新为[x]。 - 标准化提交: 执行
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。
- 检查
- 检查并继续: 进入下一个分片。
4. 执行原则 (Execution Principles)
- 命名规范 (Identity): 实体名即文件名。严禁添加类型前缀。
- 组合语义 (Combined Ops): 充分利用
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。 - 动态语法核验:
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。 - 最小化探测:
- 识别到实体后直接
create-entity,通过|| true忽略已存在错误。 - 严禁冗余的
ls或全局search。
- 识别到实体后直接
- 溯源强制: 所有的
append-update必须包含filename:line_range。
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 75 lines · 48 tokens per session scan A f360a436c1ca
im-wiki-extractor is a skill published in the GitHub repository cafe3310/public-agent-skills (253 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,315 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
fda-database
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
iso-13485-certification
Comprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems. Use when users need help with ISO 13485 QMS documentation, including (1) conducting gap analysis of existing documentation, (2) creating Quality Manuals, (3) developing required procedures and work…
notaire
Notaire IA pour le droit immobilier, les successions, les donations, le droit de la famille et le droit des sociétés en France. Copilote juridique pour la préparation d'actes, le conseil patrimonial, les calculs de frais et la vérification de conformité. Couvre le calcul des frais de notaire (DMTO, émoluments…
commissaire-aux-comptes
Commissaire aux comptes IA pour l'audit des comptes annuels d'entreprises françaises. Applique la démarche NEP en 7 phases : prise de connaissance, contrôle du FEC, vérification du bilan, du compte de résultat, de la balance, de la liasse fiscale, et contrôles transversaux. Émet une opinion motivée sur la fiabilité…
crisis-holding
Draft crisis holding statements, journalist Q&A posture, and what-not-to-say guidance from confirmed incident facts, with a hard legal-counsel gate. Builds each statement through proven crisis-comms frameworks (holding-statement anatomy, SCCT, CAP order, the legitimate non-answer, bridge/flag/block).
dependency-audit
Audits direct and transitive dependencies for license compliance, maintenance health, CVEs, abandoned packages, and bloat. Triggers on: "audit dependencies", "license check", "dependency health", "abandoned packages", "unused dependencies", "license compliance", "supply chain", "dependency risk".