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 liucongg/liucong-skills --skill llm-wiki-opsgit clone --depth 1 https://github.com/liucongg/liucong-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/liucongg/liucong-skills/llm-wiki-ops)<a href="https://agentmods.dev/skills/liucongg/liucong-skills/llm-wiki-ops"><img src="https://agentmods.dev/badge/skills/liucongg/liucong-skills/llm-wiki-ops/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/liucongg/liucong-skills/llm-wiki-ops"><img src="https://agentmods.dev/badge/skills/liucongg/liucong-skills/llm-wiki-ops.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 | $0.00100 | $0.01936 |
| Opus 5 | $0.00050 | $0.00968 |
| Sonnet 5 | $0.00020 | $0.00387 |
| Haiku 4.5 | $0.00010 | $0.00194 |
Grade A, and why
llm-wiki-ops 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 13d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Wiki 运维技能
在飞书知识库中运维 LLM Wiki——基于 Karpathy 的 LLM Wiki 模式:LLM 把原始资料持续编译成互相链接的持久化 wiki。
第一步:检测绑定状态
每次使用本技能前,必须先检测知识库绑定状态。
- 读取本技能目录下的
config/wiki-binding.json。 - 如果文件存在且包含有效的
space_id和nodes,则视为已绑定,直接进入运维模式。 - 如果文件不存在、为空或缺少关键字段,则视为未绑定,进入初始化流程(见
references/init.md)。
绑定文件路径:<skill_dir>/config/wiki-binding.json
已绑定:直接运维
绑定后,所有操作基于 wiki-binding.json 中的节点 token 和 doc_id 执行。无需再让用户提供知识库地址。
核心操作
1. Ingest(入库)
原始资料入库:
- 读取用户提供的资料文件(全文,不跳过)。
- 在「原始资料」区创建资料卡文档,保留原文链接。
- 从资料中提取值得沉淀的实体/概念/方法论,在「词条」区创建词条文档。
- 每个新词条必须同时建立与已有词条的双链关系(见下方「双链规则」)。
- 更新「索引」文档(A-Z 排序,先英文后中文)。
- 在「更新日志」追加
ingest条目。
文章入库:
- 判断是成稿还是草稿,分别放入「我的文章/成稿」或「我的文章/草稿」。
- 清理文章中的无关内容(如视频播放器 UI 文字)。
- 从文章中提取有价值的概念/实体创建词条(词条来源标注文章标题)。
- 更新索引和日志。
详细流程见 references/ingest.md。
2. Query(查询)
- 先读「索引」定位相关词条和资料卡。
- 深入阅读相关文档。
- 综合出带引用的答案。
- 有价值的答案(比较、分析、新连接)归档回 wiki 成为新页面,并更新索引与日志。
详细流程见 references/query.md。
3. Lint(体检)
定期检查:
- 页面间矛盾、过期论断
- 孤儿页(无入链的词条)——发现后立即补全双链
- 提到但缺页的概念
- 缺失的交叉引用
- 事实标注是否完整(每条事实是否标注来源)
- 索引与实际词条是否一致
结果记录到更新日志,类型为 lint。详细流程见 references/lint.md。
4. 词条管理
- 新建词条:必须包含定义、关键事实(标注来源)、与其他词条的关系(双链)、来源四个部分。
- 更新词条:只改被点名的范围,保留未要求改动的内容。
- 删除词条:需用户明确授权,删除后更新索引和相关词条的双链。
词条模板见 references/entry-template.md。
5. 索引与日志维护
- 索引:每次入库/删除后必须更新。按 A-Z 字母排序,每个字母下先英文后中文。包含原始资料、我的文章(成稿+草稿)、词条三个区域。
- 更新日志:追加式记录,不修改历史。条目格式:
## [YYYY-MM-DD] <动作> | <主题>,动作取值:ingest/query/lint/init/update。
词条文档规范(强制)
每篇词条文档必须包含以下结构:
- 定义:一句话定义该实体/概念。
- 关键事实:列出从资料/文章中提取的事实。
- 与其他词条的关系:说明与其他词条的关联,必须使用飞书文档双链链接。
- 来源:标注来源文件名或文章标题。
事实与来源规则(强制)
- 所有事实必须来自用户提供的资料和文章,禁止编造。
- 每条事实必须标注来源,格式:
(来源:<文件名/文章标题>)。 - 资料里没有的信息,明确写「暂无资料」,不得臆造。
双链规则(强制)
- 每个词条的「与其他词条的关系」部分必须使用飞书文档链接(
[词条名](https://<tenant>.feishu.cn/docx/<doc_id>)),不得使用纯文本。 - 禁止产生孤儿词条:每个新词条至少链接到 1-2 个已有词条;被链接的词条也应在关系部分回链。
- 关系描述要具体,不能只写“相关”,要说明是什么关系(对比、基于、同属、被采用等)。
- 绑定文件
wiki-binding.json中不记录每个词条的 doc_id;查询时通过索引或 wiki 节点列表获取。
What ships with it
8 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.
- 13d ago First seen · 153 lines · 100 tokens per session scan A 655194ae9e23
llm-wiki-ops is a skill published in the GitHub repository liucongg/liucong-skills (246 stars, last pushed 4d ago), licensed Apache-2.0. It adds 100 tokens to every session and 1,936 once invoked, about $0.0005 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
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
Migrate
Intakes external content, classifies chunks against LifeOS taxonomy, commits with provenance. Sources: .md/.txt, stdin, LifeOS dirs, CLAUDE.md/Cursor/OpenAI Custom Instructions, Obsidian/Notion/Apple Notes exports. MigrateScan classifies → routing table. MigrateApprove with…
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…
email-assistant
Read, search, draft, and send emails via Himalaya CLI or Python IMAP/SMTP. Requires email account configuration.
calendar
Manage calendar events via CalDAV (Google/iCloud/Nextcloud) or local ICS files. View, create, and query events.