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 agentmods add skills/gyf0311/lorekit/wiki-outputnpx skills add GYF0311/lorekit --skill wiki-outputgit clone --depth 1 https://github.com/GYF0311/lorekitWrote 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/gyf0311/lorekit/wiki-output)<a href="https://agentmods.dev/skills/gyf0311/lorekit/wiki-output"><img src="https://agentmods.dev/badge/skills/gyf0311/lorekit/wiki-output.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00095 | $0.01674 |
| Opus 5 | $0.00048 | $0.00837 |
| Sonnet 5 | $0.00019 | $0.00335 |
| Haiku 4.5 | $0.00010 | $0.00167 |
Grade A, and why
wiki-output 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 3d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-output
把 corpus/知识库/ 里的已有沉淀组合成对外产物（幻灯片 / 文章 / 图表 / 汇报稿），落在 corpus/输出/{子目录}/ 下作为终态产物保留。
When to trigger
- 用户说"做个 Marp 幻灯片讲 XXX"、"给我做个分享 PPT"、"演讲稿"
- 用户说"写一篇对外文章"、"我要投公众号"、"给我一份投稿草稿"
- 用户说"出一张 matplotlib 图"、"趋势图"、"对比图"
- 用户说"汇报一下 XXX"、"写一份给 XXX 看的汇报材料"
不要触发：
- 用户只是内部 query / 综合 →
wiki-query（产物落输出/问答/） - 用户要存外部资料 →
wiki-ingest - 用户要存对话洞察 →
wiki-fileback
分工边界（重要）
| 本 skill 负责 | 不负责 |
|---|---|
读 知识库/ 综合，组织成对外叙事 |
爬外部新资料（去 wiki-ingest） |
| 按输出类型选格式（.md / .py / marp） | 回流进知识库（除非先生明确） |
落盘到 corpus/输出/{子目录}/ |
更新 concept 页 compiled truth |
frontmatter 加 graph-excluded: true |
修改 corpus/index.md 的知识库登记 |
产出形式 × 落盘路径
| 输出类型 | 文件形式 | 落盘路径 | frontmatter 关键字段 |
|---|---|---|---|
| Marp 幻灯片 | .md（含 marp: true） |
corpus/输出/幻灯片/YYYY-MM-DD-<slug>.md |
marp: true, graph-excluded: true |
| matplotlib 图表 | .py（可直接运行） |
corpus/输出/图表/YYYY-MM-DD-<slug>.py |
无 frontmatter；头部注释写数据来源 wikilink |
| 对外文章 | .md（公众号友好） |
corpus/输出/文章/YYYY-MM-DD-<slug>.md |
graph-excluded: true, target_audience: <对象> |
| 汇报材料 | .md（结构化汇报稿） |
corpus/输出/文章/YYYY-MM-DD-<slug>.md |
同上 |
铁律：所有产物 frontmatter 必含 graph-excluded: true——输出属于终态产物，不进图谱、不进入长期知识索引。
6 步流程
1. 明确输出类型与受众
先问清楚（或从上下文推断）：
- 什么类型？（Marp 幻灯片 / 对外文章 / matplotlib 图表 / 汇报材料）
- 给谁看？（领导 / 同行 / 公众号读者 / 投稿目标刊物）
- 大概多长？（几页 / 几分钟 / 几千字）
2. 读 知识库/ 相关沉淀
- 先 Read
corpus/index.md定位相关分区 - Read
{dir}/_INDEX.md定位具体页 - Read 对应 concept / synthesis / 摘要页
- 只用
知识库/的沉淀作为素材，不要临时 WebFetch 新资料（那是 wiki-ingest 的职责） - 如果素材不够，主动告诉先生："corpus 里相关沉淀只有 N 页，输出可能单薄。要不要先 ingest 一些新来源？"
3. 按输出类型组织叙事
- Marp 幻灯片：title / agenda / 分节 slides / take-aways / Q&A / sources 页。每 slide 一个核心论点 + 1-2 个 wikilink 引用
- 对外文章：标题 → 导言 → 核心论点分节（每节带 source 引用脚注）→ 结论 → 参考资料
- matplotlib 图表：头部注释写数据来源 wikilink + 生成时间；代码块可直接跑；若数据需要手工填，注释明确标"数据源 TODO"
- 汇报材料：背景 → 关键事实 → 分析 → 建议 → 附录（sources）
4. 落盘到 corpus/输出/{子目录}/
- 路径按上方表格
- frontmatter 必含
graph-excluded: true - 同步更新
corpus/log.md：## [YYYY-MM-DD HH:mm] output | <类型> | <一句话简述>
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.
- 3d ago First seen · 112 lines · 95 tokens per session scan A 2036f8e9ebfb
wiki-output is a skill published in the GitHub repository GYF0311/lorekit (5 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 1,674 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 2026-08-31.
Other skills, from other repositories
wiki-ingest
Digest a course source file into the wiki. This skill should be used when the user says "ingest", "消化", "process this PDF/slide", or drops a course file into raw/ and wants it turned into wiki pages. Reads the source, deduplicates via manifest, creates source + concept pages, and finds cross-course connections.
wiki-diagram
Add Mermaid diagrams to wiki pages to aid understanding. This skill should be used during ingest/review when a concept involves a process, architecture, sequence, hierarchy, or comparison that is easier to grasp visually, or when the user explicitly asks to "画图"/"配图"/"diagram"/"visualize" a concept.
wiki-lint
Health-check the wiki and apply confidence decay. This skill should be used when the user says "lint", "检查wiki", "check the wiki", or wants to find orphan pages, broken links, contradictions, or stale concepts. Runs the 30-day confidence decay rule and reports issues for the user to fix.
wiki-ingest
Ingest exactly one research paper or source document into an open-llm-wiki vault. Use when the user explicitly asks to add, ingest, process, or publish a paper into the wiki. The workflow parses the source, drafts a source page, runs independent QA, publishes only after the quality gate passes, extracts and normalizes…
wiki-ingest
Ingest sources into the Obsidian wiki vault. Reads a source, extracts entities and concepts, creates or updates wiki pages, cross-references, and logs the operation. Supports files, URLs, and batch mode. Triggers on: ingest, process this source, add this to the wiki, read and file this, batch ingest, ingest all of…
wiki-prune
Weekly janitor for the Obsidian wiki. Archives wiki/daily/YYYY-MM-DD/ folders older than 7 days into wiki/.archive/YYYY-WW/, keeping the rolled-up summaries that wiki-fold produced. Dry-run by default; --commit moves the folders; --hard deletes archive entries older than 30 days. Suggested cadence: every Monday…