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 chengkj99/kj-skills --skill ai-conversation-to-wikigit clone --depth 1 https://github.com/chengkj99/kj-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/chengkj99/kj-skills/ai-conversation-to-wiki)<a href="https://agentmods.dev/skills/chengkj99/kj-skills/ai-conversation-to-wiki"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/ai-conversation-to-wiki/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/chengkj99/kj-skills/ai-conversation-to-wiki"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/ai-conversation-to-wiki.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00178 | $0.01939 |
| Opus 5 | $0.00089 | $0.00970 |
| Sonnet 5 | $0.00036 | $0.00388 |
| Haiku 4.5 | $0.00018 | $0.00194 |
Grade A, and why
ai-conversation-to-wiki 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 12d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 对话沉淀到 Wiki
把一次性 AI 对话转化为可追溯、可维护、可复用的个人知识资产。保留原文与推理路径，明确区分用户观点、AI 建议和待验证事项。
核心原则
- 先保真，后提炼：不得用摘要替代对话原文；不得把 AI 推断改写成用户原话。
- 默认预览：第一次处理对话时只分析并输出沉淀清单，不落盘。
- 确认门闩：严格读取目标 Wiki 的确认规则。若其要求口令（例如“确认沉淀”），未收到符合规则的确认前不得写入 AI 协作结论。
- 分层路由：原始对话、结构化实录、分析结论、跨源综合和经营决策分别落到适合的位置。
- 可追溯：每条关键结论尽量保留对话轮次、段落或原始文件锚点。
- 增量维护：写入前检查重复页面；优先更新已有主题，避免换名重复建页。
- 遵守本地规则：目标 Wiki 的
AGENTS.md、CLAUDE.md、SCHEMA.md和专项规则优先于本技能。
工作流
1. 定位目标 Wiki 并读取规则
- 根据当前仓库、用户指定路径和全局路由规则确定 Wiki 根目录。
- 完整读取目标 Wiki 的
AGENTS.md或CLAUDE.md、SCHEMA.md。 - 检查
.cursor/rules/、.agents/skills/或其他本地说明中是否存在 AI 协作纪要、Ingest、OS 路由和日志规则。 - 若目标 Wiki 提供专用 Ingest Skill，在确认写入后的导入阶段优先使用它；不要复制或绕过其约束。
- 读取
wiki/index.md并搜索相关主题，建立重复与冲突清单。
若无法确定目标 Wiki，先询问落点，不要写入当前项目的任意 docs/。
2. 获取并检查对话输入
支持以下输入：
- 用户在当前会话粘贴的完整对话；
- ChatGPT、Claude、Codex 等平台导出的 Markdown、JSON、HTML 或文本；
- 用户明确指定的本地文件；
- 当前环境能够读取的对话链接。
若链接只在原平台内部可见、当前环境无法读取，请用户粘贴全文或提供导出文件。不要仅归档不可复现的内部链接。
记录可获得的来源信息：平台、对话标题、conversation ID 或 URL、发生日期、导出日期、参与者、隐私级别。缺失字段标记“未提供”，不得猜测。
3. 进行高保真价值分析
按对话顺序阅读全文；长对话分段读取后建立覆盖清单。至少区分：
- 用户提供的事实、经历和案例；
- 用户明确表达的判断或已确认决定；
- AI 给出的建议、方案或推断；
- 尚未解决、待验证或互相冲突的问题；
- 可复用的框架、流程、清单、标准和提示词；
- 行动项、经营建议和内容选题；
- 有价值的追问、观点转折、反例与失败路径；
- 隐私、敏感信息和不适合公开的内容。
不要因为某个观点表达完整就默认它已被用户采纳。AI 建议统一标注为“建议”或“待验证”。
4. 输出沉淀清单并暂停
默认使用 references/deposition-manifest.md 的格式输出：
- 对话概览；
- 高价值内容清单；
- 用户结论 / AI 建议 / 待验证问题；
- 重复与冲突；
- 建议文件及更新方式；
- 隐私与脱敏提醒；
- 本次明确跳过的内容；
- 确认提示。
此阶段不得创建、编辑或移动任何 Wiki 文件。若目标 Wiki 规定了固定确认口令，逐字提示用户使用该口令。
5. 收到确认后保真归档
仅在确认范围清楚且满足目标 Wiki 门闩后执行：
- 将用户提供的对话原文原样归档到目标 Wiki 允许的原始素材目录。
- 添加来源、归档日期和隐私级别等元数据，但不得改写正文。
- 若需要断句、纠错或去除界面噪声，另建整理稿；不得覆盖原文。
- AI 生成的结论纪要与原始聊天全文分文件保存。
- 若对话含敏感信息，先按清单中确认的范围脱敏；无法安全处理时停止写入并说明原因。
6. 分层生成知识页面
按照 references/routing-matrix.md 和目标 Wiki Schema 选择页面：
sources：3–5 条导航级摘要，链接到原始来源和衍生页面；transcripts：长篇、多主题对话的结构化实录，保留原文锚点，不写推断；analysis：议题地图、观点矩阵、论点与依据、开放问题和覆盖清单；synthesis：仅用于多段对话或多来源的跨源收敛、矛盾和行动框架；concepts/entities：仅创建能跨场景复用且尚不存在的概念或实体；os/inbox：尚未确认的经营建议、产品决策、计划和行动实验；- 正式 OS 页面：只有用户已明确确认且本地规则允许时才更新。
What ships with it
3 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.
- 12d ago First seen · 137 lines · 178 tokens per session scan A f428a8a75f9c
ai-conversation-to-wiki is a skill published in the GitHub repository chengkj99/kj-skills (14 stars, last pushed 11d ago), licensed MIT. It adds 178 tokens to every session and 1,939 once invoked, about $0.0009 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
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…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.