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 long-chat-task-processorgit 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/long-chat-task-processor)<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/long-chat-task-processor"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/long-chat-task-processor.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.01967 |
| Opus 5 | $0.00014 | $0.00983 |
| Sonnet 5 | $0.00006 | $0.00393 |
| Haiku 4.5 | $0.00003 | $0.00197 |
Grade A, and why
long-chat-task-processor 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 8d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
聊天记录项目化处理工作流 (Long Chat Task Processor)
此技能旨在将非结构化的、按标题组织的聊天记录（Markdown格式）转化为可执行的项目管理资产。它严格基于文档目录结构 (TOC) 进行分段处理，而非简单的行数切分，以确保对话上下文的完整性。
使用时机
当用户提供导出的聊天记录（Markdown），且记录使用标题（#, ##...）区分不同群聊或对话对象时。
用户通常要求：
- 项目化梳理：提取任务(Assigner/Assignee)、状态(Status)、决策(Decision)。
- 特定产出物：根据聊天内容撰写周报、Bug清单、特定事件的时间线复盘等。
- 背景对齐：处理过程中需要参考用户提供的背景文档（如 PRD、人员表）。
工作流
1. 准备阶段 (Initialization)
首先，必须初始化工作区并解析文档结构。
- 接收输入：确认源文件、背景文档、以及用户的额外诉求（例如：“帮我把所有关于 API 的讨论单独整理成一个文档”）。
- 执行初始化：
运行脚本扫描源文件标题结构，并生成工作区：
python3 .gemini/skills/long-chat-task-processor/scripts/setup_workspace.py "path/to/chat_log.md" "工作区目录名称"
工作区目录名称可使用 YYYY-MM-DD-HH 沟通记录整理 格式。
初始化后，工作区结构如下：
Chat_Projectization_YYYY-MM-DD-HH-MM/
├── 0-工作日志.md # [核心] 基于 TOC 生成的树状任务列表
├── 1-原始记录/ # 存放源文件
├── 2-项目背景/ # 存放用户提供的背景文档，以及用户的所有指示
├── 3-实体映射表.md # [动态] 自动积累的人名/概念术语表
├── 4-任务池.md # [动态] 累积提取的任务列表
├── 5-决策与里程碑.md # [动态] 累积提取的决策和时间点
└── 6-额外输出/ # 存放用户要求的额外的输出文档
- 将用户的指示和背景文档复制到
2-项目背景/目录下，确保后续处理有据可依。
2. TOC 分段处理循环 (TOC Loop)
打开 0-工作日志.md，你将看到一个基于 Markdown 标题层级的任务树。
按顺序处理每一个标记为 [ ] 的 Section。
在处理每个 Section 前，务必读取：
0-工作日志.md(获取当前 Section 的行号范围、标题背景)2-项目背景/(理解业务上下文)3-实体映射表.md(确保人名对齐)- 用户的额外诉求 (确认本段对话是否涉及需要单独输出的主题)
处理步骤：
- 读取内容：根据日志中记录的
Line Start-End，读取1-原始记录/中对应的内容。 - 执行分析 (Analysis)：
- 通用提取：
- 任务：更新
4-任务池.md。格式：[ ] <Time> **Assigner** -> **Assignee**: <Task> (Status) - 决策：更新
5-决策与里程碑.md。 - 新实体：发现新人名/黑话，追加到
3-实体映射表.md。
- 任务：更新
- 特定主题提取 (Extra Requests)：
- 如果用户的诉求包含“整理 API 问题”、“输出周报素材”等，且当前段落包含相关信息：
- 在
6-最终输出/下创建或追加对应的文档（例如6-最终输出/API_Issue_Log.md）。
- 通用提取：
- 更新状态：
- 在
0-工作日志.md中将该 Section 标记为[x]。
- 在
3. 整合与交付 (Synthesis)
当所有 Section 处理完毕后：
- 整理任务池：检查
4-任务池.md，合并重复项，按人名或优先级归类。 - 生成最终交付物：
- 如果用户要的是一份完整的汇总报告，基于
4、5和6中的内容进行汇总。 - 如果用户要的是分散的文档（如“任务清单”+“会议纪要”），则分别整理输出。
- 如果用户要的是一份完整的汇总报告，基于
What ships with it
2 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.
- 8d ago First seen · 141 lines · 28 tokens per session scan A 0466d7fe72b1
long-chat-task-processor is a skill published in the GitHub repository cafe3310/public-agent-skills (253 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 1,967 once invoked, about $0.0001 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
memory-init
Scaffold a project-local memory directory and AGENTS.md guidance for reusable agent knowledge. Use when a user wants to initialize .agents/memories/ or another project memory path so future agents can read and maintain durable project context.
paleo-auto
Use when you want automatic token-saving without manual skill selection. Auto-detects long sessions (>15 turns), high token usage, or bulky context — then auto-enables paleo + paleo-trim-context + paleo-converse + paleo-budget at safe defaults. User does not need to think about which skill is active. Off: "disable…
paleo-converse
Use when user says "compress conversation", "condense chat", "summarize history", "too long context", or a session has many old turns. Condense prior conversation turns into a tight summary, merge near-duplicate messages, keep the last N turns verbatim. Saves context tokens without losing task state. Off: "stop…
paleo-trim-context
Use when context window is large / token cost high / long session. Proactively trim, summarize, or drop stale content to save context tokens without losing the task state.
firstsun-harness
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session lifecycle, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
rem-sleep
Memory consolidation and defragmentation for long-term memory maintenance. Use when asked to consolidate memories, defrag memory, run REM sleep, clean up memory files, or process session logs into durable memory. Also use periodically during heartbeats for memory maintenance.