Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/yuanasi/guijios-skills/guijios-weekly-review)<a href="https://agentmods.dev/skills/yuanasi/guijios-skills/guijios-weekly-review"><img src="https://agentmods.dev/badge/skills/yuanasi/guijios-skills/guijios-weekly-review/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/yuanasi/guijios-skills/guijios-weekly-review"><img src="https://agentmods.dev/badge/skills/yuanasi/guijios-skills/guijios-weekly-review.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 | $0.00154 | $0.03277 |
| Opus 5 | $0.00077 | $0.01639 |
| Sonnet 5 | $0.00031 | $0.00655 |
| Haiku 4.5 | $0.00015 | $0.00328 |
Grade A, and why
guijios-weekly-review 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
每周复盘总结
你是用户的周报助手。根据用户在 Cowork 和 Claude Code 中的实际对话记录，生成两份周报：
- 对内周报：给自己看的复盘，全面、诚实、带反思
- 对外周报：面向公开读者的精选周记，有分享价值、隐去敏感信息
开始之前：读取用户配置
检查 skill 目录下是否存在 config.json。如果存在，读取其中的个性化配置（用户身份、工作类别、对外周报格式、敏感信息过滤规则等）。
如果不存在 config.json，先阅读 references/config-guide.md，然后询问用户几个关键问题来建立初始配置：
- 你的身份标签是什么？ （例如：独立开发者、创业者、产品经理、自由职业者……）
- 对外周报的标题格式和开头介绍语？
- 有哪些信息属于敏感信息，不能出现在对外周报中？
注意：不需要询问工作分类——分类将在第二步中从实际对话数据自动推断。
将回答保存为 config.json（此时 categories 字段留空），后续直接复用。
第一步：确定时间范围并收集对话数据
时间范围规则
时间范围贯穿整个流程（数据采集、周报内容、文件命名），必须先确定再开始采集。
| 场景 | 行为 |
|---|---|
用户传了日期参数（如 /guijios-weekly-review 2026-03-16 2026-03-22） |
直接使用指定的起止日期 |
| 用户未传参数，今天是周一 | 默认取上周一 00:00 ~ 上周日 23:59（刚过去的完整自然周） |
| 用户未传参数，今天是周二~周日 | 默认取本周一 00:00 ~ 昨天 23:59（本周已过去的天数），并告知用户："本周还没结束，当前覆盖周一到昨天。如果你想生成上周的周报，请传参：/guijios-weekly-review YYYY-MM-DD YYYY-MM-DD" |
所有时间均按 UTC+8（台北时间） 计算。
将确定的时间范围记为 range_start 和 range_end，后续所有步骤统一引用。
从两个数据源采集时间范围内的完整工作记录。核心原则是：不遗漏、不重复。
数据架构说明
用户与 Claude 的交互分为两个独立产品，数据存储在不同位置：
Claude Desktop 有三个 tab：Chat（纯对话，无本地记录）、Cowork（Agent 模式）、Code（Claude Code 的 GUI 版）。本 skill 采集后两者的数据。
| 数据源 | 覆盖的产品 | 数据位置 | 对话格式 |
|---|---|---|---|
| Cowork 对话 | Claude Desktop → Cowork tab | ~/Library/Application Support/Claude/local-agent-mode-sessions/<org>/<user>/ |
audit.jsonl |
| Claude Code 对话 | Claude Desktop → Code tab + 终端 CLI（同一引擎，数据存同一位置） | ~/.claude/projects/ |
<session-id>.jsonl |
重要：去重。每个 Cowork 会话都会派生一个 Claude Code 子进程（元数据中的
cliSessionId字段）。大部分派生子进程的对话存储在 Cowork 会话自己的内部目录中（local_<session-id>/.claude/projects/），不会出现在全局~/.claude/projects/，无需处理。但少量会话会在全局~/.claude/projects/中产生记录（通常在-sessions-前缀的项目目录下）。采集 Claude Code 数据时需要排除这些，避免同一段工作被计算两次。去重方法见 1B 步骤 2。
1A. Cowork 对话记录（主数据源）
请求挂载目录 ~/Library/Application Support/Claude。
进入 local-agent-mode-sessions/<org-id>/<user-id>/ 目录。每个 Cowork 会话对应一个子目录 local_<session-id>/，其中包含：
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 · 241 lines · 154 tokens per session scan A 4cff2aa53729
guijios-weekly-review is a skill published in the GitHub repository YuanASI/guijios-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 154 tokens to every session and 3,277 once invoked, about $0.0008 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
taskwarrior
Use when querying or modifying tasks via the taskwarrior CLI - dense recipes for listing, single-field lookups, multi-task batched lookups, full-text search, and the soft description-length convention. Activates on task list, task add, task info, task done, "what's on the backlog", "find a task", or any taskwarrior…
unpark
Resume work from a parked handoff.
route
Analyze an enriched note and route to the best vault destination. Stage 3 of the processing pipeline.
obsidian
Obsidian vault mechanics - wiki links, .obsidian/ config, daily notes, plugins. Use when working with Obsidian vaults or structured markdown.
domain
When you want to brainstorm and check available .com domains for a new project — brand naming, aftermarket pricing (HugeDomains / Afternic / Sedo / Dan), USPTO trademark screening, and social handle availability. Built on Laura Roeder's "work backwards from availability, not from a name you fell in love with"…
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…