📦
chronicle-project-tracker
78跟踪 Chronicle 项目里程碑
开发工作可能会变得难以与里程碑、会话和路线图优先级关联起来。此技能使用 Chronicle MCP 工具和 CLI 工作流来跟踪进度和后续步骤。
效率 查看
技能 chronicle-remote-summarizer
📦
chronicle-remote-summarizer
内容修订 r1 高风险 ⚙️ 外部命令🌐 网络访问📁 文件系统访问🔑 环境变量
总结远程 Chronicle 会话
当源机器无法访问 Gemini 时，Remote Chronicle 会话可能很难总结。此技能会指导导出、本地总结，以及将结构化结果导入回源系统。
支持: Claude Codex Code(CC)
安装前请停下并请求确认。
请审查安装计划，并在更改文件前获得用户明确同意。
使用我的智能体安装
将此请求复制给你的智能体，其中包含权威 Skill 页面和清单。
智能体请求
Review the Skillstore skill "chronicle-remote-summarizer" from https://skillstore.io/skills/chandlerhardy-chronicle-remote-summarizer.md and its manifest at https://skillstore.io/api/skills/chandlerhardy-chronicle-remote-summarizer/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.你的智能体仍应展示其计划，并按安全策略请求必要确认。
Agent 可读资源
当 AI Agent、爬虫或脚本需要干净上下文，而不是读取完整页面时，请使用这些链接。
测试它
正在使用“chronicle-remote-summarizer”。 会话 7 存在于一台无法访问 Gemini 的 FreeBSD 主机上。
预期结果:
助手确认主机详细信息，导出会话，在本地总结，并报告总结已导入回去。
正在使用“chronicle-remote-summarizer”。 单行 SSH 管道在总结过程中卡住。
预期结果:
助手切换到手动工作流，创建可审查的中间文件，并在确认后导入总结。
正在使用“chronicle-remote-summarizer”。 多个远程会话缺少总结。
预期结果:
助手确认目标 ID，逐个处理它们，并报告每个会话的成功或失败情况。
安全审计
高风险v8 • 2026/7/6 打开版本化报告
This Markdown skill is primarily a Chronicle remote summarization workflow, not executable source code. Most raw backtick detections are false positives, but confirmed risks remain around SSH command execution, secret configuration, hidden and temporary transcript files, stderr suppression, and remote overwrite behavior. No prompt injection attempt was found in the reviewed SKILL.md content.
1
已扫描文件
349
分析行数
51
复核项
0
已忽略误报
已确认安全问题 (2)
高
Unvalidated Shell Command Construction
The skill tells the assistant to ask for hostname and Chronicle path, then construct and run shell commands. Without validation or quoting rules, user-supplied host, path, or session IDs could alter SSH command behavior.
The workflow explicitly asks for host and path values and then constructs commands. The file does not define validation, escaping, or confirmation requirements for those values.
中
Automatic Remote Summary Overwrite
The workflow states that import-and-summarize overwrites existing summaries by design and later instructs the assistant to run commands. A wrong session ID or host could replace existing remote summaries.
The overwrite behavior is stated directly, and the assistant workflow includes running the command. The main uncertainty is whether the underlying Chronicle command prompts before overwrite.
能力复核项 (51)
这些是真实的本地能力，对此技能可能是预期行为，因此需要复核，但不会按已确认恶意行为计分。
高
Ruby/shell backtick execution
- Gemini API key configured on local machine (`chronicle config ai.gemini_api_key YOUR_KEY`)
This command configures a Gemini API key, so it may expose a secret through shell history or Chronicle configuration. The command is part of the documented setup flow.
高
Ruby/shell backtick execution
```bash
This line starts a full SSH pipeline that exports remote session data, summarizes it locally, filters output, and imports results back. It performs remote command execution and data transfer.
高
Ruby/shell backtick execution
```bash
The manual SSH pipeline interpolates remote host and session values into shell commands. Without validation, it can run unintended remote commands or transfer the wrong session data.
高
Ruby/shell backtick execution
```bash
The example runs the same SSH export, local summarize, and remote import pipeline. It is a real command workflow, not just an inert reference.
高
Ruby/shell backtick execution
```bash
This command configures a Gemini API key placeholder and may encourage entering secrets at the shell. Secret setup should avoid history and logs.
高
Ruby/shell backtick execution
```bash
This example runs a hardcoded SSH export, local summarization, output filtering, and remote import pipeline. It transfers session data and modifies remote state.
高
Ruby/shell backtick execution
```bash
The batch workflow runs SSH commands in a shell loop and pipes each session into summarization and remote import. Batch execution increases the impact of wrong IDs or host values.
高
Hidden file in home directory
- Stores transcript in `~/.ai-session/sessions/session_-3.cleaned`
The documented Chronicle workflow stores transcript data under a hidden home-directory path. If cleanup fails, sensitive session text can remain in a less visible location.
高
Hidden file access
- Stores transcript in `~/.ai-session/sessions/session_-3.cleaned`
The hidden Chronicle session path stores transcript content during import and summarization. That is real hidden-file access to potentially sensitive data.
高
Generic API/secret keys
- Gemini API key configured on local machine (`chronicle config ai.gemini_api_key YOUR_KEY`)
The skill tells users to configure a Gemini API key through Chronicle commands. API keys are secrets and may be exposed through shell history, logs, or local config if handled casually.
高
Generic API/secret keys
chronicle config ai.gemini_api_key YOUR_API_KEY_HERE
The skill tells users to configure a Gemini API key through Chronicle commands. API keys are secrets and may be exposed through shell history, logs, or local config if handled casually.
中
Ruby/shell backtick execution
Chronicle provides `import-and-summarize --quiet` which:
The skill centers on invoking the Chronicle summarization subcommand, which processes session data and calls Gemini. It is intended command execution and should be reviewed before automatic use.
中
Ruby/shell backtick execution
```bash
The bash block writes remote host and executable path settings and lists configuration with grep. It is intended local command execution against Chronicle config.
中
Ruby/shell backtick execution
**Note:** The `grep -A 999999 '^{$'` filters out Google library warnings that can leak through even
The grep filter is part of the documented pipeline and discards output before import. This can hide unexpected warnings or malformed output in a data-transfer workflow.
中
Ruby/shell backtick execution
```bash
This command exports a remote Chronicle session over SSH into a local file. It handles potentially sensitive session data and should not run without confirmation.
中
Ruby/shell backtick execution
```bash
The example exports a specific remote session to a local temporary file. It is an executable SSH command that can expose session content locally.
中
Ruby/shell backtick execution
```bash
This command pipes a local session export into Chronicle summarization and writes the summary to disk. It processes potentially sensitive transcript data.
中
Ruby/shell backtick execution
```bash
The example runs local Chronicle summarization on a temporary session export. It is intended command execution over sensitive session content.
中
Ruby/shell backtick execution
```bash
This command pipes the generated summary into a remote import command over SSH. It can modify the original remote session record.
中
Ruby/shell backtick execution
```bash
The example imports a summary back into a remote Chronicle session over SSH. It can update remote data and should be confirmed.
中
Ruby/shell backtick execution
```bash
The troubleshooting block includes export, local summarization, and remote import commands. These are executable commands that transfer and modify session data.
中
Ruby/shell backtick execution
```bash
The command lists remote Chronicle sessions over SSH to check a session ID. It is scoped, but still reads remote system data.
中
Ruby/shell backtick execution
```bash
This command lists Chronicle configuration and filters remote system entries. It can reveal stored hostnames and paths from local config.
中
Ruby/shell backtick execution
- Read hostname: `chronicle config remote_systems.freebsd.hostname`
The skill instructs the assistant to read a stored remote hostname from Chronicle config. This can expose infrastructure details and influences later SSH commands.
中
Ruby/shell backtick execution
- Read chronicle path: `chronicle config remote_systems.freebsd.chronicle_path`
The skill instructs the assistant to read the stored remote Chronicle path. This configuration value is used to construct later SSH commands.
中
Ruby/shell backtick execution
1. Checks config: `chronicle config remote_systems.freebsd.hostname`
The example has the assistant read the remote hostname from configuration before running commands. It is scoped config access but still part of command construction.
中
Ruby/shell backtick execution
1. Checks config: `chronicle config --list | grep remote_systems`
The example checks remote system configuration with Chronicle and grep. It reads local configuration to decide how to construct remote commands.
中
Ruby/shell backtick execution
```bash
The inspect workflow exports remote session data, summarizes it locally, reads the summary file, and imports it back over SSH. It is an executable data-transfer workflow.
中
Ruby/shell backtick execution
```bash
The debug command runs remote export and local summarization without quiet mode. It still executes a pipeline over remote session data.
中
Temp directory access
ssh <remote-host> "chronicle export-session <id>" > /tmp/session_<id>.json
The workflow reads or writes session exports and summaries under /tmp using predictable filenames. These files may contain sensitive transcript data and can be exposed or overwritten on shared systems.
中
Temp directory access
ssh freebsd "chronicle export-session 7" > /tmp/session_7.json
The workflow reads or writes session exports and summaries under /tmp using predictable filenames. These files may contain sensitive transcript data and can be exposed or overwritten on shared systems.
中
Temp directory access
cat /tmp/session_<id>.json | chronicle import-and-summarize --quiet 2>/dev/null > /tmp/summary.json
The workflow reads or writes session exports and summaries under /tmp using predictable filenames. These files may contain sensitive transcript data and can be exposed or overwritten on shared systems.
中
Temp directory access
cat /tmp/session_7.json | chronicle import-and-summarize --quiet 2>/dev/null > /tmp/summary.json
The workflow reads or writes session exports and summaries under /tmp using predictable filenames. These files may contain sensitive transcript data and can be exposed or overwritten on shared systems.
中
Temp directory access
- Outputs summary JSON to `/tmp/summary.json`
The workflow reads or writes session exports and summaries under /tmp using predictable filenames. These files may contain sensitive transcript data and can be exposed or overwritten on shared systems.
中
Temp directory access
cat /tmp/summary.json | ssh <remote-host> "chronicle import-summary"
The workflow reads or writes session exports and summaries under /tmp using predictable filenames. These files may contain sensitive transcript data and can be exposed or overwritten on shared systems.
中
Temp directory access
cat /tmp/summary.json | ssh freebsd "chronicle import-summary"
The workflow reads or writes session exports and summaries under /tmp using predictable filenames. These files may contain sensitive transcript data and can be exposed or overwritten on shared systems.
中
Temp directory access
ssh freebsd "chronicle export-session 7" > /tmp/session.json
The workflow reads or writes session exports and summaries under /tmp using predictable filenames. These files may contain sensitive transcript data and can be exposed or overwritten on shared systems.
中
Temp directory access
cat /tmp/session.json | chronicle import-and-summarize --quiet > /tmp/summary.json
The workflow reads or writes session exports and summaries under /tmp using predictable filenames. These files may contain sensitive transcript data and can be exposed or overwritten on shared systems.
中
Temp directory access
cat /tmp/summary.json | ssh freebsd "chronicle import-summary"
The workflow reads or writes session exports and summaries under /tmp using predictable filenames. These files may contain sensitive transcript data and can be exposed or overwritten on shared systems.
中
Temp directory access
2. Exports to `/tmp/session_7.json`
The workflow reads or writes session exports and summaries under /tmp using predictable filenames. These files may contain sensitive transcript data and can be exposed or overwritten on shared systems.
中
Temp directory access
3. Processes locally → `/tmp/summary.json`
The workflow reads or writes session exports and summaries under /tmp using predictable filenames. These files may contain sensitive transcript data and can be exposed or overwritten on shared systems.
中
Temp directory access
chronicle import-and-summarize --quiet 2>/dev/null > /tmp/summary.json
The workflow reads or writes session exports and summaries under /tmp using predictable filenames. These files may contain sensitive transcript data and can be exposed or overwritten on shared systems.
中
Temp directory access
cat /tmp/summary.json | jq '.summary'
The workflow reads or writes session exports and summaries under /tmp using predictable filenames. These files may contain sensitive transcript data and can be exposed or overwritten on shared systems.
中
Temp directory access
cat /tmp/summary.json | ssh freebsd "chronicle import-summary"
The workflow reads or writes session exports and summaries under /tmp using predictable filenames. These files may contain sensitive transcript data and can be exposed or overwritten on shared systems.
低
Standard device file access
**Note:** The `grep -A 999999 '^{$'` filters out Google library warnings that can leak through even
The workflow suppresses stderr with /dev/null in command pipelines. The device file is standard, but hiding warnings or errors can make unsafe imports harder to detect.
低
Standard device file access
- `2>/dev/null` suppresses Google library warnings (harmless)
The workflow suppresses stderr with /dev/null in command pipelines. The device file is standard, but hiding warnings or errors can make unsafe imports harder to detect.
低
Standard device file access
cat /tmp/session_<id>.json | chronicle import-and-summarize --quiet 2>/dev/null > /tmp/summary.json
The workflow suppresses stderr with /dev/null in command pipelines. The device file is standard, but hiding warnings or errors can make unsafe imports harder to detect.
低
Standard device file access
cat /tmp/session_7.json | chronicle import-and-summarize --quiet 2>/dev/null > /tmp/summary.json
The workflow suppresses stderr with /dev/null in command pipelines. The device file is standard, but hiding warnings or errors can make unsafe imports harder to detect.
低
Standard device file access
- **Suppress stderr**: Add `2>/dev/null` to hide Google library warnings
The workflow suppresses stderr with /dev/null in command pipelines. The device file is standard, but hiding warnings or errors can make unsafe imports harder to detect.
低
Standard device file access
chronicle import-and-summarize --quiet 2>/dev/null | \
The workflow suppresses stderr with /dev/null in command pipelines. The device file is standard, but hiding warnings or errors can make unsafe imports harder to detect.
低
Standard device file access
chronicle import-and-summarize --quiet 2>/dev/null > /tmp/summary.json
The workflow suppresses stderr with /dev/null in command pipelines. The device file is standard, but hiding warnings or errors can make unsafe imports harder to detect.
风险因素
⚙️ 外部命令 (80)
SKILL.md:17 SKILL.md:31 SKILL.md:32 SKILL.md:35 SKILL.md:44 SKILL.md:49-56 SKILL.md:56-62 SKILL.md:62-64 SKILL.md:64-69 SKILL.md:69-71 SKILL.md:71-74 SKILL.md:74-76 SKILL.md:76-78 SKILL.md:78 SKILL.md:86-90 SKILL.md:90-99 SKILL.md:99-101 SKILL.md:101-104 SKILL.md:104-106 SKILL.md:106-109 SKILL.md:109-111 SKILL.md:111-114 SKILL.md:114-116 SKILL.md:116-119 SKILL.md:119-122 SKILL.md:122-125 SKILL.md:125-127 SKILL.md:127-130 SKILL.md:130-132 SKILL.md:132-141 SKILL.md:141-145 SKILL.md:145 SKILL.md:146-147 SKILL.md:147-149 SKILL.md:149-153 SKILL.md:153-161 SKILL.md:161-163 SKILL.md:163-167 SKILL.md:167-170 SKILL.md:170-171 SKILL.md:171 SKILL.md:190-199 SKILL.md:199-203 SKILL.md:203-206 SKILL.md:206-208 SKILL.md:208-214 SKILL.md:214-217 SKILL.md:217-219 SKILL.md:219-223 SKILL.md:223-229 SKILL.md:229-230 SKILL.md:230-231 SKILL.md:231-242 SKILL.md:242-244 SKILL.md:244-246 SKILL.md:246-247 SKILL.md:247-248 SKILL.md:248-250 SKILL.md:250-267 SKILL.md:267-268 SKILL.md:268-271 SKILL.md:271-273 SKILL.md:273-277 SKILL.md:277-280 SKILL.md:280-282 SKILL.md:282-289 SKILL.md:289-290 SKILL.md:290-298 SKILL.md:298-309 SKILL.md:309-313 SKILL.md:313-323 SKILL.md:323-327 SKILL.md:327-329 SKILL.md:329-332 SKILL.md:332-334 SKILL.md:334 SKILL.md:338-339 SKILL.md:339-340 SKILL.md:340-341 SKILL.md:341-342
🌐 网络访问 (1)
📁 文件系统访问 (30)
SKILL.md:146 SKILL.md:231 SKILL.md:52 SKILL.md:63 SKILL.md:146 SKILL.md:231 SKILL.md:272 SKILL.md:282 SKILL.md:78 SKILL.md:90 SKILL.md:110 SKILL.md:115 SKILL.md:230 SKILL.md:306 SKILL.md:316 SKILL.md:100 SKILL.md:105 SKILL.md:110 SKILL.md:115 SKILL.md:122 SKILL.md:126 SKILL.md:131 SKILL.md:192 SKILL.md:195 SKILL.md:198 SKILL.md:289 SKILL.md:290 SKILL.md:316 SKILL.md:319 SKILL.md:322
🔑 环境变量 (2)
审计者: codex 查看审计历史 →
分享与引用此报告
分享版本化评估报告、中性徽章、嵌入卡片和引用。Skillstore 只报告证据，不判断该 Skill 是否安全。
复制报告链接
https://skillstore.io/skills/chandlerhardy-chronicle-remote-summarizer/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 徽章
[](https://skillstore.io/skills/chandlerhardy-chronicle-remote-summarizer?utm_source=security_passport_badge)HTML 徽章
<a href="https://skillstore.io/skills/chandlerhardy-chronicle-remote-summarizer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/chandlerhardy-chronicle-remote-summarizer/security.svg" alt="Skillstore security assessment" loading="lazy"></a>嵌入卡片
<iframe src="https://skillstore.io/embed/skills/chandlerhardy-chronicle-remote-summarizer.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>学术引用 (APA · BibTeX · CFF)
APA 引用
ChandlerHardy. (2026). chronicle-remote-summarizer security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/chandlerhardy-chronicle-remote-summarizer/audits/8BibTeX 引用
@techreport{chandlerhardy-chandlerhardy-chronicle-remote-summarizer-2026,
author = {ChandlerHardy},
title = {chronicle-remote-summarizer security audit report (audit version 8)},
institution = {Skillstore},
year = {2026},
number = {8},
url = {https://skillstore.io/skills/chandlerhardy-chronicle-remote-summarizer/audits/8},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "chronicle-remote-summarizer security audit report (audit version 8)"
version: "unspecified"
type: report
authors:
- name: "ChandlerHardy"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/chandlerhardy-chronicle-remote-summarizer/audits/8"
identifiers:
- type: other
value: "skillstore:chandlerhardy-chronicle-remote-summarizer:audit:8"
description: "Skillstore immutable audit report identifier"
Skillstore 评分
评分依据 证据置信度: 中 55
架构
85
可维护性
87
内容
70
社区
83
规范符合性
你能构建什么
从受限的开发主机总结
将 Chronicle 会话从无法访问 Gemini 的远程机器移动到本地机器进行总结。
SSH 管道失败时恢复
使用记录的三步工作流检查文件，并手动完成总结传输。
处理多个未完成的会话
在确认目标和主机详细信息后，调整批处理工作流以总结多个已知的会话 ID。
试试这些提示
总结一个远程会话
总结我 FreeBSD 主机上的 Chronicle 会话 7。在运行命令之前，先向我询问缺失的连接详细信息。
使用已保存的远程配置
使用我已保存的 Chronicle 远程系统配置来总结会话 12，并将结果导入回源主机。
导入前检查
导出并总结远程会话 18，然后在导入回去之前向我展示总结以供审查。
批处理远程会话
查找我指定的远程会话，在本地逐个总结，并在覆盖任何现有远程总结之前进行确认。
最佳实践
- 在运行 SSH 命令之前，确认远程主机、会话 ID 和 Chronicle 路径。
- 当会话内容敏感时，在导入生成的总结之前先进行检查。
- 在工作流完成后删除临时会话和总结文件。
避免
- 不要将 API 密钥粘贴到可能保存在 shell 历史记录中的命令里。
- 不要在未确认每个目标会话 ID 的情况下运行批量导入。
- 在排查导入或总结失败时，不要抑制错误。
常见问题
这个技能会总结什么？
它会总结从另一个系统导出的 Chronicle 会话，并将总结导入回原始会话。
它需要 SSH 吗？
是的。记录的工作流假定本地机器与远程 Chronicle 主机之间具有 SSH 访问权限。
它会调用 Gemini 吗？
是的。本地机器必须已为 Chronicle 总结配置 Gemini API 访问权限。
我可以先审查总结吗？
可以。手动工作流支持在将生成的总结导入回远程主机之前先进行检查。
它可以处理多个会话吗？
可以，但批处理工作流应在导入总结或覆盖现有总结之前确认每个会话 ID。
它适合敏感会话吗？
请谨慎使用。会话导出和总结可能包含敏感数据，尤其是在存储于临时文件中时。
开发者详情
许可证
MIT
Skillstore 修订
r1
版本提示
作者未声明版本。
仓库
https://github.com/ChandlerHardy/chronicle/tree/main/chronicle-skills/chronicle-remote-summarizer引用
dd4a3ef9f20ddf38830950b4bb713df96b431fd6
维护新鲜度
2026/7/18
使用量
6 次下载 · 198 次浏览
文件结构
📄 SKILL.md
ChandlerHardy 的更多技能
查看全部📦
chronicle-context-retriever
78检索过往开发上下文
团队在不同开发会话之间容易遗忘决策、阻塞点和之前的实现细节。此技能会搜索 Chronicle 历史记录，并为当前工作返回聚焦的上下文。
效率 查看
📦
chronicle-workflow
77跟踪 Chronicle 开发会话
在提交、工具变更和上下文切换之后，开发会话很难重建。此技能通过一个工作流指导 Chronicle 会话跟踪、摘要、搜索和 Obsidian 文档记录。
效率 查看
📦
chronicle-assistant-guide
71使用 Chronicle 项目记忆
当 AI 助手忽略先前的 Chronicle 会话和路线图上下文时，会浪费时间。此技能会指导它们搜索历史记录、选择 MCP 或 CLI，并复用项目知识。
效率 查看
📦
chronicle-session-documenter
70记录 AI 开发会话
当细节停留在聊天历史或本地日志中时，开发会话很难审查。此技能会将 Chronicle 数据转换为结构化的 Obsidian 笔记，包含摘要、元数据和链接。
文档 查看
相关技能
查看全部📦
context-compression
81可靠压缩长代理上下文
由 muratcankoylan
当上下文窗口填满时，长时间 AI 会话会丢失关键决策、文件变更和后续步骤。此技能为 Claude、Codex 和 Claude Code 提供结构化压缩方法和评估探针。
效率 查看
📦
descriptive-action
79中立地分析信息
由 BellaBe
用户经常需要不包含建议的中立分析。此技能指导 Claude、Codex 和 Claude Code 区分事实、推论、证据和未知项。
写作与内容 查看
📦
research-synthesizer
78基于证据综合研究来源
由 ACSKamloops
研究摘要可能混合主张、引用和缺乏支持的解读。此技能帮助 Claude、Codex 和 Claude Code 基于提供的来源生成中立的综合分析。
研究与学习 查看
📦
firebase-ai-logic
78在应用中集成 Firebase AI Logic
由 supercent-io
Firebase 团队在添加 Gemini 功能时，通常需要安全的模式，而不是分散的设置说明。此技能指导 Firebase AI Logic 设置、SDK 使用、提示词处理和基本安全实践。
编码与开发 查看
📦
deep-research
78运行深度研究报告
由 sickn33
深度研究通常需要多次搜索、来源核查和综合分析。本技能会引导 Claude、Codex 和 Claude Code 完成一个由 Gemini 驱动的结构化研究工作流。
研究与学习 查看
📦
nano-banana-2
78使用 inference.sh 生成 Gemini 图像
由 inferen-sh
图像创建通常需要模型命令和选项细节。此技能提供用于通过 inference.sh 进行 Gemini 图像生成的现成提示词和 CLI 模式。
设计与创意 查看