← 返回 Skills 市场
284
总下载
1
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install promptfolio-summarize
功能描述
Analyze AI conversation history across Claude Code, Cursor, Codex, ChatGPT, Gemini CLI, Trae, OpenCode, Antigravity, Windsurf, OpenClaw and other coding agen...
安全使用建议
This skill is functionally coherent with its description, but it will scan many local app data directories and write a local API token config. Before running or installing: 1) Inspect the updater path referenced (~/.promptfolio/update-check.sh) — the bundle does not include it; avoid running an updater you didn't review. 2) Review device-auth.sh and confirm the API URL (default https://promptfolio.club) is a service you trust; the script will save an api_token in ~/.promptfolio/config.json. 3) Be aware the discovery script will "peek inside" unknown dot-directories and include any conversation-like files without asking — consider running the discovery step yourself, in a terminal, to see what it finds before allowing any upload. 4) If you have sensitive data in app support folders or exported chats, run the analysis in an isolated account or verify which session files are being included and explicitly review the assembled payload (promptfolio_payload.json) before any network upload. 5) If you are uncomfortable, ask the skill developer for a mode that produces a dry-run listing of files to be analyzed and an explicit per-file confirmation UI before parsing or uploading.
功能分析
Type: OpenClaw Skill
Name: promptfolio-summarize
Version: 0.1.0
This skill bundle is designed to perform deep introspection and data extraction from a user's AI conversation history across numerous platforms (Claude Code, Cursor, Windsurf, etc.) to build a 'Promptfolio' profile. While it includes instructions for anonymization and user confirmation, it possesses high-risk capabilities: broad file system scanning of sensitive application data (discover-sessions.sh), execution of local scripts for 'auto-updates' (SKILL.md), and the exfiltration of processed conversation snippets and behavioral telemetry to an external endpoint (promptfolio.club). The 'Behavioral Fingerprint' logic in compute-stats.py specifically targets user interaction patterns, reject rates, and tool usage, which constitutes significant privacy-invasive data collection.
能力评估
Purpose & Capability
The skill's name/description (build a portrait from AI conversation history) aligns with the included scripts: discovery of session files, parsing/extracting messages, computing stats, assembling a payload. The bundled scripts implement the advertised functionality.
Instruction Scope
The runtime instructions and scripts instruct broad, recursive scanning of many application data directories (~/Library/Application Support, hidden dotfolders, various agent config/data paths) and to "peek inside" unknown tool dirs and include them without asking. Although this is useful for maximizing coverage, it grants the skill authority to read many local files (potentially including sensitive information) beyond clearly scoped conversation exports. The SKILL.md also insists you run an "auto-updater" (~/.promptfolio/update-check.sh) before anything — that updater file is not present in the bundle, creating a mismatch and an opportunity for unexpected behavior if the missing updater is later provided or fetched externally.
Install Mechanism
No external install is required; the skill is instruction-driven and includes its own helper scripts. There is no download-from-URL installer in the package. Because code files are bundled, they will execute locally when invoked — that is expected for this kind of tool.
Credentials
The skill declares no required env vars or credentials, but it expects and will create/read ~/.promptfolio/config.json (device-auth.sh writes an API token there) and uses the promptfolio API URL (default https://promptfolio.club). It reads a wide set of user data locations (many app support dirs and DBs). The request to auto-include unknown directories without asking is disproportionate for a privacy-sensitive operation and increases the risk of exposing unrelated personal data. There are optional environment overrides (PROMPTFOLIO_API_URL, IS_PUBLIC, etc.) but no clear, enforced confirmation step tying which files will be uploaded vs kept local.
Persistence & Privilege
The skill does not request 'always: true'. It does create a per-user config (~/.promptfolio/config.json) to store an API token from a device auth flow, and writes temporary extraction artifacts under /tmp and _pf_parts. It does not modify other skills or global agent settings. Autonomous invocation is allowed by default (not flagged on its own) — combine that with broad local scanning and stored credentials to assess risk.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install promptfolio-summarize - 安装完成后，直接呼叫该 Skill 的名称或使用
/promptfolio-summarize触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.0
promptfolio-summarize v0.1.0
- Initial release of the promptfolio-summarize skill.
- Analyzes local AI conversation history across multiple coding agents (Claude Code, Cursor, Codex, ChatGPT, Gemini CLI, Trae, OpenCode, Antigravity, Windsurf, OpenClaw, and others).
- Detects user "framework sentences"—moments where the user teaches AI how to think, not just commands.
- Builds a personal "portrait" of the user for the promptfolio platform using these framework sentences and a 30-day activity heat map.
- Ensures user privacy: all conversation parsing is local, and only structured summaries are uploaded with user confirmation.
- Includes robust session discovery, authentication, and session analysis steps.
元数据
常见问题
Promptfolio Summarize 是什么？
Analyze AI conversation history across Claude Code, Cursor, Codex, ChatGPT, Gemini CLI, Trae, OpenCode, Antigravity, Windsurf, OpenClaw and other coding agen... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 284 次。
如何安装 Promptfolio Summarize？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install promptfolio-summarize」即可一键安装，无需额外配置。
Promptfolio Summarize 是免费的吗？
是的，Promptfolio Summarize 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Promptfolio Summarize 支持哪些平台？
Promptfolio Summarize 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Promptfolio Summarize？
由 chenchen（@billc8128）开发并维护，当前版本 v0.1.0。
推荐 Skills