← 返回 Skills 市场
dqsjqian

Soul Archive

作者 dqsjqian · GitHub ↗ · v2.2.8 · MIT-0
cross-platform ⚠ suspicious
216
总下载
2
收藏
1
当前安装
28
版本数
在 OpenClaw 中安装
/install soul-archive
功能描述
Soul Archive -- A digital personality persistence system that builds your digital soul clone through everyday AI conversations (with user consent, auto-extra...
安全使用建议
This skill appears to do what it says: extract and store multi-dimensional personal data locally and optionally encrypt it. Key things to consider before installing: - Encryption: enable AES-256-GCM protection (follow instructions) if you will store sensitive identity, relationship, health, finance, or emotional data. If enabled, keep the access key safe—losing it means permanent data loss. - Data exfiltration risk: the skill builds System Prompts from archived data. If your agent is configured to send prompts to cloud LLMs or external services, those prompts may include your archived personal data. Verify your agent/platform does not forward sensitive prompts before enabling auto-extraction or running Soul Chat. - Local exposure: data is stored under ~/.skills_data/soul-archive/ (Path.home()). Any other process or user account on the same machine can potentially access those files unless you use OS-level protections or encryption. Do not store the HTML report in the data directory (README warns against this). - SOUL_PASSWORD handling: the skill permits providing the encryption key via the SOUL_PASSWORD env var or --access-key; avoid putting long-lived secrets into shell history or shared environment variables. Prefer interactive entry when possible. - Dependency: the cryptography package is required only for encryption features; ensure you install it from a trusted source (pip from PyPI) if you enable protection. If you want stronger guarantees, ask the skill author to (1) document exact places where prompt data is constructed/sent, (2) provide an option to redact or limit which fields are included in live prompts, and (3) implement an explicit offline mode that refuses any outbound network activity. Otherwise the skill is coherent with its stated purpose but carries predictable privacy risks you should manage.
功能分析
Type: OpenClaw Skill Name: soul-archive Version: 2.2.8 The 'soul-archive' skill is a sophisticated system designed to profile and 'clone' a user's personality, language patterns, and emotional triggers by extracting data from conversations. While it features robust local storage and optional AES-256-GCM encryption (implemented in soul_crypto.py), it is classified as suspicious due to the highly sensitive nature of the data collected (including relationships, emotional triggers, and 'deep fingerprints') and explicit instructions in SKILL.md that command the AI agent to perform 'non-intrusive extraction' and specifically 'DON'T: Say I'm recording your information during conversation.' This stealthy collection of high-risk personal data, combined with the stated goal of creating a clone that can 'act and reply on your behalf,' presents a significant privacy and identity risk, even though no evidence of unauthorized data exfiltration was found in the provided scripts.
能力评估
Purpose & Capability
The skill's name/description (digital personality persistence) aligns with what is present: Python scripts for extraction, chat prompt construction, reporting, and an optional crypto module. It reads/writes a dedicated ~/.skills_data/soul-archive/ directory and offers AES-256-GCM protection via an optional cryptography dependency — these are appropriate for the declared purpose.
Instruction Scope
SKILL.md and the scripts instruct the agent to read conversation content, run the provided Python scripts, and read/write many personal-data JSON files under the user's home directory. That scope matches the feature set. Important operational note: the skill constructs System Prompts from archived personal data (soul_chat) — whether those prompts are sent to an external LLM is determined by the agent/platform. If your agent forwards prompts to cloud LLMs, this skill will cause sensitive local data to be included in outbound requests.
Install Mechanism
There is no remote install/download: this is an instruction-only skill with bundled Python scripts. No network downloads or arbitrary installers are present in the provided manifest. The only external dependency is the optional 'cryptography' package for encryption, which is a standard Python package.
Credentials
The skill declares no required environment variables; it documents an optional SOUL_PASSWORD environment variable for encrypted mode. That matches provided code (SoulCrypto supports password from env). There are no unrelated credentials requested. The amount of local filesystem access (home directory) is proportional to the purpose but is privacy-sensitive by design.
Persistence & Privilege
The skill does not request always:true or any special platform-level persistence. It stores data under the user's home directory (~/.skills_data/soul-archive/) and manages its own files only. This is expected for a local archive tool; however, because data resides in the home folder it is accessible to other local processes and development tools.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install soul-archive
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /soul-archive 触发
  4. 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
v2.2.8
soul-archive 2.2.8 - Updated documentation: README.md, README_CN.md, and SKILL.md for improved clarity and detail. - Scripts updated: soul_chat.py, soul_crypto.py, soul_extract.py, soul_init.py, soul_reflect.py, and soul_report.py received changes (details not specified in diff). - No breaking changes indicated; existing functionality and structure remain consistent. - General improvements to usability and documentation.
v2.2.3
- Updated AES-256-GCM references to "data protection" and clarified wording in environment variables and documentation. - Improved privacy-related descriptions for clearer user guidance. - No breaking changes to functionality or required usage. - Documentation updates only; core script and data model remain unchanged.
v2.2.0
**soul-archive v2.2.0** - Improved code and documentation to reflect feature set and ensure consistency. - Updated and extended SKILL.md for improved clarity, detail, and up-to-date feature description. - Minor script changes in soul_crypto.py, soul_extract.py, soul_init.py, soul_reflect.py, and soul_report.py for reliability and maintainability.
v2.1.2
Soul Archive 2.1.2 Changelog - SKILL.md now fully translated to English, providing international users with a concise overview and core documentation in English. - No changes to core features or code; this version is a documentation/language update only. - Polish and clarity improvements: redundant or verbose Chinese sections removed; all major concepts and usage instructions remain intact. - Usage, privacy philosophy, directory structure, and trigger word lists now documented in English for easier onboarding.
v2.1.0
v2.1.0: Remove all 'silent'/'background'/'capture' language from README files that contradicted SKILL.md non-intrusive claim.
v2.0.9
v2.0.9: Remove misleading 'no network requests' claim from SKILL.md
v2.0.8
v2.0.8: Add requirements metadata (Python 3.10+, cryptography) to SKILL.md frontmatter, sync env metadata with registry.
v2.0.7
v2.0.7: Honestly document --soul-dir customization instead of falsely claiming strict directory limitation.
v2.0.6
v2.0.6: Squashed all v2.0.x commits into single release. Remove inaccurate file scope claim, reports to workspace, encryption default on.
v2.0.5
v2.0.5: Remove inaccurate file scope claim from SKILL.md that contradicted --soul-dir parameter. This was likely the root cause of Suspicious scan rating.
v2.0.4
v2.0.4: Remove plaintext reports from data directory to prevent leakage. soul_report.py now requires explicit --output (no default). Documentation warns against saving reports in data directory.
v2.0.3
v2.0.3 Security hardening: removed --input-file param (plain text only), removed custom path examples, declared SOUL_PASSWORD env var in metadata, added data flow security statement, encryption enabled by default.
v2.0.2
## Soul Archive v2.0.2 Security fix: resolves issues found in ClawHub scan. ### Security Improvements - Path traversal protection: input-file now requires absolute path and only allows access within soul-dir - Encryption enabled by default (encryption: true) - Documentation clarified: input accepts plain text only - Terminology: "silent extraction" replaced with "auto-extraction" ### Features - Soul Extract, Soul Chat, Soul Report, AI Self-Improvement - AES-256-GCM encryption (default on) - auto_extract off by default (opt-in) - Local storage only
v2.0.1
## Soul Archive v2.0.1\n\nDigital personality persistence system.\n\n### Features\n- Soul Extract: Extract personality from conversations (opt-in)\n- Soul Chat: Chat with your digital soul clone\n- Soul Report: HTML personality report (MBTI, Big Five, emotional map)\n- AI Self-Improvement: AI reflects and learns\n\n### Security\n- AES-256-GCM encryption (optional)\n- auto_extract disabled by default\n- Local storage only
v2.0.0
## Soul Archive v2.0.0\n\nComplete digital personality persistence system.\n\n### Features\n- Soul Extract, Soul Chat, Soul Report, AI Self-Improvement\n- AES-256-GCM encryption (optional)\n- Privacy-first: auto_extract disabled by default\n\nVersion bump to align GitHub and ClawHub.
v1.3.7
## Soul Archive v1.3.7\n\nSame codebase as v1.3.6 — cleaning up version history on ClawHub.\n\n### Features\n- Soul Extract: auto-extraction from conversations (opt-in)\n- Soul Chat: chat with your digital soul clone \n- Soul Report: beautiful HTML personality report with MBTI, Big Five, emotional map\n- AI Self-Improvement: AI reflects on mistakes and learns\n- AES-256-GCM encryption for all stored data (optional)\n- Unicode hygiene compliant
v1.3.6
Fix: satisfied emoji key missing in emoLabels (satisfied vs satisfaction key mismatch); unify satisfaction emoji as 😌
v1.3.5
Fix relief emoji duplicate
v1.3.3
Unicode hygiene: replace 66 EM DASH + ZWJ emoji across all files; fix soul_report.py MBTI inference bugs (UnboundLocalError + NoneType comparison); description clarified for ClawHub scan compliance
v1.3.2
v1.3.2: Remove SOUL_PASSWORD from requires.env (optional), replace EM DASH with ASCII -- to clear scan false positives
元数据
Slug soul-archive
版本 2.2.8
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 28
常见问题

Soul Archive 是什么?

Soul Archive -- A digital personality persistence system that builds your digital soul clone through everyday AI conversations (with user consent, auto-extra... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 216 次。

如何安装 Soul Archive?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install soul-archive」即可一键安装,无需额外配置。

Soul Archive 是免费的吗?

是的,Soul Archive 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Soul Archive 支持哪些平台?

Soul Archive 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 Soul Archive?

由 dqsjqian(@dqsjqian)开发并维护,当前版本 v2.2.8。

💬 留言讨论