Soul Archive

What it does

When your agent uses it

• Words: soul extract
• Learn from mistakes

Example prompts

• “/soul-archive”

Requirements

• Python 3
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Grep, Glob, WebSearch

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

1. 1生前：以用户的风格代为行事、回复消息
2. 2身后：让亲友继续与"你"对话，延续情感连接

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash
  • Grep
  • Glob
  • WebSearch

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 6 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python3
  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • SOUL_PASSWORD

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Soul Archive loads about 2.9k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 139 tokens; SKILL.md has 505 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~139

When it runs · the whole SKILL.md, loaded when a task matches

~2.9k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Write, Edit, Bash, Grep, Glob, WebSearch

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 505 words, ~2,896 tokens.

name

soul-archive

description

Soul Archive — A digital personality persistence system that silently builds your digital soul clone through everyday AI conversations, while continuously improving AI capabilities. Four modes: Soul Extract, Soul Chat, Soul Report, AI Self-Improvement. | 灵魂存档 —— 通过日常对话静默构建数字人格克隆体，同时持续改进 AI 自身能力。四大模式：灵魂沉淀、灵魂对话、灵魂报告、AI 自我改进。Trigger words: soul extract, soul archive, soul update, soul sync, soul snapshot, soul sediment, soul report, soul chat, self-reflect, self-improve, learn from mistakes, 灵魂沉淀, 灵魂提取, 灵魂存档, 灵魂报告, 灵魂对话, 自我反思, 自我批评, 自我学习.

allowed-tools

Read, Write, Edit, Bash, Grep, Glob, WebSearch

{SKILL_DIR}/                               ← Skill（你在这里）
~/.skills_data/soul-archive/                           ← 数据（灵魂本体，存放于用户主目录下）

~/.skills_data/soul-archive/
├── profile.json                  # 灵魂核心档案（完整度、版本）
├── config.json                   # 隐私与采集配置
├── identity/
│   ├── basic_info.json           # 姓名、年龄、职业、地点...
│   └── personality.json          # 性格、价值观、MBTI...
├── memory/
│   ├── episodic/                 # 情景记忆（按日期的经历提取）
│   │   └── YYYY-MM-DD.jsonl
│   ├── semantic/
│   │   ├── topics.json           # 话题兴趣与观点图谱
│   │   └── knowledge.json        # 专业知识与认知
│   └── emotional/
│       └── patterns.json         # 情感触发与反应模式
├── style/
│   ├── language.json             # 语言指纹（口头禅、句式）
│   └── communication.json        # 沟通偏好
├── voice/                        # 语音数据（可选）
│   ├── samples/
│   └── voice_profile.json
├── relationships/
│   └── people.json               # 人际关系图谱
├── agent/                        # 🆕 AI 自我改进
│   ├── patterns.json             # 行为模式库
│   ├── episodes/                 # 工作经历（按日期）
│   │   └── YYYY-MM-DD.jsonl
│   ├── corrections.jsonl         # 自我批评/纠正日志
│   └── reflections.jsonl         # 自我反思日志
└── soul_changelog.jsonl          # 灵魂变更日志

# 使用默认数据目录（~/.skills_data/soul-archive/）
python3 scripts/soul_extract.py \
  --input "<对话内容或文件路径>" \
  --mode auto

# 指定自定义数据目录
python3 scripts/soul_extract.py \
  --soul-dir "/custom/path" \
  --input "<对话内容>" \
  --mode auto

python3 scripts/soul_chat.py \
  --mode interactive

python3 scripts/soul_report.py \
  --output ~/.skills_data/soul-archive/reports/soul_report.html

builder.add_reflection(
    task='迁移数据目录',
    outcome='success',
    went_well=['全面扫描了路径'],
    went_wrong=['遗漏了一个目录'],
    lesson='迁移前应全面扫描所有目录'
)

builder.add_critique(
    trigger='user_correction',
    user_said='不要胡扯，就填我发的',
    what_i_did_wrong='多写了不存在的细节',
    root_cause='过度发挥',
    correction='严格按用户指令执行',
    severity='high',
    pattern_id='pat-strict-instruction-following'
)

builder.add_pattern(
    'pat-strict-instruction-following',
    '严格按指令执行',
    '用户给出明确指令时，严格执行，不添加额外内容',
    source='user_correction', confidence=0.95
)

~/.skills_data/soul-archive/agent/
├── patterns.json          ← 行为模式库
├── episodes/              ← 工作经历（按日期）
│   └── YYYY-MM-DD.jsonl
├── corrections.jsonl      ← 自我批评/纠正日志
└── reflections.jsonl      ← 自我反思日志

# 查看 AI 自我改进状态
python3 scripts/soul_reflect.py --mode status

# 查看行为模式库
python3 scripts/soul_reflect.py --mode patterns

python3 scripts/soul_init.py

{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "bash ${SKILLS_DIR}/soul-archive/hooks/post-task.sh \"$TOOL_OUTPUT\" \"$EXIT_CODE\""
          }
        ]
      }
    ],
    "Stop": [
      {
        "matcher": "",
        "hooks": [
          {
            "type": "command",
            "command": "bash ${SKILLS_DIR}/soul-archive/hooks/session-end.sh"
          }
        ]
      }
    ]
  }
}

{
  "privacy_level": "standard",
  "auto_extract": true,
  "auto_reflect": true,
  "extract_dimensions": {
    "identity": true,
    "personality": true,
    "language_style": true,
    "knowledge": true,
    "episodic_memory": true,
    "emotional_patterns": true,
    "relationships": false,
    "voice": false
  },
  "agent_self_improvement": {
    "enabled": true,
    "auto_reflect_on_completion": true,
    "auto_critique_on_correction": true,
    "pattern_extraction": true
  },
  "sensitive_topics_filter": true,
  "require_confirmation_for": ["health", "finance", "intimate_relationships"],
  "data_retention_days": null,
  "encryption": false
}

python3 scripts/soul_init.py --enable-encryption

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 10 other files (scripts, references) in skills/soul-archive of LeoYeAI/openclaw-master-skills.

• SKILL.md
• README.md
• README_CN.md
• _meta.json
• references/extraction_prompts.md
• scripts/soul_chat.py
• scripts/soul_crypto.py
• scripts/soul_extract.py
• scripts/soul_init.py
• scripts/soul_reflect.py
• scripts/soul_report.py

Open the folder on GitHubat commit e5199b5