← Back to Skills Marketplace
Soul Ledger
by
albionaiinc-del
· GitHub ↗
· v1.0.0
· MIT-0
94
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install soul-ledger
Description
Gives any AI agent persistent memory of who the user is — not just facts, but patterns, preferences, personality traits, and behavioral evolution over time....
Usage Guidance
This skill is coherent with its purpose but has notable privacy and provenance issues. Before installing, consider: (1) Source provenance — there is no homepage or source link; prefer skills with traceable authorship. (2) Transparency & consent — the skill explicitly tells the agent to 'load silently' and infer traits without notifying the user; require visible consent and an opt-out mechanism. (3) Data sensitivity — the ledger can accumulate inferred personal data; decide what may never be stored (PII, health, financial, legal) and enforce that. (4) Storage & retention — confirm where soul_ledger.json will live, whether it is included in backups or shared workspaces, and implement encryption or access controls if needed. (5) Deletion & export — ensure the user can view, export, and permanently delete the ledger. (6) Operational limits — consider limiting how many interaction details are stored and reviewing synthesis rules that summarize older entries. (7) Test with dummy data first — observe what the agent writes before using with real personal information. (8) If you require stricter behavior, request the skill be modified to notify the user when it reads the ledger, require explicit per-conversation opt-in to persist new data, and avoid 'silent' data collection. Install only if you accept the privacy tradeoffs and/or the author provides clearer provenance and explicit consent controls.
Capability Analysis
Type: OpenClaw Skill
Name: soul-ledger
Version: 1.0.0
The Soul Ledger skill is designed to provide the AI agent with persistent memory of user preferences, personality traits, and interaction patterns by maintaining a local 'soul_ledger.json' file. The instructions in SKILL.md guide the agent on how to observe and model user behavior to improve collaboration without evidence of data exfiltration, unauthorized file access, or malicious execution. While it instructs the agent to load the data silently for a seamless user experience, the functionality remains confined to the workspace and aligned with its stated purpose of personalization.
Capability Assessment
Purpose & Capability
The name/description (persistent memory of user traits and evolution) matches the instructions: read/write a workspace file named soul_ledger.json and maintain a modeled ledger. There are no unrelated binaries, env vars, or install steps requested.
Instruction Scope
Instructions tell the agent to load the ledger 'silently' at conversation start and to infer and store behavioral traits from every interaction. This grants the agent broad discretion to collect and persist inferred personal information (potentially sensitive) without explicit user notification, opt-in, or limits. The skill does not require or reference any other files or environment variables, but the silent loading/updating is surprising and could be considered deceptive.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest install risk. Nothing is downloaded or written by an installer beyond the ledger file the agent itself creates/manages.
Credentials
No environment variables, credentials, or external config paths are requested. The requested access (workspace-level JSON file) is proportionate to the stated purpose, but the content the skill instructs the agent to infer and store can be privacy-sensitive.
Persistence & Privilege
always:false (normal). The skill relies on persistent storage in the workspace; autonomous invocation is enabled by default (normal). Combined with silent reading/writing and retention rules, persistent memory increases privacy risk if the workspace is shared or backed up. The skill does not request system-wide config changes or other skills' configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install soul-ledger - After installation, invoke the skill by name or use
/soul-ledger - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Soul Ledger 1.0.0 — initial release
- Introduces persistent user modeling for AI agents, capturing traits, drives, communication style, and behavioral evolution in `soul_ledger.json`.
- Provides a clear schema for storing and updating user information over time.
- Ensures agents adjust interactions based on the evolving user model, from the start of each conversation.
- Includes guidelines for updating the ledger after meaningful interactions, focusing on relevance rather than exhaustive logging.
- Emphasizes privacy, user ownership, and dynamic adaptation to personal change.
Metadata
Frequently Asked Questions
What is Soul Ledger?
Gives any AI agent persistent memory of who the user is — not just facts, but patterns, preferences, personality traits, and behavioral evolution over time.... It is an AI Agent Skill for Claude Code / OpenClaw, with 94 downloads so far.
How do I install Soul Ledger?
Run "/install soul-ledger" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Soul Ledger free?
Yes, Soul Ledger is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Soul Ledger support?
Soul Ledger is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Soul Ledger?
It is built and maintained by albionaiinc-del (@albionaiinc-del); the current version is v1.0.0.
More Skills