← Back to Skills Marketplace
309
Downloads
2
Stars
0
Active Installs
39
Versions
Install in OpenClaw
/install relic-soul-chip
Description
One soul, many agents. Persistent AI personality and cross-agent memory sync via pure Markdown files. Zero deps.
Usage Guidance
This skill is coherent and instruction-only, but check these points before installing: (1) Confirm you are comfortable letting an agent read and write files under ~/relic/brain/ (SOUL.md, MEMORY.md, SESSIONS/, etc.). (2) The anchor that makes the integration persistent must be manually pasted by you into your host's config — never paste sensitive secrets into the anchor. (3) During an upload/import (Scenario A) the agent may ask you to provide paths to files outside ~/relic/brain/ — only provide paths or paste content that you explicitly approve. (4) The skill may ask the host agent/platform to 'sync' memories into the platform's built-in memory; verify whether your platform will perform those writes automatically or will prompt you, since the skill itself asserts it cannot programmatically modify host config files. (5) The optional network check goes to raw.githubusercontent.com only — if you prefer, keep the agent offline while reviewing. If any of these behaviors are unacceptable or unclear, ask the skill author (or refuse) before enabling.
Capability Analysis
Type: OpenClaw Skill
Name: relic-soul-chip
Version: 2.1.1
The 'relic-soul-chip' skill is a framework for maintaining persistent AI personality and memory across different agent platforms using local Markdown files in `~/relic/brain/`. It employs a manual 'anchor' mechanism where users copy-paste instructions into agent configuration files (e.g., `AGENTS.md`, `CLAUDE.md`) to trigger a boot sequence each session. While the skill requests broad filesystem access to its own directory and includes instructions for the agent to read/write personal data and conversation logs, it emphasizes user consent, local storage, and manual configuration. Security risks are addressed through explicit rules against automated config modification and requirements for per-item user approval for sensitive data (passwords, API keys). No evidence of malicious intent, data exfiltration, or unauthorized execution was found in `SKILL.md`, `AGENT.md`, or the documentation files.
Capability Tags
Capability Assessment
Purpose & Capability
The name/description (cross-agent, Markdown-based persistent persona) match the instructions: the skill reads and manages SOUL.md/USER.md/MEMORY.md and related directories under ~/relic/brain/. It requests no external credentials or binaries. Required filesystem scope and operations are proportional to the stated purpose.
Instruction Scope
SKILL.md is an instruction-only protocol that limits programmatic writes to ~/relic/brain/ and explicitly requires the anchor be pasted manually by the user into host config files (user_manual_paste). It allows one optional HTTP GET (version check). One area of mild ambiguity: the protocol repeatedly says you should 'sync new memories to your platform's built-in memory system' — the skill claims it has no programmatic ability to write host config files, so this sync must be performed by the host platform or by the agent using host-provided memory APIs. Ensure you understand whether your host agent/platform will perform those writes automatically or whether it will prompt you; do not assume the skill will autonomously modify host config files.
Install Mechanism
No install spec or code files are present; the skill is instruction-only. That is the lowest-risk install mechanism and matches the 'zero deps' claim.
Credentials
The skill requests no environment variables, no credentials, and no config-path access beyond the specified ~/relic/brain/ files. The single optional network request is to a well-known host (raw.githubusercontent.com) for version checking and is described as read-only. This is proportionate to the stated functionality.
Persistence & Privilege
always is false and disable-model-invocation is false (normal). The skill does not request permanent system-wide privileges and explicitly states it cannot programmatically write host config files; anchor planting is performed by the user via manual paste. No elevated persistence is requested.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install relic-soul-chip - After installation, invoke the skill by name or use
/relic-soul-chip - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.1.1
relic-soul-chip v2.1.1
- Clarified and strengthened documentation and metadata on security and file access.
- Rewrote all config file modification descriptions to emphasize zero programmatic write capability; all config changes require manual user copy-paste.
- Added explicit details on user control over SOUL.md/USER.md, including read-only and delete options.
- Documented optional, one-way host memory sync flow; clarified that Relic files remain unchanged and sync is user/host-initiated only.
- No changes to core functionality—this is a documentation/manifest hardening and policy update for transparency and compliance.
v2.1.0
## v2.1.0
- Expanded and updated docs: major improvements to `docs/load-soul.md`, `docs/resonate-soul.md`, and `docs/upload-soul.md` (plus localized versions).
- Documentation now covers usage, scenarios, and multi-agent workflows in greater detail.
- Chinese localization updated for new and existing feature explanations.
- No changes to core security model or config anchors—update is documentation-focused.
v2.0.0
Relic Soul Chip 2.0.0
- Major documentation overhaul: rewritten and expanded English and Chinese docs for `load-soul.md` and `upload-soul.md`.
- Updated skill version to 2.0.0 in all docs and metadata files.
- Clarified installation/setup instructions and agent onboarding flow.
- Improved explanation of manual anchor pasting and security model.
- Expanded details on the one-time user-directed import for initial setup.
v1.9.0
## relic-soul-chip 1.9.0
- Config anchor can now only be added by manual user copy-paste; agent-assisted planting is no longer supported.
- Updated config_write description to clarify: the skill never writes to any config file—only outputs text for user to paste using their own editor.
- Tightened safety language: no agent-assisted mode for config changes, all actions are user-initiated.
- Added extra clarification about how SOUL.md personality settings are treated as user preferences, not behavioral overrides.
- No changes to file/folder access, network policy, or core functionality.
v1.8.0
**Relic Soul Chip 1.8.0 Changelog**
- Clarified and strengthened the config file anchoring process: anchor text is now generated and displayed to the user for manual copy-paste, not written automatically.
- Updated frontmatter to specify user_manual_paste as the default config modification method, with agent-assisted planting as an explicit, opt-in fallback only.
- Expanded and reorganized config_write documentation for increased clarity and security transparency.
- Emphasized user control and manual involvement in all critical actions, especially regarding configuration changes.
- No executable code, background processes, or new network access added; security and privacy guarantees remain unchanged.
v1.7.0
Version 1.7.0
- Added explicit documentation of one-time user-directed file reads outside ~/relic/brain/ during initial setup, with strict user consent and limited scope.
- Declared new fields in the frontmatter: `network_access` (details optional version check HTTP GET) and `user_directed_read` (covers explicit user-initiated import scenarios).
- Clarified security and behavior guarantees in the SKILL.md, directly addressing common automated scanner concerns regarding file and network access.
- No changes to executable or operational logic; skill remains instruction-only and security-focused.
v1.6.0
- Updated version and documentation for clarity and user protection; now at v1.5.0.
- The anchor instruction block now includes a description of size (~60 lines), with explicit mention of a status report template, and improved clarity that it contains no executable code.
- Session conversation logging is now disabled by default—user must explicitly opt in and consent to each log individually.
- Enhanced user control: anchor is never planted without showing the full content; users are encouraged to manually copy/paste the anchor for maximum safety.
- General tightening of privacy/security guarantees, emphasizing local-only file access and strict consent protocols for importing sensitive data.
v1.5.0
Relic Soul Chip 1.5.0 — Documentation and guide expansion
- Expanded and updated documentation files, including EN and ZH-CN guides for load, resonate, and upload soul workflows.
- Improved instructions for data capture, anchor setup, and file system access.
- Clarified user consent and sensitive information import steps in user-facing docs.
- Refined Markdown to improve readability in all help and setup files.
- No functional changes to code or permissions; this release focuses on clarity and guidance.
v1.4.0
relix-soul-chip 1.4.0
- Improved privacy protection: Anchor block can never include content from SOUL.md or any Relic data, only a short instructional text.
- Enhanced user consent: Each conversation now requires individual user approval before importing into SESSIONS/; no bulk import without review.
- Documentation updated for stronger safety guarantees and stricter instructions regarding sensitive information and anchor behavior.
- Clarified that all persistent data stays strictly in ~/relic/brain/ and is never copied or exported via config file anchors.
- Updated Chinese and English documentation for load-soul and upload-soul accordingly.
v1.3.2
Security hardening: reinforced anchor safety guarantees (plain text only, no executable code, user reviews before planting). Added hardening options (chmod 444, SESSIONS opt-out). Clarified all import consent flows.
v1.3.1
ClawHub security hardening: removed all ambiguous scan instructions, replaced with explicit user-ask-only workflow. No self-scanning, no auto-inventory, no reading files without user permission.
v1.3.0
v1.2.1 protocol fixes: mandatory boot report in anchors, MEMORY category format, SKILLS no-restriction, entry definition, correction format, multi-agent write risk, TROUBLESHOOTING rewrite, Hermes integration guide, version check timeout
v1.2.6
Version 1.2.6
- Expanded SKILL.md with detailed file access, security policy, and anchor config write/rollback instructions
- Clarified which files are read/written and when, including new directories such as INBOX/
- Documented exact anchor-write flow and explicit user confirmation requirements
- Improved specification of handling and confirmation for sensitive user data
- Updated documentation files (upload-soul.md, load-soul.md) in both English and Chinese for step-by-step scenario clarity
v1.2.5
Relic Soul Chip 1.2.5 Changelog
- Improved and clarified documentation in both English and Chinese, including detailed updates to load-soul.md and upload-soul.md.
- No code logic changes; all updates are documentation-only.
v1.2.4
Relic Soul Chip 1.2.4 Changelog
- Updated SKILL.md and SKILL.zh-CN.md to improve metadata formatting and clarify documentation.
- Added explicit author, license, homepage, and metadata fields for skill registry compatibility.
- Streamlined skill description and quick start guide for clarity.
- Emphasized that agents should use AGENT.md or AGENT.zh-CN.md for operational steps, not SKILL.md.
- No functional or behavioral changes to skill logic.
v1.2.3
v1.2.3: Include all runtime instruction files for complete security verification
v1.2.2
v1.2.2: Declared anchor config file whitelist, rollback instructions, and data capture rules per security review
v1.2.1
v1.2.1: Self-contained package - AGENT files included, explicit file system and network declarations for security review
v1.2.0
v1.2.0: Ultra-thin router architecture - AGENT.md routing + scenario file split + brain/ pure data + resonate-soul daily boot
v1.1.1
v1.1.1: Terminology unification (躯壳/Host), full bilingual completion, open memory format (100% info preservation), Cyberpunk 2077 themed examples. Author: LucioLiu. GitHub: github.com/LucioLiu/relic
Metadata
Frequently Asked Questions
What is Relic Soul Chip?
One soul, many agents. Persistent AI personality and cross-agent memory sync via pure Markdown files. Zero deps. It is an AI Agent Skill for Claude Code / OpenClaw, with 309 downloads so far.
How do I install Relic Soul Chip?
Run "/install relic-soul-chip" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Relic Soul Chip free?
Yes, Relic Soul Chip is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Relic Soul Chip support?
Relic Soul Chip is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Relic Soul Chip?
It is built and maintained by LucioLiu (@lucioliu); the current version is v2.1.1.
More Skills