← Back to Skills Marketplace
133
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install normieclaw-knowledge-vault
Description
You have 200 bookmarks you'll never revisit and a 'Read Later' list that's basically a graveyard. Knowledge Vault changes the game: paste any URL — article,...
Usage Guidance
This skill is broadly coherent with its stated purpose, but take these precautions before installing:
- Review the SETUP-PROMPT.md before pasting or executing it. It contains shell commands (mkdir, install, chmod, cat). Only run them in a workspace you trust and have permission to modify.
- Confirm your agent platform's memory/long-term-storage policy. The vault config enables syncing entries to the agent's memory_store; if you don't want persistent storage, disable memory_integration or adjust importance/retention settings.
- Inspect scripts/vault-stats.sh locally before running. It requests jq and performs file reads; I noticed some malformed/odd code fragments in the script (likely a bug). Don't run scripts you haven't reviewed in an untrusted environment.
- The skill will fetch external URLs when you ask it to ingest content (web_fetch/browser). Only ingest URLs you trust, and be comfortable with the agent making outbound fetches on your behalf.
- If you plan to deploy the dashboard or API routes, secure them behind auth and don't expose the local data directory publicly.
If you want higher assurance, ask the author for a reproducible install/test in a sandbox or request an updated release that fixes the script issues and documents platform/tool expectations.
Capability Analysis
Type: OpenClaw Skill
Name: normieclaw-knowledge-vault
Version: 1.0.3
The Knowledge Vault skill bundle is a well-documented and security-conscious tool for content ingestion and summarization. The SKILL.md file includes explicit and robust prompt-injection defenses, instructing the agent to treat all fetched content as untrusted data and ignore any embedded commands. The utility script (vault-stats.sh) and setup instructions (SETUP-PROMPT.md) use transparent shell commands with safe practices, such as restricted file permissions (chmod 600/700) and strict error handling (set -euo pipefail). No indicators of data exfiltration, malicious execution, or unauthorized persistence were found.
Capability Assessment
Purpose & Capability
Name/description (save, summarize, and search saved content) matches the actions described in SKILL.md and the included files. The skill uses agent tools (web_fetch, pdf, summarize, memory_store) and local storage (data/, config/, scripts/) which are appropriate for a vault-style capability.
Instruction Scope
SKILL.md stays on-topic (fetch content, summarize, store entries). It explicitly instructs the agent to treat fetched content as data, not as executable instructions (prompt-injection defense). One setup convenience asks the user to paste a shell-based 'SETUP-PROMPT' into the agent chat which runs mkdir/install/cat commands to copy files into the workspace — this is functional for local installation but is a sensitive step: review the commands before executing them and only run them in a trusted environment.
Install Mechanism
No network downloads or package installs are specified; this is instruction-only with two local files copied by the setup script. No remote URLs, installers, or extracted archives are present.
Credentials
The skill declares no required environment variables, credentials, or external endpoints. It does enable memory_integration (writing to the agent's long-term memory) in config/vault-config.json — this is reasonable for a vault but is a persistence/privacy consideration the user should be aware of.
Persistence & Privilege
always:false (not forced). The skill writes to local workspace directories (data/, config/, scripts/) and integrates with the agent's memory_store per config. Autonomous invocation is allowed by default (platform default); combined with memory writes this expands blast radius compared to a read-only skill, so confirm platform memory retention settings if you are sensitive about long-term storage.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install normieclaw-knowledge-vault - After installation, invoke the skill by name or use
/normieclaw-knowledge-vault - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
v1.0.3: Security fixes: confined scripts to skill directory, removed filesystem traversal from setup
v1.0.2
v1.0.2: MIT license, cleaned descriptions, removed cross-sell
v1.0.0
Initial publish from NormieClaw.ai — Free OpenClaw skills for everyone.
Metadata
Frequently Asked Questions
What is Knowledge Vault?
You have 200 bookmarks you'll never revisit and a 'Read Later' list that's basically a graveyard. Knowledge Vault changes the game: paste any URL — article,... It is an AI Agent Skill for Claude Code / OpenClaw, with 133 downloads so far.
How do I install Knowledge Vault?
Run "/install normieclaw-knowledge-vault" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Knowledge Vault free?
Yes, Knowledge Vault is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Knowledge Vault support?
Knowledge Vault is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Knowledge Vault?
It is built and maintained by Nollio (@nollio); the current version is v1.0.3.
More Skills