← Back to Skills Marketplace
587
Downloads
1
Stars
3
Active Installs
2
Versions
Install in OpenClaw
/install skill-cortex-pub
Description
Skill Cortex is the system's capability cortex. When lacking ability, it autonomously acquires Skills from ClawHub or GitHub, then releases them after use. E...
Usage Guidance
This Skill is conceptually useful (it lets the agent find and temporarily use other Skills), but it leaves important runtime details unspecified. Before installing: 1) Confirm which installer/tools it will actually call (clawhub CLI, git, curl, package managers) and ensure those binaries will be present or blocked; 2) Expect it to create ~/.openclaw/skill-cortex/cortex.json — back up or inspect that file and verify the entity‑filtering behavior; 3) Recognize that installing third‑party Skills means running unreviewed code — require sandboxing or strict user confirmation for every install and for system dependency installs; 4) Ask the author for explicit install commands, allowed sources (only official ClawHub? only vetted GitHub orgs?), and the exact safety checks performed (VirusTotal, checksums, signatures, sandboxing); 5) If you need stronger guarantees, run the Skill in an isolated environment (VM/container) or decline until the Skill exposes a clear, auditable installation flow. Because runtime behavior depends on external installs that are not fully specified, treat this Skill with caution.
Capability Analysis
Type: OpenClaw Skill
Name: skill-cortex-pub
Version: 0.0.2
The OpenClaw AgentSkills skill bundle 'skill-cortex' is designed to autonomously manage the acquisition and use of other skills from external sources like ClawHub or GitHub. While this core functionality inherently involves downloading and executing external code, the bundle includes extensive and explicit safety mechanisms. These include mandatory user confirmation for all skill installations and system dependency installations, strict exclusion of write/delete/shell operations from automated 'reflex' mode, privacy-focused entity filtering for stored data, and structured learning to prevent arbitrary LLM instructions. There is no evidence of prompt injection attempts, data exfiltration, malicious execution, persistence, or obfuscation within the provided files. The design documents clearly outline the risks and how they are mitigated, indicating a strong intent for secure and privacy-aware operation.
Capability Assessment
Purpose & Capability
The Skill claims to search ClawHub/GitHub and install/run other Skills, but the package declares no required binaries, no network access, and no CLI (README mentions the 'clawhub' CLI). Installing or building Skills normally requires tools (clawhub, git, package managers) and network access; the lack of declared dependencies is a mismatch between stated purpose and declared requirements.
Instruction Scope
SKILL.md instructs the agent to read/write a persistent cortex file (~/.openclaw/skill-cortex/cortex.json), search external hubs, present candidates, install selected Skills, generate execution plans, run them, and update learning memory. Although it requires explicit user approval for installs and claims write operations never enter reflex, the instructions still enable fetching and executing arbitrary third‑party code and persisting behavioral data — the flow and safeguards for scanning or sandboxing fetched Skills are underspecified.
Install Mechanism
There is no install spec (instruction-only), which lowers immediate disk-write risk from the skill bundle itself—but the Skill's runtime behavior depends on installing external Skills from ClawHub/GitHub. The mechanism, hosts, and commands used to install those Skills are not specified; that omission means arbitrary remote archives or repos could be pulled and executed, which is high risk unless clearly constrained to vetted sources and explicit install commands.
Credentials
The skill declares no required environment variables or primary credential, yet its DESIGN.md and examples reference reading env names (e.g., TODOIST_API_KEY), running 'which <key>', network endpoints, and possibly invoking other Skills that will need credentials. It may therefore prompt for or consume unrelated credentials during candidate validation or Skill installation; the credential needs and handling are not declared or constrained.
Persistence & Privilege
always:false (good) and installs require user confirmation per SKILL.md, but the Skill creates and maintains a persistent cortex.json under ~/.openclaw/skill-cortex which stores routing and usage data. That persistent store includes signal words and metadata; DESIGN.md claims entity filtering, but the agent will still persist behavioral metadata locally — consider this a privacy/attack surface risk if third‑party Skills can read or exfiltrate it.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install skill-cortex-pub - After installation, invoke the skill by name or use
/skill-cortex-pub - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.0.2
- Streamlined and simplified the SKILL.md documentation for clarity and brevity.
- Removed detailed internal process descriptions, edge case handling, confidence scaling, and pruning specifics.
- Condensed multi-phase workflow and rules to a high-level overview, focusing on key user-facing steps.
- Updated file and schema references for consistency.
- Boundary rules summarized and clarified for easier understanding.
v1.0.1
- Added initial public documentation for Skill Cortex, detailing its phases: Perception, Validation & Authorization, Execution, and Learning & Cleanup.
- Completely outlined reflex mode rules, standard mode flows, and boundary conditions for handling skills and user tasks.
- Defined mechanisms for short-term memory management, skill search, candidate selection, and adaptive learning from usage outcomes.
- Specified strict entity filtering and structured knowledge recording during the skill learning process.
- Included rules for installation, retention, pruning, and self-organization of skill regions and memory.
- Clarified security and user confirmation policies, especially for installation and destructive actions.
Metadata
Frequently Asked Questions
What is Skill Cortex Pub?
Skill Cortex is the system's capability cortex. When lacking ability, it autonomously acquires Skills from ClawHub or GitHub, then releases them after use. E... It is an AI Agent Skill for Claude Code / OpenClaw, with 587 downloads so far.
How do I install Skill Cortex Pub?
Run "/install skill-cortex-pub" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Skill Cortex Pub free?
Yes, Skill Cortex Pub is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Skill Cortex Pub support?
Skill Cortex Pub is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Skill Cortex Pub?
It is built and maintained by Ank Wu (@ankwu001); the current version is v0.0.2.
More Skills