← Back to Skills Marketplace
zhangchenchen

Skill Optimizer

by zhangchenchen · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ✓ Security Clean
137
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install skill-optimizer-2
Description
Analyze the current conversation history and local installed skills to identify missed skill triggers, overlapping or duplicate skills, weak metadata, stale...
Usage Guidance
This skill appears coherent and appropriate for auditing local skills, but before running it you should: (1) confirm which directories it may scan (e.g., ./skills, ./.agents/skills) so it does not access unrelated sensitive files; (2) prefer running an initial dry-run read-only audit and review the generated report before allowing any edits; (3) avoid storing secrets in skill files or in locations that the auditor will scan, or explicitly exclude those paths; and (4) when presented with the action queue, verify targets (absolute paths) before choosing Delete or Merge. If you want stronger safeguards, ask the skill to limit its scan to explicit paths you list and to require confirmation for every file-modifying step.
Capability Analysis
Type: OpenClaw Skill Name: skill-optimizer-2 Version: 0.1.0 The skill-optimizer-2 bundle is a governance tool designed to audit local skill installations for duplicates, weak metadata, and security risks (e.g., skills lacking guardrails). While it possesses the capability to modify or delete files, the instructions in SKILL.md explicitly mandate a 'report-first' approach, requiring user confirmation before any changes are made. No evidence of data exfiltration, unauthorized execution, or malicious intent was found across the code or documentation.
Capability Assessment
Purpose & Capability
Name and description claim an audit of the current conversation and locally visible skills; the SKILL.md only asks the agent to read the conversation and local skill directories, produce a report, and wait for the user's confirmation before making edits — all of which align with the stated purpose.
Instruction Scope
Runtime instructions explicitly tell the agent to scan the current thread and 'locally visible skill directories' (examples provided). This is appropriate for an optimizer, but the instructions do not strictly limit scanning to a small set of safe paths — there is a small risk the agent could search broader workspace files if 'locally visible' is interpreted widely. The SKILL.md does, however, require editing only after explicit user selection and instructs the agent not to modify files during analysis.
Install Mechanism
No install spec, no code files to write or execute. Instruction-only skills are lowest-risk from an install perspective.
Credentials
The skill declares no required environment variables, binaries, or credentials. The only resource access it needs is file-system visibility to skill directories and access to the current conversation, which is proportionate to the audit task. Note: if user skills store secrets in their skill files or nearby config, the auditor could read those files unless the user confines the scan scope.
Persistence & Privilege
always is false and model invocation is allowed (default). The skill does not request persistent installation, nor does it claim to modify other skills without explicit user confirmation. Autonomous invocation is normal platform behavior and not by itself concerning here.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install skill-optimizer-2
  3. After installation, invoke the skill by name or use /skill-optimizer-2
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
Initial release of Skill Optimizer — a tool for auditing, optimizing, and managing skill sets and trigger quality. - Audits conversation history and local skill directories for missed triggers, duplicates, metadata issues, risky or stale skills, workflow problems, and overlap. - Produces a structured audit report with evidence and an actionable queue for user decisions. - Suggests fixes, merges, deletions, or keeping skills; edits only after user confirmation. - Enforces strict, user-facing action options: Fix, Merge, Delete, or Keep and Skip. - Designed for safety: no silent edits, deletion confirmations, and nuanced recommendations.
Metadata
Slug skill-optimizer-2
Version 0.1.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Skill Optimizer?

Analyze the current conversation history and local installed skills to identify missed skill triggers, overlapping or duplicate skills, weak metadata, stale... It is an AI Agent Skill for Claude Code / OpenClaw, with 137 downloads so far.

How do I install Skill Optimizer?

Run "/install skill-optimizer-2" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Skill Optimizer free?

Yes, Skill Optimizer is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Skill Optimizer support?

Skill Optimizer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Skill Optimizer?

It is built and maintained by zhangchenchen (@zhangchenchen); the current version is v0.1.0.

💬 Comments