← Back to Skills Marketplace
skill-expert-skills
by
TinkCarlos
· GitHub ↗
· v1.0.1
310
Downloads
0
Stars
4
Active Installs
2
Versions
Install in OpenClaw
/install skill-expert-skills-openclaw
Description
Creates, optimizes, validates, and packages AI Agent Skills (SKILL.md format). Mandatory 6-Phase workflow with quality gates: Phase 0: Task Classification +...
Usage Guidance
This package appears coherent with its stated purpose, but take standard precautions before running code: 1) Review scripts (scripts/*.py) and requirements.txt yourself to ensure they do only what you expect. 2) Run any pip install commands inside an isolated virtualenv and not as root. 3) Be aware the tool will read and write files under the skill directories you point it at (init_skill, package_skill), so avoid pointing it at system or secrets directories. 4) If you do not want an agent to run these scripts autonomously, keep model-invocation disabled for this skill in your agent settings. 5) If you plan to allow network access, note SKILL.md recommends web searches/URL fetch — consider whether that is acceptable in your environment.
Capability Analysis
Type: OpenClaw Skill
Name: skill-expert-skills-openclaw
Version: 1.0.1
The skill bundle is a comprehensive toolkit designed to assist in the creation, optimization, and validation of AI Agent Skills. It includes a suite of Python utility scripts (e.g., scripts/quick_validate.py, scripts/universal_validate.py, scripts/package_skill.py) that perform structural checks, quality scoring, and portability audits. Notably, universal_validate.py actively scans for and flags sensitive absolute paths to prevent accidental data leakage or portability issues. The instructions in SKILL.md and the extensive documentation in the references/ directory are strictly aligned with the stated purpose of improving skill development workflows and do not contain any malicious patterns, exfiltration logic, or prompt injection attacks.
Capability Assessment
Purpose & Capability
The name/description promise (create/optimize/validate/package SKILL.md-based skills) aligns with the included scripts (init_skill, quick_validate, universal_validate, package_skill, analyze_trigger, diff_with_official, etc.) and the many reference docs. The skill does not request unrelated environment variables or credentials.
Instruction Scope
SKILL.md describes multi-phase workflows and explicitly tells the agent to use local docs, scripts, and (when available) external research tools (web search / URL fetch). The frontmatter lists allowed-tools (Read Write Bash Grep Glob), and the included scripts perform filesystem operations (create SKILL.md, read/write directories, package files). This is expected for a skill-creator tool, but be aware the instructions suggest using network-based research tools when available — the skill does not declare network access or credentials, so network use depends on the agent environment rather than the skill itself.
Install Mechanism
There is no install spec (instruction-only SKILL.md), which lowers automatic risk. However documentation/quick-navigation instructs users to run pip install -r scripts/requirements.txt; a requirements.txt exists (content not shown here). Running those commands would pull external packages. The repository itself contains many local Python scripts; packaging code writes zip files locally. There are no downloads from arbitrary URLs in the provided scripts.
Credentials
The skill declares no required env vars, no primary credential, and no config paths — appropriate for a tooling/authoring skill. The scripts legitimately need local filesystem access to create/validate/package skills; no sensitive or unrelated credentials are requested.
Persistence & Privilege
always:false and user-invocable:true (default) — the skill does not demand forced/global inclusion. The scripts create or modify files under user-specified skill directories (init_skill, package_skill), which is expected behavior for an authoring tool. The skill does not attempt to modify other skills' configurations or claim system-wide privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install skill-expert-skills-openclaw - After installation, invoke the skill by name or use
/skill-expert-skills-openclaw - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
**Major update with new workflow, conciseness, and classification features**
- Introduced Fast Track Decision: classify skill tasks as Simple, Standard, or Complex for tailored workflow paths.
- Adopted consistent reference pointer pattern (→ references/xxx.md) for offloading details.
- Added SKILL.md Positioning rules and a 5-point Conciseness Checklist (NON-NEGOTIABLE).
- Expanded metadata: now includes version 4.0.0, last_updated, and enhancement notes.
- Consolidated references navigation and included phase-based guides for each step.
- Retained strict quality gates, Definition of Done, and Source Credibility Tiers.
v1.0.0
- Initial release of the Skill Expert—Universal Edition.
- Provides a mandatory 6-phase workflow for creating, optimizing, validating, and packaging AI Agent Skills.
- Includes detailed quality gates, checklist-based phase progression, and user confirmation at key stages.
- Enforces concise, maintainable SKILL.md structure and strict separation between core instructions and references.
- Supports Python 3.8+ for validation scripts.
Metadata
Frequently Asked Questions
What is skill-expert-skills?
Creates, optimizes, validates, and packages AI Agent Skills (SKILL.md format). Mandatory 6-Phase workflow with quality gates: Phase 0: Task Classification +... It is an AI Agent Skill for Claude Code / OpenClaw, with 310 downloads so far.
How do I install skill-expert-skills?
Run "/install skill-expert-skills-openclaw" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is skill-expert-skills free?
Yes, skill-expert-skills is completely free (open-source). You can download, install and use it at no cost.
Which platforms does skill-expert-skills support?
skill-expert-skills is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created skill-expert-skills?
It is built and maintained by TinkCarlos (@tinkcarlos); the current version is v1.0.1.
More Skills