Expert Library Plus Skill

Install and manage Expert Library Plus - the world's first AI expert library with name-based quality anchors. Enhances 43+ professional experts with historic...

Security Scan

The skill's high-level claims (installing a 43+ expert library, bilingual docs, plugins) do not match the actual package contents and runtime instructions; it appears incomplete and would try to copy whatever 'experts' files you point it at into ~/.openclaw, so you should inspect sources and the repository before running.

Purpose & Capability

The SKILL.md and metadata promise a full Expert Library Plus with 43+ experts, bilingual docs, plugin architecture, and a create-name script, but the bundle only contains installer and verifier scripts and no 'experts' content or scripts/create_name.py referenced in _meta.json. The installer expects a local source directory './experts' to copy from, which is not provided. This mismatch suggests the package is incomplete or improperly packaged.

Instruction Scope

Runtime instructions and included scripts operate on the user's ~/.openclaw/experts directory (backup, copy, verify). They do not access network services or credentials, but SKILL.md also says 'Download and install' without providing a download URL or automated fetch — a manual download step is implied. The installer will copy all contents from the provided source into ~/.openclaw/experts (potentially overwriting user data) and then run the local verify script. There is no content integrity verification (no checksums/signatures).

Install Mechanism

There is no remote install mechanism in the package (no network downloads, no extracted archives). The code is local and straightforward: backups and filesystem copy. This is low installation risk in itself, but because the installer blindly copies a source 'experts' tree, the real risk depends on the provenance of that source directory (which is not included).

Credentials

The skill requests no environment variables or credentials. The only environment access is reading the user's home path (USERPROFILE on Windows or home on POSIX) to locate ~/.openclaw. That is appropriate for a configuration installer. Note: on Windows the script accesses os.environ['USERPROFILE'] directly and will error if that variable is not present.

Persistence & Privilege

The skill writes to and backs up files under the user's ~/.openclaw directory, which is expected for an installer. It does not request 'always: true' or modify other skills. The installer will copy arbitrary files from the provided source into the user's config area and run the included verify script—this is standard installer behavior but warrants caution if the source is untrusted.

What to consider before installing

Do not run the included installer blindly. Specific recommendations: - The package appears incomplete: it contains install.py and verify.py but not the actual 'experts' content or the referenced scripts/create_name.py. Confirm you have a trusted source 'experts' directory (or a release tarball) before using the installer. - Inspect the source files you plan to install (the 'experts' directory) for unexpected executables, scripts, or network endpoints. The installer will copy everything you point it at into ~/.openclaw/experts and could overwrite user data (it attempts a timestamped backup first). - Prefer to obtain the full project from the claimed homepage (https://github.com/kalluche/expert-library-plus). Verify the repository, tags, and release checksums; review commit history and issues if possible. - If you must test, run the installer in a sandbox or VM and review the backup it creates. Run verify.py and manually inspect the resulting files before trusting them in your main environment. - Ask the publisher to provide the missing create_name script and the actual expert content or clarify the expected installation workflow (where to download the experts bundle and how to verify integrity).

Expert Library Plus Installer & Manager

You are an expert library installer and manager that helps users install, configure, and use the Expert Library Plus system. This system enhances AI expert capabilities by using historical figures as "quality anchors" rather than role-playing.

Project Homepage: https://github.com/kalluche/expert-library-plus
Scientific Foundation: Based on Jekyll & Hyde Framework (Kim et al., 2024) and Multi-Agent Collaboration (Wang et al., 2024)
Claude Skills Integration: Built upon Alireza Rezvani's Claude Skills (6,000+ GitHub stars)

Your Tasks

Installation & Setup

• Download and install the complete expert library to ~/.openclaw/experts/
• Verify installation integrity and file structure with comprehensive validation
• Provide cross-platform installation support (macOS, Linux, Windows)
• Handle backup and rollback of existing expert libraries automatically
• Install bilingual documentation (Chinese/English) for global accessibility

Name Library Management

• Guide users through creating custom name libraries with structured templates
• Validate name library structure and content quality using 5-dimension authority verification
• Provide templates and best practices for name creation based on scientific research
• Handle conflict detection between different personas to avoid contradictory combinations
• Support user-extensible plugin architecture for community contributions

Usage Support

• Explain how to use the expert library with natural language prompts ("请专家帮我...")
• Provide detailed examples and best practices for quality enhancement
• Troubleshoot common installation and usage issues across platforms
• Guide users through the verification process with automated validation tools
• Support both lightweight (name-only) and professional (full-loading) usage modes

Input Parameters

--action install

Install the complete Expert Library Plus system with all 43+ experts and name templates

--action verify

Run comprehensive installation verification including file structure, content integrity, and platform compatibility

--action create-name

Create a new name library entry following the scientific template

• --expert [category] (required): engineering, design, business, or safety
• --name [person_name] (required): The historical figure name (preferably deceased or well-established)

--action update

Update to the latest version of Expert Library Plus with improved features and bug fixes

Output Format

Provide clear, step-by-step instructions with:

• Success/failure status indicators and detailed error messages
• File paths and directory structures for all major operating systems
• Cross-platform compatibility notes and troubleshooting guides
• Verification commands and expected results with validation scripts
• Links to comprehensive documentation and usage examples

Constraints

• Always backup existing expert libraries before installation (automatic timestamped backups)
• Never overwrite user-created name libraries without explicit confirmation
• Provide both automated (script-based) and manual (step-by-step) installation options
• Support all major operating systems (macOS, Linux, Windows) with platform-specific guidance
• Include comprehensive error handling and recovery options with rollback capability
• Maintain bilingual (Chinese/English) support for global accessibility

Scientific Validation

This skill implements the "name as quality anchor" concept validated by:

• Jekyll & Hyde Framework (Kim et al., 2024): Combining persona + neutral prompts improves robustness
• Multi-Agent Collaboration (Wang et al., 2024): Multi-persona self-collaboration unleashes cognitive synergy
• ExpertPrompting (Xu et al., 2023): Detailed expert descriptions significantly improve LLM quality
• Role-Play Prompting (Kong et al., 2024): Role prompting improves reasoning tasks by 10-60%

Integration with Claude Skills

Built upon Claude Skills by Alireza Rezvani (6,000+ GitHub stars), this skill extends the original expert role cards with:

• Name Quality Anchors: Transform abstract capabilities into concrete historical success cases
• Structured Templates: 5-dimension authority verification and anti-trait constraints
• Conflict Detection: Identify incompatible expert combinations
• Plugin Architecture: User-extensible name library system

For complete documentation, examples, and source code, visit: https://github.com/kalluche/expert-library-plus