BytesAgain AI Skills Search

evaluate_skill

Full skill evaluation lab. Static analysis (23 patterns: sensitive file reads, remote exec, reverse shells, obfuscation) Docker sandbox execution (install skill, run with strace, monitor syscalls, file access, network) AI evaluation (strengths, weaknesses, risks, quality grade, verified capabilities) Returns: safety_score, risk_level, execution_report, evaluation (summary + verified_capabilities + strengths + weaknesses + risks + quality_grade + recommendation)

Input Schema

TableJSON Schema

Name	Required	Description	Default
`slug`	Yes	ClawHub skill slug to evaluate. Example: "shell", "invoice-pdf". Required.
`test_input`	No	Test input to pass to the skill. Default: "hello world".

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full transparency burden. It discloses the evaluation pipeline (static analysis patterns, Docker sandbox with strace and syscall monitoring, AI evaluation) and the return structure, giving a solid sense of what happens. It does not mention potential side effects or prerequisites (e.g., Docker availability), but covers the main behaviors well.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense and information-rich, front-loaded with the main purpose and then structured around the three evaluation phases. Every sentence contributes value, though the long return-fields list makes it slightly heavy. It is concise given the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no output schema, the description fully spells out the return fields (safety_score, risk_level, execution_report, evaluation with all subfields). It also explains the three evaluation stages, making the tool's behavior and outputs clear. This is robust for a multi-phase evaluation tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with both parameters ('slug' and 'test_input') having descriptive comments. The description adds no extra parameter semantics, but since the schema is complete, the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states what the tool does: it is a 'Full skill evaluation lab' with three concrete phases (static analysis, Docker sandbox execution, AI evaluation). It distinguishes itself from siblings like 'scan_skill' by emphasizing comprehensiveness (static analysis patterns, sandbox execution, AI evaluation).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description says this is a 'Full skill evaluation lab', which clearly signals when to use it over simpler tools like 'scan_skill' or 'score_skills'. It does not explicitly name alternatives or exclusions, but the context is strong enough to infer the intended use case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All BytesAgain AI Skills Search tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0

Disambiguation3/5

Several tools have overlapping purposes: evaluate_skill and scan_skill both assess skill safety, while generate_usecase, get_workflow, and score_skills all involve skill scoring and recommendation. Description differences exist but boundaries are not always crisp, potentially causing misselection. The unrelated get_deals tool also adds confusion.

Naming Consistency4/5

Tool names mostly follow a consistent verb_noun snake_case pattern (e.g., search_skills, get_skill, submit_request). Minor inconsistencies exist: popular_skills uses an adjective instead of a verb, and generate_usecase uses 'usecase' while search_use_cases uses 'use_cases'.

Tool Count4/5

With 14 tools, the server is on the higher end of the typical range but still well-scoped for its broad functionality (search, evaluation, workflows, community, content pipeline). Each tool serves a distinct functional area, though a few could be consolidated.

Completeness4/5

The core workflow of searching, retrieving, and evaluating skills is well covered, including use cases and community requests. However, there are minor gaps such as lack of a category browsing tool or direct single-skill installation, and the inclusion of unrelated AliExpress deals seems out of place.

Resources

Need Help?