Name: xai-agent-tools
Rating: 57.599999999999994 (1 reviews)
Author: fernandezbaptiste

xai-agent-tools

xAI Agent Tools API for autonomous tool calling with X search, web search, and code execution. Use when building agents that need real-time data access and autonomous task execution.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/xai-agent-tools/SKILL.md

The canonical home for this skill is xai-agent-tools in fernandezbaptiste/Skrillz

Quality

Content

65%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with abundant executable code, but it is a single long monolithic document that repeats boilerplate and lacks validation feedback loops for its cost-sensitive, multi-step tool-calling workflows. Progressive disclosure is limited because no reference files are used to offload detail.

Suggestions

Add explicit validation/checkpoint steps for batch and cost-sensitive tool-calling workflows (e.g. verify tool results before synthesizing, retry on failure) to lift workflow clarity above 3.

Split the tool-config reference and the repetitive agent-pattern functions into separate reference files (e.g. TOOL_CONFIG.md, AGENT_PATTERNS.md) and link to them from a leaner SKILL.md.

De-duplicate the repeated client setup and chat.completions.create boilerplate across the agent examples to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly code examples with light prose, but it repeats the same client-setup and chat.completions.create pattern across many near-identical agent functions and includes redundant commentary, so it could be tightened considerably.	3 / 5
Actionability	Every section provides complete, copy-paste-ready, executable Python with real parameters, tool config objects, and concrete examples covering the common cases (research, analysis, financial, streaming, conversation).	5 / 5
Workflow Clarity	The agent patterns show rough step sequences inside prompts, but there are no explicit validation checkpoints or error-recovery feedback loops for batch/cost-sensitive tool-calling operations, which caps the score at 3 per the rubric.	3 / 5
Progressive Disclosure	Content is organized into clear sections, but there are no bundle files and no one-level-deep references for the bulk of tool-config detail and agent patterns, so material that could live in separate files is inlined in a single long SKILL.md.	3 / 5
	Total	14 / 20 Passed

Description

67%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly states both what the skill does and when to use it, with concrete named tools and a reasonable trigger clause. Its main weakness is trigger-term quality, which relies on technical jargon rather than the natural phrases a user would say.

Suggestions

Add natural-language trigger phrases users actually say (e.g. 'search X/Twitter in an agent', 'have Grok run code and searches autonomously') alongside the technical terms.

Mention document_search alongside X search, web search, and code execution so the 'what' coverage matches the body.

Dimension	Reasoning	Score
Specificity	Names the domain (Agent Tools API) and several concrete actions ('autonomous tool calling with X search, web search, and code execution', 'real-time data access and autonomous task execution'), with only minor gaps such as document_search being omitted from the description.	4 / 5
Completeness	It explicitly answers both 'what' (autonomous tool calling with X/web search and code execution) and 'when' ('Use when building agents that need real-time data access and autonomous task execution'), though the 'when' clause is fairly high-level and could name more concrete trigger scenarios.	4 / 5
Trigger Term Quality	It includes some relevant terms ('agents', 'tool calling', 'X search', 'web search') but leans on technical jargon and misses natural synonyms or phrasings a user would actually say when needing real-time data access.	3 / 5
Distinctiveness Conflict Risk	The xAI/Grok Agent Tools niche is fairly distinct and tied to a specific provider's autonomous tool-calling loop, with only minor overlap risk against generic web-search or agent-building skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: .claude/skills/xai-agent-tools/SKILL.md
Commit: 93ed392

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.