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

69%

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 ./skills/xai-agent-tools/SKILL.md

Quality

Content

50%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 body is a well-structured API catalog with executable code, a cost table, and error handling, but it has three systematic weaknesses: heavily duplicated agent-pattern examples that inflate token budget, orphaned tool configs that are never integrated into a real request, and no content split across reference files. It reads as a reference dump rather than a workflow that gets Claude to a working tool-enabled agent quickly.

Suggestions

Show one complete example that passes the tool configurations (e.g., x_search_config) into client.chat.completions.create so the configs are actually wired to the API, and drop the unused config fragments or fold them into that example.

Consolidate the five near-identical agent-pattern functions (research, analysis, financial, multi-step, cost-optimized) into a single parameterized example plus a short table of prompt strategies — they differ only in prompt text, not in API usage.

Move the agent patterns, cost management, and model-selection sections into a references/ file (e.g., references/patterns.md) linked from a lean SKILL.md overview, keeping the main file to Quick Start and core tool configuration.

Dimension	Reasoning	Score
Conciseness	Prose is lean with no concept over-explanation, but eight code blocks (research_agent, analysis_agent, financial_agent, multi_step_agent, cost_optimized_agent, robust_agent, streaming_agent, ConversationalAgent) are structurally identical create() calls differing only in prompt text — ~150 lines of near-duplicate code that could be tightened, matching anchor 3 rather than anchor 4's 'minor instances'.	3 / 5
Actionability	Quick Start is copy-paste ready, but the tool configuration dicts (x_search_config, web_search_config, code_execution_config) are never shown being passed to an API call — no example demonstrates actually enabling tools, and the 'Agent with automatic tool use' example enables none. This missing key detail places it at anchor 3 rather than anchor 4's minor gaps.	3 / 5
Workflow Clarity	The content is organized as a catalog (setup → configs → patterns → error handling) with an error-handling example, but there is no explicit step sequence or validation checkpoints for building an agent — the implied flow matches anchor 3's 'sequence present but checkpoints missing or implicit'. No destructive/batch cap applies.	3 / 5
Progressive Disclosure	Section headers are clear and a References section with external links exists, but everything is inlined in a single ~330-line file; the agent patterns, cost management, and model-selection content would sit better in reference files, matching anchor 3's 'content that should be separate is inline' rather than anchor 4's appropriate placement.	3 / 5
	Total	12 / 20 Passed

Description

75%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.

A solid description that clearly states what the skill covers and when to use it, with a specific trigger clause and mostly natural keywords. Its main limitations are modest coverage gaps (no document_search, no Grok/Twitter synonyms) and some trigger-term overlap with closely related xAI skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('xAI Agent Tools API') and several concrete actions ('autonomous tool calling with X search, web search, and code execution'), matching anchor 4's several specific actions with minor gaps — comprehensive coverage (anchor 5) is not reached since document_search and configuration capabilities are unmentioned.	4 / 5
Completeness	Both 'what' ('autonomous tool calling with X search, web search, and code execution') and an explicit 'when' ('Use when building agents that need real-time data access and autonomous task execution') are present; the when-clause is explicit but less concrete than anchor 5's multi-trigger phrasing, so 4 fits best.	4 / 5
Trigger Term Quality	Good natural keyword coverage ('building agents', 'X search', 'web search', 'code execution', 'real-time data access'), but a few natural terms users would say are missing (e.g., 'Grok', 'Twitter'), placing it just below anchor 5's comprehensive synonym/extension coverage.	4 / 5
Distinctiveness Conflict Risk	'Agent Tools API' carves a clear niche with distinct triggers, but 'web search' and 'code execution' overlap generic search/code-execution skills and the sibling xai-x-search skill, matching anchor 4's minor overlap risk rather than anchor 5's minimal conflict risk.	4 / 5
	Total	16 / 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: skills/xai-agent-tools/SKILL.md
Commit: 93ed392

Reviewed: 14 hours 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.