xurl

A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.

1.44x

Quality

—

Does it follow best practices?

Impact

97%

1.44x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

72%

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

The body is highly actionable with executable commands and clear section organization, but it loses some token efficiency to duplication between the Quick Reference table and Command Details, and its workflows omit validation checkpoints for destructive and batch operations.

Suggestions

Collapse the duplication between the Quick Reference table and the Command Details code blocks — keep the table as the index and have Command Details cover only non-obvious flag combinations and edge cases.

Add explicit validation/confirmation checkpoints to destructive and batch workflows, e.g. a confirm-or-preview step before 'xurl delete POST_ID' and a verify step after multi-media uploads.

Consider moving the verbatim flag reference and raw-API/streaming sections into a reference file if the bundle grows, to keep SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and free of concept-overexplaining fluff, but the Quick Reference table and Command Details sections substantially overlap — nearly every command appears in both the table and again as a code block, which could be tightened.	2 / 3
Actionability	Throughout the body, commands are fully executable, copy-paste ready, and include specific flags, IDs, URLs, and example bodies — matching the score-3 anchor for concrete executable guidance.	3 / 3
Workflow Clarity	Multi-step workflows like post-with-media and multi-app setup are clearly sequenced, but destructive operations (e.g. delete) and batch operations lack explicit validation/feedback-loop checkpoints, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	No bundle files exist, but the content is cleanly partitioned into well-labeled, one-level sections (Installation, Prerequisites, Quick Reference, Command Details, Global Flags, etc.) with easy navigation, which meets the bar for well-organized single-document skills.	3 / 3
	Total	10 / 12 Passed

Description

100%

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 is specific, complete, and well-triggered: it states concrete capabilities and gives an explicit 'Use this skill when' clause with natural user vocabulary. It uses third-person voice and presents a distinct niche with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint' — matching the score-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers what ('A CLI tool for making authenticated requests to the X (Twitter) API') and when ('Use this skill when you need to post tweets, reply, quote...') with an explicit Use-when trigger clause.	3 / 3
Trigger Term Quality	Phrases like 'post tweets', 'reply', 'search', 'send DMs', 'upload media' are exactly what a user would naturally say, giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	The X (Twitter) API niche with X-specific actions (tweets, DMs, followers) is distinct and unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: trpc-group/trpc-agent-go
Commit: dfab3c6

Reviewed: 2 days 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.