xurl

X/Twitter via xurl CLI: raw post search, posting, DM, media.

Quality

73%

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/social-media/xurl/SKILL.md

Quality

Content

77%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.

Highly actionable, executable content with a well-validated agent workflow, but it is a single monolithic file that duplicates commands across three sections. Splitting the command reference and troubleshooting into reference files and de-duplicating would improve both conciseness and progressive disclosure.

Suggestions

Move 'Command Details', 'Troubleshooting', and the Docker/setup detail into references/ files (e.g. COMMANDS.md, TROUBLESHOOTING.md) and link them from the Quick Reference, keeping SKILL.md as an overview.

De-duplicate: the Quick Reference table, Command Details code blocks, and Common Workflows repeat the same commands (media upload, reply, search) — keep one canonical form per action.

Trim the Hermes/Docker HOME pitfall block into a short pointer plus one example command; the current four-command block largely repeats the setup steps above it.

Dimension	Reasoning	Score
Conciseness	The body is command-dense with almost no concept explanation Claude already knows, but the same commands appear three times — the Quick Reference table, 'Command Details' code blocks, and again in 'Common Workflows' (e.g. media upload + post appears at lines 273-275, 349-351, and in the table at line 153). That matches 'mostly efficient but... could be tightened' rather than the minor-trim level of 4.	3 / 5
Actionability	Every command is copy-paste executable with real arguments, flags, and expected outputs (e.g. the full media upload workflow, raw API examples with -X/-d/-H flags, and the troubleshooting table mapping symptoms to exact fixes). Matches the anchor 'fully executable; copy-paste ready... specific examples cover the common cases'.	5 / 5
Workflow Clarity	The 'Agent Workflow' section gives a 9-step sequence with explicit validation checkpoints — verify prerequisites ('xurl --help', 'xurl auth status'), a cheap read to confirm reachability, confirm intent before any write, and step 7's rule that only command output proves a write happened — plus the troubleshooting table as an error-recovery feedback loop. The destructive-operation cap of 3 does not apply because validation steps are present.	5 / 5
Progressive Disclosure	Section headers and the quick-reference table give real structure, but the file is a ~420-line monolith with no bundle files at all: the full command reference, troubleshooting matrix, and setup guide are all inlined in SKILL.md where they belong in separate references/. Matches 'some structure but could be better organized; content that should be separate is inline'.	3 / 5
	Total	16 / 20 Passed

Description

70%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 compact, distinctive description with concrete named actions, but it omits any 'when to use' guidance and misses several natural trigger terms. Adding a use-when clause and synonyms like 'tweet' or 'timeline' would lift it substantially.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user wants to tweet, search X, reply, DM, or manage followers via the X API.'

Add natural synonyms users actually say — 'tweet', 'reply', 'retweet/repost', 'timeline', 'mentions' — to the keyword set.

Mention the raw X API v2 endpoint access and account/graph actions so the capability list is comprehensive, not just the top four.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — "raw post search, posting, DM, media" — tied to a named tool (xurl CLI), matching the anchor 'lists several specific actions; minor gaps in coverage'. It falls short of 5 because notable capabilities from the body (liking, following, timelines, raw v2 endpoint access) are absent, and 'media' alone is less concrete than the others.	4 / 5
Completeness	The 'what' is clear (X/Twitter operations via xurl CLI), but there is no 'Use when...' clause or any equivalent explicit trigger guidance — the judging guidelines explicitly cap completeness at 3 in that case. It is not 2 because the 'what' half is concrete and multi-action, not vague.	3 / 5
Trigger Term Quality	"X/Twitter", "post search", "posting", "DM", "media" give good natural keyword coverage a user would say. It is not 5 because common synonyms and variations users actually say — 'tweet', 'reply', 'timeline', 'followers' — are missing.	4 / 5
Distinctiveness Conflict Risk	"X/Twitter via xurl CLI" carves out a clear niche with distinct triggers (platform name plus specific tool); no realistic overlap with unrelated skills. Matches the anchor 'clear niche with distinct triggers; minimal conflict risk'.	5 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/social-media/xurl/SKILL.md
Commit: 68fa7e9

Reviewed: 3 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.