cue-omni-reader

Parse and understand an HTTP(S) URL or an authorized local document, audio, or video source through Cue Omni Reader when the Agent has the official Omni MCP tools.

Quality

75%

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 ./builtin-skills/skills/cue-omni-reader/SKILL.md

Quality

Content

75%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-organized, dense orchestration guide with a clear numbered workflow, an operation-state table, and concrete error-handling rules. It respects Claude's competence and offloads setup detail to a single well-signaled reference.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, never explaining what a URL, MCP, or parsing is; it is dense rather than padded, with only minor spots that could be tightened.	4 / 5
Actionability	Concrete tool names (parse, get_parse_status, read_result, read_outline, save_result, discard_result) and specific field guidance (result_delivery: artifact/auto, wait: false) give mostly executable orchestration; a few edge cases lack exact invocation detail.	4 / 5
Workflow Clarity	The six-step parse workflow is clearly sequenced with explicit polling/validation checkpoints and error-recovery rules (retry only when retryable, claim deletion only after cleanup confirmed); just short of the explicit gated checklists in the 5-anchor.	4 / 5
Progressive Disclosure	Content is well-sectioned and the single external reference (references/setup.md) is clearly signaled and one level deep; the bulk reference material is appropriately offloaded rather than inlined.	4 / 5
	Total	16 / 20 Passed

Description

66%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 is specific and distinctive, clearly identifying the source types and the underlying tool. Its weakness is the "when" clause, which states a tool-availability precondition rather than concrete user trigger phrases, capping completeness.

Suggestions

Add an explicit "Use when..." clause with user-facing trigger phrases, e.g. "Use when the user shares a URL or asks to analyze a local document, audio, or video file."

Include common synonyms and file extensions (e.g. .pdf, .mp3, .mp4, transcripts) to improve trigger-term coverage.

Lead with the concrete action verbs before the conditional tool clause so the "what" reads first.

Dimension	Reasoning	Score
Specificity	Names multiple concrete source types ("HTTP(S) URL or an authorized local document, audio, or video source") and a specific action ("Parse and understand"), with only minor coverage gaps compared to the comprehensive 5-anchor.	4 / 5
Completeness	The "what" is clear (parse/understand URL or local document/audio/video), but the only "when" clause ("when the Agent has the official Omni MCP tools") is a tool-availability condition, not explicit user-trigger guidance; per the rubric a missing "Use when..." trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms users would say ("URL", "local document", "audio", "video") plus the product name "Cue Omni Reader" and "Omni MCP tools", but misses common synonyms and file extensions that the 5-anchor expects.	4 / 5
Distinctiveness Conflict Risk	The distinctive product name "Cue Omni Reader" and "Omni MCP tools" carve a clear niche with low conflict risk, though the broad source-type list leaves minor overlap with generic reader/parsing 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: iflytek/skillhub
Path: builtin-skills/skills/cue-omni-reader/SKILL.md
Commit: 7352597

Reviewed: 4 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.