rich-messaging

富媒体消息发送：语音、图片、卡片、清单、代码 diff、交互选择。 Use when: 发语音、发图、发卡片、展示结构化信息、长结构化汇报、想发一堆文字/日志/步骤、庆祝、给我听听、给我看看、让用户选、确认操作。 Not for: 纯文字聊天、技术讨论、日常回复。 Output: rich block 附着在消息上。

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%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.

A well-structured, actionable skill body: executable examples for every block kind, clear first-use and send sequencing, and progressive disclosure via a single shared reference. Minor conciseness and validation-step explicitness keep it just short of perfect.

Suggestions

Tighten conversational asides (e.g. 不只是打字！、猫猫朋友看不懂上下文) into neutral operational language to save tokens.

Make validation checkpoints explicit in the send workflow — e.g. a numbered 'before sending' checklist rather than relying on the 三条纪律 prose.

Consider moving the long common-errors table into the shared reference to keep SKILL.md focused on decisions, retaining only the top 2-3 pitfalls inline.

Dimension	Reasoning	Score
Conciseness	Mostly lean and operational, but some conversational color (不只是打字！、猫猫朋友看不懂上下文) and slightly padded error-table prose could be trimmed without losing meaning.	4 / 5
Actionability	Copy-paste-ready JSON examples for all eight block kinds plus named MCP tools (cat_cafe_create_rich_block, get_rich_block_rules, publishGeneratedImage) and exact fields cover the common cases fully.	5 / 5
Workflow Clarity	Clear sequence exists (call get_rich_block_rules first → write 1-2 sentence summary → create block) with checkpoints like the podcast-timeout rule, but a few validation steps are implicit rather than enumerated.	4 / 5
Progressive Disclosure	Overview-style SKILL.md with minimal inline examples and a single clearly signaled one-level reference (../.cat-cafe-shared-refs/rich-blocks.md) plus the live get_rich_block_rules tool for full specs.	5 / 5
	Total	18 / 20 Passed

Description

100%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 high-quality description: concrete capabilities, natural trigger phrases, explicit use/not-for/output structure, and a clear niche that avoids conflicts. Voice is third-person throughout, so no specificity penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 语音、图片、卡片、清单、代码 diff、交互选择 — covering the full range of rich block types comprehensively rather than vague abstractions.	5 / 5
Completeness	Explicitly answers what (富媒体消息发送 + enumerated types), when (Use when: …), what not (Not for), and output (rich block 附着在消息上) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Use-when clause is packed with natural phrases users actually say (发语音、发图、给我听听、给我看看、让用户选、确认操作) including synonyms and informal variants.	5 / 5
Distinctiveness Conflict Risk	Clear niche (rich media blocks) with an explicit Not-for boundary (纯文字聊天、技术讨论、日常回复) that minimizes overlap with plain-chat skills.	5 / 5
	Total	20 / 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: zts212653/clowder-ai
Path: cat-cafe-skills/rich-messaging/SKILL.md
Commit: 090626a

Reviewed: ~23 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.