dingtalk-message

钉钉消息发送技能。支持企业内部机器人（批量单聊/群聊）和 Webhook 自定义机器人两种接入方式，支持多机器人管理，支持文本、Markdown、链接、ActionCard、FeedCard等多种消息类型。

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/dingtalk-message/SKILL.md

Quality

Content

76%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 highly actionable, well-structured reference with executable commands for every feature and useful domain constraints (DingTalk Markdown subset, rate limits, error codes). Its weaknesses are the missing validation/feedback loop around batch sends and mild duplication of setup examples.

Suggestions

Add an explicit post-send validation step (e.g. check the command's success output or send a test message to confirm delivery before batch-sending to up to 100 users) to close the workflow checkpoint gap.

De-duplicate the robot-add examples and config --show verification that appear in both "首次配置" and "机器人管理", keeping one canonical location.

Move the error-code catalog and full command reference into a references/ file (e.g. references/errors.md) with a clear pointer from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is almost pure executable commands with inline comments and explains nothing Claude already knows (no 'what is DingTalk' or 'what is a webhook' padding). Minor trimmable redundancy exists: the robot-add examples appear in both "首次配置" and "机器人管理", and the config --show verification is shown twice, matching 'efficient; minor instances that could be trimmed' rather than the fully-lean anchor 5.	4 / 5
Actionability	Every message type (text, markdown, link, action-card, feed-card, file), both access methods, robot management, and signing are documented with copy-paste-ready, fully executable commands verified against the bundled scripts/dingtalk.py (e.g. --conversation-id, --at-mobiles, feed-card subcommand all exist in the script). CLI syntax rules and DingTalk Markdown limitations add the details needed for success.	5 / 5
Workflow Clarity	The first-time setup flow is well sequenced (ask for credentials -> robot-add -> 验证配置), but the send workflows themselves have no validation checkpoint — no post-send success check or verify-before-batch step for the documented batch sends ("批量单聊", "单次最多发送100个用户"). Per the guideline that batch operations without validation cap workflow clarity at 3, this sits at 'sequence present but checkpoints missing', not the 'most checkpoints present' anchor 4.	3 / 5
Progressive Disclosure	The bundle is a single real script (scripts/dingtalk.py, verified) with all guidance in one well-sectioned SKILL.md and clear headers (Webhook vs 企业内部机器人 vs management). It is not a 5 because reference-like material (error-code catalog, full command reference) is inlined rather than split into clearly signaled reference files, though structure remains good and navigation easy.	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.

A capability-rich description that clearly states what the skill does with concrete, specific actions and distinct DingTalk terminology. Its main weakness is the complete absence of a 'Use when...' trigger clause, which caps completeness and weakens discoverability.

Suggestions

Add an explicit trigger clause, e.g. "当用户要求发送钉钉消息、钉钉群通知、机器人推送或提及 DingTalk 时使用".

Include common user phrasings and synonyms in the description, such as "钉钉机器人", "发通知/告警到群", and the English name "DingTalk".

Mention remaining capabilities such as file sending to close the coverage gap and reach full specificity.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete capabilities: "支持企业内部机器人（批量单聊/群聊）和 Webhook 自定义机器人两种接入方式", "支持多机器人管理", and a full list of message types ("文本、Markdown、链接、ActionCard、FeedCard"). It lists several specific actions with minor gaps (e.g., file sending is not mentioned), matching the 'several specific actions; minor gaps' anchor rather than the comprehensive anchor 5.	4 / 5
Completeness	The 'what' is clearly answered (two access methods, multi-robot management, multiple message types), but there is no 'Use when...' or equivalent trigger clause, so 'when' is entirely missing. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms users would say are present: "钉钉消息发送", "群聊", "单聊", "Webhook 自定义机器人", "Markdown". However common variations like "钉钉机器人", "发通知/告警", or the English "DingTalk" are missing, matching 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonyms anchor 5.	4 / 5
Distinctiveness Conflict Risk	The DingTalk (钉钉) messaging niche is distinct with specific terminology (Webhook, ActionCard, FeedCard), making wrong-skill triggers unlikely. It is not a 5 because without any 'when' guidance it could overlap with other DingTalk-adjacent skills (e.g., DingTalk calendar, contacts, or notification tools).	4 / 5
	Total	15 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: agentscope-ai/ReMe
Path: skills/dingtalk-message/SKILL.md
Commit: dc12798

Reviewed: 10 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.