im-channels

Use when connecting or configuring IM channel bots (WeChat, WeCom, DingTalk, Lark), or when you receive a user message that contains an <im> block indicating it was sent from an IM channel — read this skill to understand what the context means and how to handle it correctly.

Quality

83%

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

Quality

Content

78%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 well-organized and token-efficient, with concrete examples and a clear connection workflow. Its main weakness is progressive disclosure: the four referenced reference/*.md files are signaled but not actually present in the bundle, leaving the detailed connect steps unresolvable.

Suggestions

Ship the referenced reference/wechat.md, reference/wecom.md, reference/dingtalk.md, and reference/lark.md files so the signaled navigation actually resolves.

Add an explicit validate/retry checkpoint in the connect workflow (e.g., confirm the channel reports connected before reporting success; on failure, re-prompt for corrected credentials).

Inline the minimal run_sdk_snippet call shape for Step 3 (or show one concrete example) so the connect step is executable without opening a reference file.

Dimension	Reasoning	Score
Conciseness	The body is lean: it defines <im> block fields, gives response rules, and a copy-paste status snippet without explaining what IM platforms are or padding with concepts Claude already knows; every section earns its tokens.	5 / 5
Actionability	Provides concrete <im> block examples, field semantics, exact file paths to read, and an executable status-check snippet, but the connect step ('Run the run_sdk_snippet code') defers specifics without showing the code, leaving a minor gap.	4 / 5
Workflow Clarity	Scenario B is a clearly sequenced 4-step process with a status check and a light success/failure feedback loop in Step 4, but it lacks an explicit validate-then-retry checkpoint for the credential/connection operation.	4 / 5
Progressive Disclosure	Structure is clean with clearly signaled one-level-deep markdown links to reference/wechat.md and siblings, but those referenced files are absent from the bundle, so the navigation is broken — content that should be separate is referenced to files that do not exist.	3 / 5
	Total	16 / 20 Passed

Description

87%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 strong: it pairs an explicit 'Use when...' trigger (covering both the connection setup and the inbound <im> block cases) with a clear statement of what the skill provides, scoped to four named IM platforms. It is specific, complete, and highly distinct from other skills.

Dimension	Reasoning	Score
Specificity	Names the IM domain and four specific platforms plus concrete actions ('connecting or configuring IM channel bots', 'understand what the context means and how to handle it correctly'), with only minor coverage gaps versus the comprehensive multi-action anchor at 5.	4 / 5
Completeness	Explicitly answers both 'what' (read this skill to understand context and handle it correctly) and 'when' (Use when connecting/configuring bots, or when a user message contains an <im> block) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('connecting or configuring IM channel bots', platform names, 'receive a user message that contains an <im> block') with good coverage, though it lacks the breadth of synonyms/extensions that would mark the 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — IM channel bots across four named platforms plus the distinctive <im> block trigger — with minimal overlap risk against other skills.	5 / 5
	Total	18 / 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
relative_links	Relative link issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: dtyq/magic
Path: backend/super-magic/agents/skills/im-channels/SKILL.md
Commit: f9973c5

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.