connect-apps-plugin

Composio Claude Agents SDK - 全局外部应用连接插件

Install with Tessl CLI

npx tessl i github:Lingjie-chen/MT5 --skill connect-apps-plugin

What are skills?

3.33x

Quality

36%

Does it follow best practices?

Impact

100%

3.33x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./.trae/skills/connect-apps-plugin/SKILL.md

SKILL.md

Review

Evals

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is severely lacking in all key areas. It reads as a product name/label rather than a functional description that would help Claude select the appropriate skill. Without concrete actions, natural trigger terms, or explicit usage guidance, Claude would struggle to know when to apply this skill.

Suggestions

Add specific concrete actions the SDK enables (e.g., 'Connect to external APIs, authenticate with third-party services, sync data between applications')

Include a 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when connecting to external apps, integrating third-party services, or when user mentions Slack, Gmail, or other app integrations')

List the specific external applications or categories of applications this skill supports to improve distinctiveness

Dimension	Reasoning	Score
Specificity	The description is extremely vague - '全局外部应用连接插件' (global external application connection plugin) describes no concrete actions. It doesn't specify what the SDK actually does or what operations it enables.	1 / 3
Completeness	Missing both 'what' and 'when' components. There's no explanation of capabilities and no 'Use when...' clause or equivalent trigger guidance.	1 / 3
Trigger Term Quality	Contains only technical jargon ('SDK', 'Composio', 'Claude Agents') with no natural user keywords. Users wouldn't naturally say these terms when needing external app connections.	1 / 3
Distinctiveness Conflict Risk	The specific product name 'Composio Claude Agents SDK' provides some distinctiveness, but the vague '外部应用连接' (external application connection) could overlap with any integration-related skill.	2 / 3
	Total	5 / 12 Passed

Implementation

64%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides solid, actionable code examples for Composio integration with good coverage of use cases. However, it suffers from verbosity with repetitive trading scenario examples and lacks explicit validation workflows for connection management. The content would benefit from splitting detailed examples into separate files and adding verification checkpoints.

Suggestions

Consolidate the 5 trading scenario examples into 1-2 representative examples, moving others to a separate EXAMPLES.md file

Add explicit validation steps after authorization (e.g., 'Verify connection: session.verify_connection(toolkit)' before proceeding)

Remove the application category table or move it to external documentation - Claude can reference Composio docs directly

Add a feedback loop for connection errors: check -> authorize -> verify -> retry pattern with explicit checkpoints

Dimension	Reasoning	Score
Conciseness	The skill contains useful information but is verbose with redundant examples (5 trading scenarios that demonstrate similar patterns) and explanatory tables that could be condensed. The overview section and some explanations add tokens without proportional value.	2 / 3
Actionability	Provides fully executable Python code examples with proper imports, initialization, and async patterns. Code is copy-paste ready with clear variable names and realistic usage scenarios.	3 / 3
Workflow Clarity	Steps are present but validation checkpoints are missing. The authorization flow lacks explicit verification steps, and error handling is shown but not integrated into a clear workflow with feedback loops for connection failures.	2 / 3
Progressive Disclosure	Content is reasonably structured with headers, but the file is monolithic (~200 lines) with inline content that could be split (e.g., trading scenarios, best practices). External doc links exist but internal file references for detailed guides are missing.	2 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Reviewed: 1 day 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.