connect
Connect Claude to any app. Send emails, create issues, post messages, update databases - take real actions across Gmail, Slack, GitHub, Notion, and 1000+ services.
Install with Tessl CLI
npx tessl i github:ComposioHQ/awesome-claude-skills --skill connectOverall
score
73%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
75%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 excels at specificity with concrete actions and well-known service names that serve as natural trigger terms. However, it lacks an explicit 'Use when...' clause which caps completeness, and its broad scope ('1000+ services') creates potential conflict risk with more specialized integration skills.
Suggestions
Add a 'Use when...' clause specifying trigger scenarios, e.g., 'Use when the user wants to automate workflows, integrate services, or take actions in external apps like sending emails or creating tickets.'
Consider narrowing the scope or adding disambiguation guidance to reduce conflict with potential service-specific skills (e.g., 'Use this for cross-service automation; for single-service tasks, prefer dedicated skills if available').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Send emails, create issues, post messages, update databases' - these are clear, actionable capabilities with named services (Gmail, Slack, GitHub, Notion). | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific actions and services, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The when is only implied through the action verbs. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'emails', 'issues', 'messages', 'databases', plus specific service names (Gmail, Slack, GitHub, Notion) that users commonly reference when requesting integrations. | 3 / 3 |
Distinctiveness Conflict Risk | While it names specific services, the broad scope ('1000+ services', 'any app') could overlap with individual service-specific skills. A dedicated Gmail or Slack skill might conflict with this general integration skill. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
65%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides good actionable guidance with executable code and clear examples for connecting Claude to external services. However, it includes unnecessary marketing content that wastes tokens, and the workflow could benefit from explicit validation steps after authentication. The content organization is decent but monolithic.
Suggestions
Remove marketing content (badges, 'Join 20,000+ developers', promotional CTAs) to improve token efficiency
Add explicit validation step after auth flow: 'Verify connection by running: composio list-connections' or similar
Move the extensive framework support table and full app list to separate reference files (FRAMEWORKS.md, INTEGRATIONS.md)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some marketing fluff ('Join 20,000+ developers', badges, promotional CTAs) and the comparison table, while illustrative, adds tokens without teaching Claude anything new about how to use the tool. | 2 / 3 |
Actionability | Provides fully executable code examples with real Python/bash commands, concrete natural language examples for common tasks, and clear installation steps. The code block showing MCP server integration is copy-paste ready. | 3 / 3 |
Workflow Clarity | Setup steps are clear and sequential, but the auth flow lacks explicit validation checkpoints. The troubleshooting section helps but there's no feedback loop for verifying successful connection before proceeding with actions. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but everything is inline in one file. The extensive framework support table and app lists could be split into separate reference files. No external file references for advanced topics. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
Total | 13 / 16 Passed | |
- Reviewed
Table of Contents
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.