integrations

External data sources, connectors, and custom data streams

Quality

28%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./src/skills/bundled/integrations/SKILL.md

Quality

Content

57%

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

The skill provides highly actionable, executable code examples covering a wide range of integration types, which is its primary strength. However, it suffers from being a monolithic reference document that tries to cover everything in one file — chat commands, full API reference, data tables, bot integration examples, and best practices — without progressive disclosure or cross-file navigation. The workflow for setting up and validating new integrations lacks explicit sequencing and error recovery steps.

Suggestions

Split the content into a concise SKILL.md overview with quick-start examples, linking to separate files like CHAT_COMMANDS.md, API_REFERENCE.md, and BUILT_IN_SOURCES.md for detailed reference.

Add an explicit end-to-end workflow for adding a new custom source: create → configure → test → validate → subscribe, with checkpoints and error handling at each step.

Remove the generic best practices section (validate data, handle errors gracefully, etc.) — Claude already knows these principles.

Add a troubleshooting or error recovery section showing what to do when integrations.test() fails or a WebSocket disconnects, rather than just listing reconnect config options.

Dimension	Reasoning	Score
Conciseness	The content is fairly comprehensive but includes some redundancy (e.g., the chat commands section and TypeScript API cover overlapping functionality). The best practices section is generic advice Claude already knows. The file is quite long for what could be a more focused reference.	2 / 3
Actionability	The skill provides fully executable TypeScript code examples for every integration type (webhook, REST, WebSocket), complete with configuration objects, transform functions, and subscription patterns. Chat commands are concrete and copy-paste ready.	3 / 3
Workflow Clarity	While individual API calls are clear, there's no explicit workflow for setting up a new integration end-to-end with validation checkpoints. The 'test <source-id>' command exists but isn't woven into a recommended setup sequence. No error recovery feedback loops are documented for when sources fail.	2 / 3
Progressive Disclosure	This is a monolithic wall of content — a complete API reference inlined into a single file with no references to external files. The chat commands, TypeScript API, built-in sources table, custom source types, bot integration examples, env vars, and best practices could be split across focused documents with a concise overview here.	1 / 3
	Total	8 / 12 Passed

Description

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 critically underspecified. It reads as a category label rather than a functional skill description, listing only vague nouns without any concrete actions, trigger terms, or usage guidance. It would be nearly impossible for Claude to reliably select this skill over others in a multi-skill environment.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Connects to external APIs, queries databases, imports CSV/JSON data feeds, and configures webhook integrations.'

Include an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about connecting to an API, importing external data, setting up a database connection, or configuring data pipelines.'

Narrow the scope to reduce conflict risk by specifying which types of data sources or connectors are supported (e.g., REST APIs, SQL databases, S3 buckets) rather than using catch-all terms.

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language ('external data sources', 'connectors', 'custom data streams') without listing any concrete actions. There are no verbs describing what the skill actually does.	1 / 3
Completeness	The description barely addresses 'what' (only vague nouns, no actions) and completely lacks any 'when' guidance. There is no 'Use when...' clause or equivalent trigger guidance.	1 / 3
Trigger Term Quality	The terms 'external data sources', 'connectors', and 'custom data streams' are technical jargon that users are unlikely to naturally say. Common user terms like 'API', 'database', 'import data', 'fetch', or specific connector names are absent.	1 / 3
Distinctiveness Conflict Risk	The description is extremely generic and could overlap with virtually any skill involving data retrieval, APIs, databases, ETL, or integrations. 'External data sources' and 'connectors' are too broad to carve out a clear niche.	1 / 3
	Total	4 / 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

Repository: alsk1992/CloddsBot
Path: src/skills/bundled/integrations/SKILL.md
Commit: e71a5f6

Reviewed: about 13 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.