integrate-atlas-chat

MUST be used whenever building a chat UI with Atlas agents in a Flows app. Do NOT manually write useAtlasChat integration code — this skill handles installation, component structure, and hook wiring. Triggers: useAtlasChat, atlas chat, streaming chat, agent chat, chat interface, chat component, chat UI. For a full chat app, run skills in order: (1) integrate-atlas-chat, (2) create-client-tool (per tool), (3) setup-python-tools (if Python tools needed).

Quality

88%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Critical

Do not install without reviewing

Quality

Discovery

100%

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 is an excellent skill description that clearly defines its scope, provides explicit trigger terms, and distinguishes itself from related skills. It answers both 'what' and 'when' comprehensively, includes workflow ordering context with related skills, and uses strong directive language ('MUST be used', 'Do NOT manually write') to ensure proper selection. The description is concise yet thorough.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'handles installation, component structure, and hook wiring' for building chat UIs with Atlas agents. Also specifies the workflow ordering with other skills, which adds specificity.	3 / 3
Completeness	Clearly answers 'what' (handles installation, component structure, and hook wiring for Atlas agent chat UIs in Flows apps) and 'when' (whenever building a chat UI with Atlas agents, with explicit trigger terms listed). The 'MUST be used whenever' and 'Triggers:' clauses serve as explicit trigger guidance.	3 / 3
Trigger Term Quality	Explicitly lists natural trigger terms: 'useAtlasChat, atlas chat, streaming chat, agent chat, chat interface, chat component, chat UI'. These cover a wide range of terms a user would naturally use when requesting this functionality.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche: Atlas agent chat integration in Flows apps. The specific technology stack (Atlas, useAtlasChat, Flows) and the explicit 'Do NOT manually write' instruction make it very unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

77%

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

This is a well-structured, highly actionable skill with clear sequential workflow and concrete code examples. Its main weakness is moderate verbosity in Step 4 where the component specification could be more concise or split into a reference file. The skill effectively balances completeness with clarity and provides copy-paste ready commands throughout.

Suggestions

Consider moving the detailed hook API reference and tool call display patterns into a separate REFERENCE.md file, keeping Step 4 focused on the high-level component requirements.

Tighten the dependency installation section — the three package-manager variants could be collapsed into a single line with a note like 'Install with your package manager: @sinclair/typebox@^0.33.0 ajv@^8.17.1 ajv-formats@^2.1.1'.

Dimension	Reasoning	Score
Conciseness	Generally efficient but includes some unnecessary explanation (e.g., the Python tools optional section is somewhat verbose, and the dependency table + per-package-manager commands could be tighter). The hook API documentation is well-structured but the tool call display pattern section adds moderate bulk.	2 / 3
Actionability	Provides fully concrete, executable guidance: exact npm package versions, exact import paths, executable TypeScript/TSX code snippets, specific file paths to copy, and precise hook API with property descriptions. The commands are copy-paste ready for all three package managers.	3 / 3
Workflow Clarity	Clear 5-step sequential workflow with explicit ordering ('Complete these steps in order'), a read-before-modify checkpoint in Step 1, and logical progression from understanding → copying files → installing deps → building component → optional enhancement. The instruction to 'Read each file before modifying it' serves as a validation checkpoint.	3 / 3
Progressive Disclosure	References external skills (setup-python-tools, create-client-tool) and code files appropriately, but the Step 4 component specification is quite long and inline. The hook API reference and tool call display pattern could potentially be in a separate reference file. However, no bundle files were provided to verify the referenced code/ directory structure.	2 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	9 / 11 Passed

Repository: cognitedata/builder-skills
Commit: d6af887

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.