CtrlK
BlogDocsLog inGet started
Tessl Logo

integrate-fusion-agent

MUST be used when adding AI, Atlas, an agent, a chat UI, or LLM features to a Flows/Fusion app. Use the Atlas/EOS sidebar via @cognite/app-sdk — not useAtlasChat, vendored atlas-agent, or per-row chat completions. Triggers: atlas, EOS, PAIA, agent chat, chat UI, sendAgentMessage, sendAgentLayoutMode, registerAgentServer, connectToHostApp, useAtlasChat, LLM. In-app chat: integrate-atlas-chat only if the host sidebar cannot work.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 content is highly actionable with executable code, a clearly sequenced workflow, and built-in validation/feedback loops for fragile and destructive operations. It is token-efficient and well-structured, with only minor room to tighten incidental prose.

DimensionReasoningScore

Conciseness

The body is mostly lean with tight code blocks per step, but includes a few explanatory sentences (e.g. the Comlink proxy note) that are justified non-obvious gotchas rather than padding — efficient with minor trims possible.

4 / 5

Actionability

Provides fully executable, copy-paste-ready TypeScript/TSX with concrete commands ('pnpm add @cognite/app-sdk', minimum 0.3.1), real Zod schemas, and complete factory/server wiring covering the common cases.

5 / 5

Workflow Clarity

A clear Step 0–6 sequence with explicit validation checkpoints: catch outside-Fusion rejection, setApi(() => resolvedApi), .catch() on register/unregister, and an approval gate for mutating actions with a hard-cap table for LLM-over-rows.

5 / 5

Progressive Disclosure

A self-contained skill with no bundle files and well-organized '## Step N' section headers; the only external reference is a sibling-skill cross-ref ('use-topbar'), so per the simple-skills note it earns a 5.

5 / 5

Total

19

/

20

Passed

Description

100%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 specific, third-person, and comprehensive — it names the SDK, lists concrete actions, provides a full trigger keyword set, and explicitly covers both what and when. It is a strong example of a focused, low-conflict skill description.

DimensionReasoningScore

Specificity

Names the concrete domain (Flows/Fusion app, Atlas/EOS sidebar via @cognite/app-sdk) and lists multiple specific actions (install, connect to host, open sidebar, send message, agent server) alongside explicit anti-patterns to avoid.

5 / 5

Completeness

'MUST be used when adding AI, Atlas, an agent, a chat UI, or LLM features to a Flows/Fusion app' explicitly states both what the skill does and when Claude should use it, with concrete trigger phrases.

5 / 5

Trigger Term Quality

A dedicated 'Triggers:' clause covers natural terms (atlas, EOS, PAIA, agent chat, chat UI, LLM) alongside exact API identifiers and synonyms (sendAgentMessage, sendAgentLayoutMode, registerAgentServer, connectToHostApp, useAtlasChat).

5 / 5

Distinctiveness Conflict Risk

The niche is tightly scoped to Atlas/EOS sidebar integration in Fusion apps with named distinct triggers and explicit anti-patterns, yielding minimal conflict risk with other skills.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
cognitedata/builder-skills
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.