CtrlK
BlogDocsLog inGet started
Tessl Logo

create-client-tool

MUST be used whenever creating an AtlasTool (client-side tool) for an Atlas agent. Do NOT manually write AtlasTool definitions or wire them into useAtlasChat — this skill handles the TypeBox schema, execute function, and hook wiring. Prerequisite: integrate-atlas-chat (vendored src/atlas-agent + TypeBox/AJV deps). This includes tools that fetch data, render UI, call APIs, show charts, query local state, or perform any browser-side action. Triggers: AtlasTool, client tool, add tool, create tool, new tool, tool definition, agent tool.

71

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

A concise, highly actionable single-file skill with clean organization; its only gap is the absence of an explicit verification step in the workflow.

Suggestions

Add a validation checkpoint between wiring and Done (e.g., "Run `tsc --noEmit` and confirm the tool appears in the agent's available tools") to lift workflow_clarity to 3.

Optional: factor the TypeBox quick-reference table into a REFERENCES file if the skill grows, keeping SKILL.md an overview.

DimensionReasoningScore

Conciseness

Lean body with executable snippets and a compact TypeBox reference table; the Background section explains the custom Atlas framework flow (which Claude does not already know), so it is not penalized for explaining familiar concepts, fitting the level-3 anchor.

3 / 3

Actionability

Provides fully typed, copy-paste-ready AtlasTool code, a wiring snippet, and a render snippet with notes on path adjustment, matching the level-3 anchor for executable, specific examples.

3 / 3

Workflow Clarity

Steps 1-4 are clearly sequenced (understand → define → wire → render), but there is no explicit validation/verification checkpoint (e.g., type-check or confirming the agent can invoke the tool), so it sits at level 2 (sequence present, checkpoints implicit) rather than the level-3 anchor requiring explicit validation steps.

2 / 3

Progressive Disclosure

No bundle files exist and the skill is a self-contained, well-sectioned single document with no nested references; the content is appropriately organized and easy to navigate, satisfying the level-3 anchor for a skill with no need for external references.

3 / 3

Total

11

/

12

Passed

Description

90%

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

A strong, specific description with explicit trigger guidance and a clear niche, weakened only by its imperative/second-person voice rather than third-person declarative style.

Suggestions

Rewrite directives in third person (e.g., "Creates an AtlasTool... this skill handles the TypeBox schema" instead of "Do NOT manually write...") to match the rubric's preferred voice and recover the specificity score.

Lead with the concrete capabilities (what the tool scaffolds) before the prerequisite/anti-instructions, so the description opens declaratively.

DimensionReasoningScore

Specificity

Names multiple concrete actions ("handles the TypeBox schema, execute function, and hook wiring"; "fetch data, render UI, call APIs, show charts"), which reaches the level-3 bar, but the description leans on second-person imperatives ("Do NOT manually write AtlasTool definitions or wire them into useAtlasChat") rather than third-person declarative voice, triggering the rubric's -1 voice penalty.

2 / 3

Completeness

Clearly answers what ("handles the TypeBox schema, execute function, and hook wiring") and when ("MUST be used whenever creating an AtlasTool"; explicit "Triggers:" clause), satisfying the level-3 anchor for both what and when with explicit triggers.

3 / 3

Trigger Term Quality

Explicit "Triggers:" list gives good coverage of natural phrasings a user would say ("add tool", "create tool", "new tool", "client tool", "agent tool"), matching the level-3 anchor for natural-term coverage.

3 / 3

Distinctiveness Conflict Risk

Tied to a specific niche (Atlas agent, AtlasTool, integrate-atlas-chat prerequisite) with distinct triggers, making it unlikely to fire for an unrelated skill per the level-3 anchor.

3 / 3

Total

11

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

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

Warning

metadata_version

'metadata.version' is missing

Warning

Total

14

/

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.