call-cognite-function

Call a deployed Cognite CDF Function and retrieve its response, with Zod-validated API responses and an optional React Query hook. Use this skill whenever you need to invoke any CDF Function (by numeric function ID or external ID), pass arbitrary input data, and get a typed, validated result back — regardless of what the function does, the function has an outpt, or what shape its input/output takes. Triggers: call cognite function, invoke CDF function, run CDF function, poll CDF function, CDF Functions API, cognite function result, function call nonce.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

71%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 well-structured, lean, and actionable with concrete code and a clear three-step workflow. Its main weakness is progressive disclosure: the two referenced bundle files are not actually present, so the core implementation code is unavailable despite being advertised.

Suggestions

Include the advertised 'code/cogniteFunctionService.ts' and 'code/useCogniteFunction.ts' files in the bundle, or inline their essential contents and stop referencing missing paths.

Make the polling-loop validation checkpoint explicit (e.g., a numbered 'verify status is Completed; if Failed/Timeout, surface the function error and stop' step) rather than leaving it implicit.

Trim the mutation-semantics justification paragraph to the one rule that matters (non-idempotent calls → useMutation, not useQuery).

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence — it does not explain what CDF, Zod, or React Query are in basic terms — but the mutation-semantics paragraph and a few explanatory asides could be trimmed. Not 5 because of those minor over-explanation instances; not 3 because most tokens earn their place.	4 / 5
Actionability	Provides a concrete function signature, documented options, and copy-paste-ready code examples for the schema, hook, and external-id resolution. Not 5 because the primary service implementation lives in referenced 'code/*.ts' files that are not present in the bundle, so the core executable artifact is missing; not 3 because what is inline is concrete and runnable.	4 / 5
Workflow Clarity	The three-step protocol (nonce → invoke → poll/fetch) and the 'How to use' steps are clearly sequenced, with an error-handling section covering Failed/Timeout/polling exhaustion. Not 5 because validation checkpoints in the polling loop are implicit rather than framed as an explicit validate-fix-retry loop; not 3 because sequencing and terminal-state handling are clearly present.	4 / 5
Progressive Disclosure	A Files table signals one-level-deep references to 'code/cogniteFunctionService.ts' and 'code/useCogniteFunction.ts', but those files do not exist in the bundle (no references/, scripts/, assets/, or code/ directories), so the references are broken. Not 4 because the signaled references point at missing files; not 2 because structure and signaling are present even though the targets are absent.	3 / 5
	Total	15 / 20 Passed

Description

95%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 strong: it states concrete capabilities, includes a thorough explicit trigger list, answers both what and when, and occupies a distinctive niche. The only blemish is a typo ('outpt') and minor phrasing redundancy that slightly undercut specificity.

Suggestions

Fix the typo 'outpt' to 'output' in the description.

Tighten the clause 'regardless of what the function does, the function has an outpt, or what shape its input/output takes' — it is redundant and slightly awkward.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — call/retrieve a CDF Function response, Zod-validated API responses, optional React Query hook, pass input data — with minor gaps and a typo ('outpt'). It does not reach 5 because the phrasing is slightly redundant and not as cleanly comprehensive as the top anchor; not 3 because it clearly enumerates multiple specific capabilities beyond naming the domain.	4 / 5
Completeness	Explicitly answers both 'what' (call a deployed CDF Function and retrieve its response with Zod validation and an optional React Query hook) and 'when' ('Use this skill whenever you need to invoke any CDF Function...') with concrete trigger phrases. Not 4 because both halves are concrete and explicit rather than having room for improvement.	5 / 5
Trigger Term Quality	An explicit 'Triggers:' line gives natural phrases a user would actually say ('call cognite function', 'invoke CDF function', 'run CDF function', 'poll CDF function', 'CDF Functions API', 'function call nonce'), with strong synonym coverage. Not 4 because coverage is comprehensive rather than missing only a few terms.	5 / 5
Distinctiveness Conflict Risk	A clear narrow niche — Cognite CDF Functions specifically — with distinct triggers (function ID, nonce, polling) unlikely to collide with other skills. Not 4 because the domain is tightly scoped with minimal overlap risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: cognitedata/builder-skills
Path: skills/call-cognite-function/SKILL.md
Commit: c87160a

Reviewed: 5 days 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.