config-evals

Builds and maintains configuration-based evaluations on a workflow with the eval-config tool. Use when the user asks to set up, add, view, change, or remove an evaluation, score, grade, or judge a workflow's output, or measure answer quality against a test dataset. This is the only eval form Instance AI handles — it does not touch on-canvas evaluation nodes.

Quality

93%

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

86%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 body is a dense, actionable guide with concrete tool-call signatures, required fields, and worked expression examples, plus a clear sequenced procedure and a single well-signaled reference. Its main weakness is minor redundancy around the leading-`=` rule and the start-node guard, and the absence of an explicit error-recovery feedback loop.

Suggestions

Consolidate the leading-`=` guidance into one place — either the Metrics section or the dedicated subsection — to remove the restated explanation and tighten token use.

Add a short validate→fix→retry loop for the case where an eval run fails to compile (e.g., start node lacks an incoming connection), so the workflow has an explicit recovery checkpoint.

De-duplicate the "never use the trigger as startNodeName" rule so it is stated authoritatively once in step 2 rather than echoed in step 1's bullet.

Dimension	Reasoning	Score
Conciseness	Mostly lean and efficient — it assumes Claude knows n8n/Data Table concepts and skips padding — but the leading-`=` gotcha is restated across the Metrics section and a dedicated subsection, and the "never a trigger" rule is echoed between step 1 and step 2.	4 / 5
Actionability	Provides concrete, copy-paste-ready guidance: exact tool-action signatures (eval-config(action="create"), data-tables(action="list")), expression syntax (={{ $json.output }}), required fields, and correct/wrong examples for the `=` gotcha.	5 / 5
Workflow Clarity	A clear 6-step Default Procedure with real checkpoints (respect the approval-card result, never invent a dataTableId, resolve the dataset first), but it lacks an explicit validate→fix→retry loop for the start-node compile-failure case.	4 / 5
Progressive Disclosure	Well-organized sections with a single clearly-signaled one-level-deep reference to references/config-eval-playbook.md (verified to exist and match its claimed contents), with bulk detail offloaded there.	5 / 5
	Total	18 / 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 concise, concrete, and trigger-rich, clearly stating both what the skill does and when to invoke it while drawing a sharp boundary against on-canvas evaluation nodes. It uses third-person voice and avoids fluff.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions ("set up, add, view, change, or remove an evaluation, score, grade, or judge... measure answer quality") — comprehensive coverage rather than just several with minor gaps.	5 / 5
Completeness	Explicitly answers both what ("Builds and maintains configuration-based evaluations... with the eval-config tool") and when ("Use when the user asks to set up, add, view, change...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers the natural phrases users say with synonyms ("set up an evaluation", "score", "grade", "judge", "measure answer quality against a test dataset"), matching the comprehensive-synonyms anchor.	5 / 5
Distinctiveness Conflict Risk	Clear niche with an explicit disambiguating boundary ("the only eval form Instance AI handles — it does not touch on-canvas evaluation nodes"), minimizing conflict with adjacent skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: n8n-io/n8n
Path: packages/@n8n/instance-ai/skills/config-evals/SKILL.md
Commit: 7700b76

Reviewed: ~1 hour 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.