opik-external-integrations

Build or update an Opik integration that lives OUTSIDE this repo — a standalone opik-* package (e.g. opik-openclaw, opik-claude-code-plugin) or Opik support contributed into a third-party project (e.g. LiteLLM, Dify). Use ONLY when the user names an external repository or external package as the target; for integrations under sdks/ use the opik-integrations skill instead.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%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.

A well-organized, lean instruction skill with a clear sequenced workflow and an explicit verify-and-loop checkpoint. Its main weakness is that core referenced files (workflow.md, references.md) are absent from the bundle, leaving some actionable detail and navigation unresolved.

Suggestions

Ship the referenced bundle files (workflow.md with the Phase 0 questionnaire, references.md with the curated integration list) so the load-bearing links resolve.

Reduce restating the external-vs-internal boundary across the intro, activation gate, and principles; consolidate it once.

Inline the questionnaire essentials and a minimal references list in SKILL.md so the skill remains usable even before the bundle files are opened.

Dimension	Reasoning	Score
Conciseness	The ~45-line body is lean and assumes Claude's competence with tight bullets and no padding of known concepts, but the external-vs-internal boundary and published-SDK point are restated across the intro, activation gate, and principles sections, so it is 4 rather than 5.	4 / 5
Actionability	As an instruction skill it gives concrete direction (read CONTRIBUTING/AGENTS.md, mirror the closest sibling, choose between @opik.track/track_*/low-level client/REST, verify via the Opik MCP) and names specific helper skills, but load-bearing specifics are deferred to workflow.md/references.md, leaving minor gaps.	4 / 5
Workflow Clarity	The 0–8 step workflow is clearly sequenced and includes an explicit validation checkpoint with a feedback loop ("Verify via the Opik MCP … read the trace/spans back. Loop until correct."), satisfying the anchor for clear sequence plus explicit validation and error-recovery looping.	5 / 5
Progressive Disclosure	The body is a well-structured overview with clearly signaled one-level-deep references (workflow.md, references.md, sibling skill docs), but those referenced files are not present in the bundle, so navigation points at missing material — a gap beyond the minor organization issues of a 5.	4 / 5
	Total	17 / 20 Passed

Description

87%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.

A strong description that is concrete, gives explicit use-only-when trigger guidance, and cleanly disambiguates itself from the internal opik-integrations skill. Minor room to broaden action coverage and natural-term synonyms.

Dimension	Reasoning	Score
Specificity	Concrete actions are named ("Build or update an Opik integration") with two specific shapes ("standalone opik-* package", "Opik support contributed into a third-party project") and concrete examples (opik-openclaw, LiteLLM, Dify), but the action list is essentially build/update plus two shapes rather than a broad set, so it sits at 4 not 5.	4 / 5
Completeness	It explicitly answers both what ("Build or update an Opik integration that lives OUTSIDE this repo") and when with a concrete trigger phrase ("Use ONLY when the user names an external repository or external package as the target"), plus a negative route to the sibling skill.	5 / 5
Trigger Term Quality	Natural keywords a user would name are present ("external repository", "external package", "LiteLLM", "Dify", "opik-* package"), giving good coverage; it is not a 5 because it lacks synonym/variation breadth and leans on domain jargon.	4 / 5
Distinctiveness Conflict Risk	It carves a clear external-vs-internal niche and explicitly routes the overlapping case away ("for integrations under sdks/ use the opik-integrations skill instead"), giving minimal conflict risk with the sibling skill.	5 / 5
	Total	18 / 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
relative_links	Relative link issues: 3 missing, 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: comet-ml/opik
Path: .agents/skills/opik-external-integrations/SKILL.md
Commit: 50de943

Reviewed: 2 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.