metric-pack-designer

Design custom metric packs for plugin-eval so teams can add local evaluation rubrics that emit schema-compatible checks and metrics. Use when the user wants their own evaluation criteria or visualizations.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/plugin-eval/skills/metric-pack-designer/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

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

A concise, well-structured skill body that is held back by a lack of executable manifest/script examples, a missing validation step, and a reference path that does not resolve within the bundle.

Suggestions

Add a minimal copy-pasteable metric-pack manifest example and a script skeleton that prints checks[]/metrics[] JSON to stdout.

Insert an explicit validation checkpoint after the analyze step (e.g. verify emitted JSON parses and matches the schema before relying on results).

Fix or remove the '../../references/metric-pack-manifest.md' reference — either provide the file inside the bundle or inline the manifest schema so the reference resolves.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized with no padding or explanation of concepts Claude already knows; every section earns its place.	3 / 3
Actionability	It gives one concrete command ('plugin-eval analyze <path> --metric-pack <manifest.json>') but provides no executable example of the manifest structure or the stdout-printing script, leaving key details to an external reference.	2 / 3
Workflow Clarity	A clear 4-step sequence exists, but there is no validation/verification checkpoint (e.g. confirming the emitted JSON is schema-compatible), which caps workflow clarity at 2 for a batch-style operation.	2 / 3
Progressive Disclosure	Sections are cleanly organized, but the single reference path '../../references/metric-pack-manifest.md' escapes the bundle to a non-existent file, so the reference is present but not validly signaled or navigable.	2 / 3
	Total	9 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 'Use when' guidance and a clear niche. It is held back only by jargon-heavy trigger phrasing that could use more natural user-facing keywords.

Suggestions

Add more natural trigger phrasing (e.g. 'custom rubric', 'add my own eval criteria') alongside 'evaluation criteria' so users' common phrasings match.

Consider softening jargon like 'schema-compatible' in the description itself, leaving that detail for the body.

Dimension	Reasoning	Score
Specificity	Names concrete actions and outputs — 'Design custom metric packs', 'emit schema-compatible checks and metrics' — rather than vague language, matching the multiple-specific-actions anchor.	3 / 3
Completeness	It answers both what (design metric packs that emit checks/metrics) and when, with an explicit 'Use when the user wants their own evaluation criteria or visualizations' clause.	3 / 3
Trigger Term Quality	The trigger 'evaluation criteria or visualizations' is reasonably natural, but the description leans on jargon ('metric packs', 'plugin-eval', 'schema-compatible') and misses common variations a user might say, so it stops short of the good-coverage anchor.	2 / 3
Distinctiveness Conflict Risk	The niche plugin-eval metric-pack domain with 'local evaluation rubrics' triggers is clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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: openai/plugins
Path: plugins/plugin-eval/skills/metric-pack-designer/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.