mgnify-skill

Submit compact MGnify API requests for microbiome studies, samples, and biome metadata. Use when a user wants concise MGnify summaries

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/life-science-research/skills/mgnify-skill/SKILL.md

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 content is a lean, executable single-purpose skill with a runnable example, exact endpoints, and a well-organized, shallow structure that appropriately references one bundled script. Minor gains are available from de-duplicating the example and adding an explicit response-validation step.

Suggestions

Remove the duplicated studies example (it appears in both Input common patterns and the Execution block) to tighten conciseness.

Add an explicit validation checkpoint in the workflow, e.g. 'Check `ok` and `warnings` before summarizing; surface `error.code`/`error.message` on failure' to push workflow clarity higher.

Optionally show a second executable example for the `samples` path to round out coverage of the three preferred paths.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes competence—rules, fields, and output shape are stated without explaining what MGnify or JSON:API is; minor redundancy (the studies example is repeated in Input common patterns and the Execution block) keeps it just below lean; not a 3 because padding is minimal and not a 5 because of the duplicated example.	4 / 5
Actionability	Provides a concrete script path, exact base_url, full field list, and a copy-paste-ready bash one-liner with a complete JSON payload, covering the common studies/biomes cases; matches the 'fully executable, copy-paste ready, covers common cases' anchor and is not a 4 because the example is complete and runnable.	5 / 5
Workflow Clarity	For this single-purpose request skill the operating rules and Execution section give a clear sequence and the Output section distinguishes success/failure, but there is no explicit validation checkpoint (e.g. 'check ok and warnings before summarizing'); fits 'clear sequence with most checkpoints, minor gaps' rather than 5, and is above 3 because the single action is unambiguous.	4 / 5
Progressive Disclosure	The body is well under 50 lines, cleanly sectioned (Operating rules, Execution behavior, Input, Output, Execution, References), and points to the single bundled script with no nested references; per the simple-skill guideline this earns a 5 on organization alone and is not a 4 because structure and navigation are clean.	5 / 5
	Total	18 / 20 Passed

Description

73%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, third-person, and clearly states a specific niche (MGnify microbiome API) with both a what and a when clause. Trigger coverage is solid though it lacks synonyms and accessions, keeping it just short of top marks.

Suggestions

Broaden trigger terms to include natural synonyms a user might say, e.g. 'MGnify accessions', 'metagenomics', 'study/sample metadata', or '.fastq analyses'.

Add one or two more concrete capabilities (e.g. 'fetch analyses, runs, or pipeline parameters') to lift specificity from one action to several.

Make the 'Use when' clause more concrete, e.g. 'Use when a user wants concise MGnify summaries for studies, samples, biomes, or analyses.'

Dimension	Reasoning	Score
Specificity	Names the MGnify domain and one concrete action ('Submit compact MGnify API requests' for studies, samples, biome metadata), but does not enumerate multiple distinct actions, matching the '1-2 concrete actions, not comprehensive' anchor; not a 4 because it lacks several specific operations and not a 2 because the action is concrete rather than minimal.	3 / 5
Completeness	Explicitly answers both what ('Submit compact MGnify API requests for microbiome studies, samples, and biome metadata') and when ('Use when a user wants concise MGnify summaries'), fitting the 'both what and when; when could be more explicit' anchor; not a 5 because the trigger clause is thin and not a 3 because both elements are clearly present.	4 / 5
Trigger Term Quality	Includes natural user-facing terms ('MGnify', 'microbiome studies', 'samples', 'biome metadata', 'concise MGnify summaries') a user would plausibly say, giving good coverage; not a 5 because synonyms and accessions/extensions are absent, and not a 3 because the keyword set is broader than a single generic phrase.	4 / 5
Distinctiveness Conflict Risk	MGnify is a narrow, well-defined niche with distinct domain-specific triggers, so conflict with other skills is minimal; fits the 'clear niche with distinct triggers' anchor and is not a 4 because there is no meaningful overlap risk.	5 / 5
	Total	16 / 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: openai/plugins
Path: plugins/life-science-research/skills/mgnify-skill/SKILL.md
Commit: 1dc1958

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.