Name: nannyml
Rating: 62.4 (1 reviews)
Author: membranedev

nannyml

NannyML integration. Manage data, records, and automate workflows. Use when the user wants to interact with NannyML data.

Quality

74%

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 ./skills/nannyml/SKILL.md

Quality

Content

82%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 highly actionable with executable CLI commands and a sensible validated workflow, organized into clean sections; its main weaknesses are minor marketing fluff and a couple of confusing step-numbering references.

Suggestions

Fix the step numbering: the "skip to Step 2" reference has no labeled Step 2, and the "1b" subsection has no matching 1a — renumber or relabel the connection flow consistently.

Trim promotional phrasing like "so you can focus on the integration logic rather than auth plumbing" to keep the body token-lean.

Consider moving the proxy flags table and the full clientAction state reference into a separate reference file so the main body stays a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but includes minor over-explanation such as "so you can focus on the integration logic rather than auth plumbing" and a brief conceptual intro that could be trimmed, matching the efficient-with-minor-fluff anchor.	4 / 5
Actionability	It provides copy-paste-ready CLI commands for every common case (install, login, connection ensure, action list/run, proxy request) with clear flag examples and a proxy options table, matching the fully-executable anchor.	5 / 5
Workflow Clarity	A clear install→auth→connect→search→run sequence exists with state-polling validation and a retry loop for CLIENT_ACTION_REQUIRED, but the dangling "skip to Step 2" reference and an unlabeled "1b" subsection introduce minor navigation gaps.	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections with no nested or buried references, and as a self-contained CLI integration skill it appropriately keeps guidance inline; it falls short of 5 only because nothing is split out and the proxy/action detail could justify a reference file.	4 / 5
	Total	17 / 20 Passed

Description

66%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 correctly includes both a what and a Use-when clause and targets a distinctive niche, but its actions and trigger phrasing are generic, omitting the concrete monitoring/drift terms users would naturally say.

Suggestions

Replace generic verbs ("Manage data, records, and automate workflows") with concrete NannyML actions such as estimating post-deployment model performance, detecting data drift, and monitoring model health.

Expand the trigger to reflect natural user phrasing, e.g. "Use when the user wants to monitor model performance, detect data drift, or check post-deployment model health with NannyML."

Mention key NannyML synonyms/terms (drift, performance estimation, CBPE/DLE) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the NannyML domain and a few actions ("Manage data, records, and automate workflows") but the actions are generic rather than concrete, matching the anchor for naming a domain with 1-2 non-comprehensive actions.	3 / 5
Completeness	It states both what ("Manage data, records, and automate workflows") and when ("Use when the user wants to interact with NannyML data"), but the when is explicit yet generic rather than specific, matching the anchor for having both with an imprecise when.	4 / 5
Trigger Term Quality	"NannyML" is a natural keyword a user would say, but the trigger "interact with NannyML data" misses common variations users actually voice (model performance, drift, monitoring), fitting the anchor with some relevant keywords but missing synonyms.	3 / 5
Distinctiveness Conflict Risk	NannyML is a specific named product with a distinct trigger ("NannyML data"), giving it a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	15 / 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: membranedev/application-skills
Path: skills/nannyml/SKILL.md
Commit: f484c82

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.