Name: mindsdb
Rating: 56.8 (1 reviews)
Author: membranedev

mindsdb

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

Quality

65%

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 ./skills/mindsdb/SKILL.md

Quality

Content

67%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 action-dense with executable CLI commands and a logical, checkpointed connection workflow, but it is padded with conceptual explanation and overview filler, uses inconsistent step numbering, and keeps all content inline rather than splitting reference material into separate files.

Suggestions

Cut conceptual filler and the 'MindsDB Overview' bullet list, leaving only what Claude needs to execute; move the MindsDB product description to a single line or remove it.

Normalize the workflow into explicit numbered steps (1. Install, 2. Authenticate, 3. Connect, 4. Wait for READY, 5. Discover/run actions) so the 'skip to Step 2' references resolve, and add a verify/retry checkpoint after running actions.

Move the proxy flag table and detailed connection-state handling into a reference file (e.g., references/PROXY.md) and link to it, keeping SKILL.md a concise overview.

Dimension	Reasoning	Score
Conciseness	Most of the body is concrete CLI commands, but it pads with explanations Claude largely doesn't need ('MindsDB is an open-source AI layer... making AI accessible to data stored in SQL databases', 'so you can focus on the integration logic rather than auth plumbing') and a low-value 'MindsDB Overview' bullet list, matching the 'mostly efficient but includes some unnecessary explanation' anchor.	3 / 5
Actionability	It provides copy-paste-ready commands for install, login, connection ensure, polling, action list/run, and proxy requests plus a flag table, but the examples are generic Membrane-CLI workflow steps rather than MindsDB-specific cases, leaving minor gaps versus the fully-covered level.	4 / 5
Workflow Clarity	A clear install → authenticate → connect → wait-for-ready → search → run → proxy sequence is present with state-based checkpoints (poll until not BUILDING, handle CLIENT_ACTION_REQUIRED), but the step numbering is inconsistent ('skip to Step 2' and '1b' without labeled Step 1/2 headers) and there is no explicit verify/retry loop for action-run outcomes, keeping it at 'clear sequence with minor validation gaps'.	4 / 5
Progressive Disclosure	The body is well-organized into clear section headers with no buried or nested references and no bundle files, but at ~140 lines it exceeds the simple-skill threshold and inlines bulk (the proxy flag table, detailed connection-state handling) that could live in separate reference files, fitting 'good structure; minor organization gaps'.	4 / 5
	Total	15 / 20 Passed

Description

62%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 cleanly states what the skill does and when to use it with an explicit 'Use when' clause tied to the named MindsDB product, but its action verbs and trigger phrases are generic and could be more concrete.

Suggestions

Replace generic verbs with specific MindsDB capabilities (e.g., 'train and deploy ML models in SQL databases, run predictions, manage tables and jobs') to lift specificity.

Expand the 'when' clause with concrete trigger phrases users would actually say (e.g., 'Use when the user mentions MindsDB, training ML models in a database, running predictions, or querying MindsDB tables').

Dimension	Reasoning	Score
Specificity	The description names the MindsDB domain and 2-3 actions ('Manage data, records, and automate workflows'), but the actions are generic verbs on abstract nouns rather than concrete capabilities, fitting the '1-2 concrete actions, not comprehensive' anchor rather than the several-specific-actions level.	3 / 5
Completeness	It has an explicit 'what' ('MindsDB integration. Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with MindsDB data'), but the 'when' is somewhat generic rather than listing concrete trigger phrases, so it fits 'both present; when could be more specific' rather than the fully concrete level.	4 / 5
Trigger Term Quality	'MindsDB' and the phrase 'interact with MindsDB data' are natural terms a user would say, but common variations like 'MindsDB database', model training, or predictions are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Tying triggers to the named product 'MindsDB' gives a clear niche with minimal conflict risk, but the generic action verbs ('manage data, records, automate workflows') slightly broaden overlap, so it sits at 'mostly distinct; minor overlap risk' rather than the clearest-niche level.	4 / 5
	Total	14 / 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/mindsdb/SKILL.md
Commit: f484c82

Reviewed: 6 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.