Name: brainshop
Rating: 55.2 (1 reviews)
Author: membranedev

brainshop

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

Quality

63%

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/brainshop/SKILL.md

Quality

Content

68%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 comprehensive executable Membrane CLI commands and well-organized sections, but it wastes tokens on a generic intro and a garbled overview list and lacks explicit validation checkpoints in its workflow. Tightening the prose and adding verify-after-run steps would raise conciseness and workflow clarity.

Suggestions

Delete or fix the broken "BrainShop Overview" bullet list (duplicate Knowledge Source / Document items with no explanation) and trim the introductory paragraph about what BrainShop is.

Add explicit validation checkpoints after risky steps, e.g. confirm the connection exists with `membrane connection list --json` before searching actions, and check the action-run output for errors before reporting success to the user.

Consider splitting the proxy flag table and popular-actions reference into a separate reference file so the SKILL.md body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient lean command examples, but the opening paragraph explaining what BrainShop is ("a conversational AI platform that allows developers to build and deploy chatbots...") and the garbled "BrainShop Overview" bullet list are unnecessary noise Claude does not need. It is above the verbose 2 anchor but not the lean 4 because of these padding sections.	3 / 5
Actionability	The skill provides fully executable, copy-paste-ready commands across install, login (incl. headless), connect, list connections, action search, action run with JSON params, and proxy, plus a popular-actions table and a full proxy flag table. Specific examples cover the common cases, matching the 5 anchor.	5 / 5
Workflow Clarity	A clear sequence exists (install → login → connect → discover actions → run/proxy) with numbered steps, but there are no explicit validation checkpoints — e.g. no check that the connection succeeded or that an action ran without error, only an implicit "output contains the new connection id". This matches the 3 anchor of sequenced steps with validation gaps, below the 4 anchor which requires most checkpoints present.	3 / 5
Progressive Disclosure	Content is organized into clear sections with no nested (2+ level) references and the single file is easy to navigate, but at ~130 lines it exceeds the under-50-line simple-skill exception and has a minor organization gap (the broken "BrainShop Overview" list, no quick-start/advanced split). It is above the 3 anchor but not the fully split 5 anchor.	4 / 5
	Total	15 / 20 Passed

Description

57%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 pairs a what-and-when structure with an explicit Use-when trigger and a distinct named platform, but its capability verbs are generic and trigger-keyword coverage is limited. Strengthening the concrete actions and adding synonyms would lift specificity and trigger quality.

Suggestions

Replace generic verbs with concrete capabilities, e.g. "Create and train chatbot brains, send messages and get responses" referencing the actual action set.

Broaden trigger terms with natural synonyms users might say (chatbots, virtual assistants, BrainShop API, .brain) beyond "interact with BrainShop data".

Make the when-clause more concrete, e.g. "Use when the user wants to build, train, or query BrainShop chatbots."

Dimension	Reasoning	Score
Specificity	The description names the domain ("BrainShop integration") but its actions are minimal and generic — "Manage data, records, and automate workflows" are abstract verbs with no concrete capability. It sits at the anchor for naming a domain with minimal/generic actions, below the 3 anchor which requires 1-2 concrete actions.	2 / 5
Completeness	It states both a "what" ("Manage data, records, and automate workflows") and an explicit "Use when the user wants to interact with BrainShop data" clause, so it clears the 3 cap. It is not a 5 because the "what" is generic and the "when" could be more specific with concrete trigger phrases.	4 / 5
Trigger Term Quality	"interact with BrainShop data" plus "data, records, workflows" give some relevant natural keywords, but coverage is thin with no synonyms, common variations, or file extensions. This matches the anchor where some relevant keywords are present but common variations are missing, below the 4 anchor's broader keyword coverage.	3 / 5
Distinctiveness Conflict Risk	The named platform "BrainShop" gives it a recognizable niche and low conflict risk, but the generic "data, records, workflows" verbs leave minor overlap risk with similarly broad integration skills. It is mostly distinct but not a 5 with fully distinct triggers.	4 / 5
	Total	13 / 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/brainshop/SKILL.md
Commit: f484c82

Reviewed: 4 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.