Name: pixiebrix
Rating: 57.599999999999994 (1 reviews)
Author: membranedev

pixiebrix

PixieBrix integration. Manage Persons, Organizations, Deals, Leads, Projects, Activities and more. Use when the user wants to interact with PixieBrix data.

Quality

66%

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/pixiebrix/SKILL.md

Quality

Content

61%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-packed with executable Membrane CLI commands and a well-structured connection workflow, but it carries some padded prose, a redundant entity list, and lacks validation feedback loops for destructive action/proxy operations.

Suggestions

Add a verification step after running actions or proxy requests (e.g., re-fetch the resource to confirm the change, or check the response status/error field) to restore workflow clarity above the destructive-operation cap.

Trim padded prose (the platform definition and "focus on integration logic" framing) and de-duplicate the entity list by collapsing the redundant AI-prefixed entries.

Consider moving the long entity enumeration into a references/ file and summarizing the key categories inline to improve token efficiency and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient command examples, but padded prose ("so you can focus on the integration logic rather than auth plumbing", the platform intro) and a ~60-item entity list with redundant AI-prefixed duplicates could be tightened, matching the mostly-efficient-but-could-tighten anchor.	3 / 5
Actionability	Concrete copy-paste commands are given throughout (npm install, membrane login, connection ensure, action run, request) with a clear proxy flag table, but placeholder gaps (CONNECTION_ID vs <id>, <actionId>) and the entity list being names rather than runnable actions keep it just below fully executable.	4 / 5
Workflow Clarity	The connection flow has good state-based checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED), but action execution and proxy requests (which support destructive POST/PUT/DELETE methods) lack any validation or verification feedback loop, triggering the destructive/batch cap at 3.	3 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections with a self-contained single-file structure and no nested references, though the large entity list could plausibly live in a separate reference file, matching the good-structure-with-minor-gaps anchor.	4 / 5
	Total	14 / 20 Passed

Description

71%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 answers both what and when with a distinct PixieBrix-specific trigger, but relies on a single repeated brand keyword and a generic "Manage" verb, leaving trigger-term coverage and specificity short of top marks.

Suggestions

Replace the repeated generic verb "Manage" with varied concrete actions (e.g., create, list, update, search) per entity to raise specificity.

Add natural synonyms and concrete trigger phrases users would say (e.g., "PixieBrix records", "PixieBrix bricks", ".pixiebrix") beyond the single brand name.

Tighten the "when" clause with concrete triggers (e.g., "Use when the user wants to create, search, or update PixieBrix records") instead of the generic "interact with PixieBrix data".

Dimension	Reasoning	Score
Specificity	It names the domain ("PixieBrix integration") and lists several concrete entity nouns ("Persons, Organizations, Deals, Leads, Projects, Activities"), but every action uses the same generic verb "Manage" and "and more" signals coverage gaps, so it sits below the comprehensive 5 anchor.	4 / 5
Completeness	Both a "what" ("Manage Persons, Organizations...") and an explicit "when" ("Use when the user wants to interact with PixieBrix data") are present, but the trigger is generic rather than concrete trigger phrases, so it is below the 5 anchor.	4 / 5
Trigger Term Quality	The only natural keyword is the brand "PixieBrix" (repeated as "PixieBrix data"), with no synonyms, file extensions, or common variations a user might actually say, matching the anchor for some relevant keywords but missing common variations.	3 / 5
Distinctiveness Conflict Risk	The trigger is anchored to the distinct brand name "PixieBrix", giving it a clear niche with minimal conflict risk against other skills, matching the 5 anchor.	5 / 5
	Total	16 / 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/pixiebrix/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.