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

Blog Docs Log in Get started

graphy

Graphy integration. Manage Organizations. Use when the user wants to interact with Graphy 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/graphy/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 a clean, mostly executable guide to driving Graphy through the Membrane CLI, with good sequencing and state-based recovery on the connection flow. Its main weakness is workflow clarity: the batch/list action workflow has no validation or verification checkpoints, which the rubric caps at 3.

Suggestions

Add a verification checkpoint after running batch/list actions, e.g. inspect the output field, confirm expected record count, and handle pagination or empty results before proceeding.

Resolve the abstract placeholders: show how to obtain CONNECTION_ID from the connection ensure output and pick an actionId from the action list results.

Move the Popular actions table and proxy flag reference into a separate reference file, leaving SKILL.md as a concise overview with a clearly signaled pointer.

Dimension	Reasoning	Score
Conciseness	The body is efficient, relying on tables and executable code blocks without over-explaining concepts Claude knows, with only minor filler such as "so you can focus on the integration logic rather than auth plumbing" and "This is the fastest way to get a connection".	4 / 5
Actionability	Provides concrete, runnable Membrane CLI commands with real flags (--json, --wait, --intent) and a Popular actions table with real action keys; minor gaps are unresolved placeholders like CONNECTION_ID and the abstract --intent value.	4 / 5
Workflow Clarity	The connection flow is well sequenced with state-based feedback (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR), but the action-running workflow for batch/list operations (orders, users) lacks validation or verification of returned data, capping this dimension at 3.	3 / 5
Progressive Disclosure	Single well-organized SKILL.md with clearly labeled sections and no nested references; the bulk Popular actions and proxy-flag tables are reference material that could be split into separate files, leaving a minor organization gap.	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 includes both a capability statement and an explicit "Use when" trigger tied to a named product, which gives it reasonable completeness and distinctiveness. Its weakness is specificity and trigger-term quality: it says only "Manage Organizations" and the trigger is generic rather than enumerating the concrete entities (orders, courses, users) the skill actually handles.

Suggestions

Replace the generic "Manage Organizations" with concrete actions, e.g. "Manage Graphy orders, enrollments, courses, users, and products".

Expand the trigger phrase to include natural user terms, e.g. "Use when the user wants to query or manage Graphy orders, enrollments, courses, users, or products."

Keep third-person voice (already compliant) but ensure the action list maps to the popular actions exposed in the skill body.

Dimension	Reasoning	Score
Specificity	"Manage Organizations" names the Graphy domain but offers only a single minimal, generic action with no listing of concrete capabilities (orders, enrollments, courses, products are all absent from the description).	2 / 5
Completeness	Both "what" ("Manage Organizations") and "when" ("Use when the user wants to interact with Graphy data") are explicitly present; the "when" could be more specific with concrete trigger phrases.	4 / 5
Trigger Term Quality	Includes the natural keyword "Graphy" and an explicit "Use when" clause, but the trigger phrase "interact with Graphy data" is generic and misses the concrete terms users would actually say (orders, courses, users, enrollments).	3 / 5
Distinctiveness Conflict Risk	Naming the specific product "Graphy" gives it a clear niche with minimal conflict risk, though the generic "Manage Organizations" trigger leaves minor overlap potential with other admin-style skills.	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/graphy/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.