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

Blog Docs Log in Get started

hygraph

Hygraph integration. Manage Projects. Use when the user wants to interact with Hygraph 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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/hygraph/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 highly actionable with concrete Membrane CLI commands and a well-instrumented connection workflow, but it is somewhat verbose and references a 'Step 2' that is never defined. Trimming explanatory fluff and fixing the step numbering would make it sharper.

Suggestions

Cut concept explanation Claude already knows — e.g., the 'Hygraph is a headless content management system...' sentence and 'Membrane handles authentication... so you can focus on the integration logic rather than auth plumbing' phrasing.

Resolve the dangling 'Step 2' reference: either relabel the connection sections as Step 1 / Step 2 or remove the cross-reference.

Add a brief validation/check step before destructive actions (e.g., confirm IDs before delete-content-entry / delete-asset) since the popular-actions table includes deletes but Running actions shows no pre-check.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but includes mild over-explanation Claude does not need (the 'Hygraph is a headless content management system...' intro and 'burn less tokens / make communication more secure' best-practice padding).	3 / 5
Actionability	Provides concrete, executable CLI commands throughout (install, login, connection ensure, action list/run, request) plus flag tables and a popular-actions table; minor gaps are placeholders like CONNECTION_ID that the user must fill.	4 / 5
Workflow Clarity	The connection flow has a clear sequence with explicit state checkpoints (READY, BUILDING, CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR) and a poll/feedback loop; a dangling 'Step 2' reference and no pre-check before destructive actions are minor gaps.	4 / 5
Progressive Disclosure	Well-organized single-file skill with clear sections and no external references needed; the large inline popular-actions and flag tables could arguably be split out, but inline placement is reasonable for a CLI skill.	4 / 5
	Total	15 / 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 is well-targeted to a distinct product and includes an explicit Use-when trigger, but it is thin on concrete capabilities and natural-language synonyms. Expanding the action list and trigger phrasing would lift it from good to strong.

Suggestions

Replace the generic 'Manage Projects' with a few concrete actions drawn from the body (e.g., 'Create and publish content entries, manage assets, run GraphQL queries').

Broaden trigger terms to natural variations users might say, such as 'Hygraph', 'Hygraph CMS', 'Hygraph content', 'Hygraph GraphQL API', or 'Hygraph assets'.

Tighten the 'what' so it summarizes breadth in one clause (e.g., 'Manage Hygraph content, assets, schema, and GraphQL queries') instead of a single resource type.

Dimension	Reasoning	Score
Specificity	Names the domain ('Hygraph integration') and one concrete action ('Manage Projects'), but coverage is not comprehensive given the many resource types (Content, Asset, Schema, etc.) listed in the body.	3 / 5
Completeness	Explicitly answers both what ('Hygraph integration. Manage Projects.') and when ('Use when the user wants to interact with Hygraph data.'), though the 'what' could be more concrete.	4 / 5
Trigger Term Quality	Includes 'Hygraph' and 'Hygraph data' as natural terms, but lacks common variations or synonyms that users might say; coverage is relevant but thin.	3 / 5
Distinctiveness Conflict Risk	Hygraph is a specific named product with a distinct trigger, so it is clearly distinguishable from other skills with minimal conflict risk.	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/hygraph/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.