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

Blog Docs Log in Get started

grafbase

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

Quality

62%

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/grafbase/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 a well-structured, actionable guide dominated by concrete CLI commands and a clear connection workflow. Its main weaknesses are a slightly padded intro, a missing end-to-end worked example, and a dangling 'Step 2' reference.

Suggestions

Trim the opening Grafbase explainer to one line; Claude can infer the platform's purpose from the docs link.

Add a single complete worked example that chains connection ensure -> action list -> action run with realistic output, so the common case is copy-paste end-to-end.

Fix the 'skip to Step 2' reference by either labeling the 'Searching for actions' section as Step 2 or rewording to 'skip to Searching for actions'.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete CLI commands, but the opening paragraph explains what Grafbase is ('serverless GraphQL platform', 'global data mesh, edge caching') and includes light filler ('so you can focus on the integration logic rather than auth plumbing'), fitting 'Mostly efficient but includes some unnecessary explanation'; not a 4 because the intro could be trimmed.	3 / 5
Actionability	It provides concrete, copy-paste-ready bash commands for login, connection ensure, polling, action list/run, and proxy requests with a clear flag table, matching 'Mostly executable guidance; concrete code or commands with minor gaps'; not a 5 because there is no complete end-to-end worked example tying the steps together.	4 / 5
Workflow Clarity	The connection flow is well-sequenced with a polling feedback loop and explicit state branches (READY, CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR), matching 'Clear sequence with most checkpoints present; minor validation gaps'; not a 5 because 'skip to Step 2' references a label that is never defined and error-recovery detail is light.	4 / 5
Progressive Disclosure	The file is well-organized into clearly headed sections (Overview, Install, Authentication, Connecting, Searching, Popular actions, Proxy, Best practices) with no nested references, matching 'Good structure; most content is appropriately placed; minor organization gaps'; not a 5 because the inline Popular actions table is reference material that could live in a separate file.	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 is functional with an explicit trigger clause and a distinct named-product niche, but its capability list is thin and generic. Tightening 'Manage Projects' into concrete actions and adding trigger synonyms would raise it.

Suggestions

Replace the generic 'Manage Projects' with 2-3 concrete actions (e.g., 'Run GraphQL queries and mutations, introspect schemas, manage cache and rate-limit rules').

Add natural trigger synonyms in the 'Use when...' clause (e.g., 'GraphQL API', 'Grafbase schema', 'edge caching') so users phrasing it differently still match.

Keep third-person voice (already correct) but expand the 'what' to briefly enumerate the main Grafbase resource types you can manage.

Dimension	Reasoning	Score
Specificity	The description names the domain (Grafbase) and a single generic action ('Manage Projects') but offers no concrete capabilities, matching the anchor 'Names the domain but actions are minimal or generic'; it is not a 3 because 'Manage Projects' is too vague to count as a concrete action like 'extracts content'.	2 / 5
Completeness	It answers both what ('Grafbase integration. Manage Projects.') and when ('Use when the user wants to interact with Grafbase data'), but the 'what' is thin and the 'when' could be more specific, matching 'Has both what and when; when could be more explicit or specific'; not a 5 because the trigger phrases lack concrete synonyms.	4 / 5
Trigger Term Quality	It includes relevant natural keywords ('Grafbase', 'Projects') and an explicit trigger phrase ('Use when the user wants to interact with Grafbase data'), but misses common synonyms or variations a user might say, fitting 'Some relevant keywords but missing common variations or synonyms'; not a 4 because coverage is thin.	3 / 5
Distinctiveness Conflict Risk	Grafbase is a specific named product with a clear niche and low overlap risk, fitting 'Mostly distinct; minor overlap risk with closely related skills'; not a 5 because 'Manage Projects' alone is generic enough to risk overlap with project-management 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/grafbase/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.