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

safegraph

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

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/safegraph/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 content is a strongly actionable, well-sequenced guide to driving SafeGraph via the Membrane CLI, with genuine state-polling validation; its main weaknesses are background padding and a vague overview section.

Suggestions

Trim the introductory SafeGraph background paragraph and the 'auth plumbing' commentary so the body leads with the workflow.

Replace the bare 'SafeGraph Overview' bullet list and 'Use action names and parameters as needed' with a concrete example action query, or move it to a reference file.

Label the post-connection step explicitly (e.g. '## Step 2: Search for actions') so the 'skip to Step 2' reference resolves.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient commands, but the opening paragraph explaining what SafeGraph is, the 'auth plumbing' aside, and the vague 'SafeGraph Overview' bullet list are unnecessary explanation that could be trimmed.	3 / 5
Actionability	It provides copy-paste-ready commands for install, login, connection ensure/get, action list/run, and proxying, with only the 'SafeGraph Overview' and 'Popular actions' sections staying abstract.	4 / 5
Workflow Clarity	There is a clear install→auth→connect→search→run sequence with a state-polling feedback loop (READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), though the 'skip to Step 2' reference points to an unlabeled step.	4 / 5
Progressive Disclosure	With no bundle files, content lives in one well-sectioned file with clear headers and easy navigation, but the >50-line length and the disjointed 'SafeGraph Overview' list leave minor organization gaps.	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-statement with an explicit 'Use when' trigger and leverages a distinctive brand name, but its capability verbs are vague and it relies on a single trigger keyword without synonyms.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete SafeGraph actions such as querying POI/places data, fetching geometry, or pulling patterns.

Add natural trigger synonyms and file/domain cues, e.g. 'Use when the user wants to query SafeGraph POI data, places, points of interest, or building footprints.'

Dimension	Reasoning	Score
Specificity	The description names the SafeGraph domain but its actions — 'Manage data, records, and automate workflows' — are generic verbs rather than concrete operations, matching the 'names domain, actions minimal/generic' anchor rather than the concrete-action anchor above.	2 / 5
Completeness	Both a 'what' ('Manage data, records, and automate workflows') and an explicit 'Use when the user wants to interact with SafeGraph data' trigger are present, but the single generic trigger keeps it just below the comprehensive anchor 5.	4 / 5
Trigger Term Quality	It surfaces 'SafeGraph' and 'SafeGraph data' but lacks common synonyms a user might say (POI, places, points of interest, building footprints), fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	SafeGraph is a unique named service giving it a clear niche and low conflict risk, though the generic 'manage data/records/workflows' phrasing leaves minor overlap with other data-integration 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/safegraph/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.