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

Blog Docs Log in Get started

fullcontact

FullContact integration. Manage Persons, Organizations. Use when the user wants to interact with FullContact 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/fullcontact/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 well-structured, command-driven integration guide with concrete executable commands and a clear connection workflow including validation checkpoints. Its main weaknesses are marketing-flavored padding in the intro and best-practices sections and the absence of a fully worked end-to-end example with real parameter values.

Suggestions

Trim the opening brand/marketing paragraph and the "burn less tokens" phrasing in Best practices to assume Claude's competence.

Add one fully worked end-to-end example showing real action input JSON and parsed output for a common case (e.g., enrich-person).

Fix the inconsistent step numbering (unlabeled "Step 2" reference and the orphan "1b" subsection) so the connection workflow reads as a coherent numbered sequence.

Dimension	Reasoning	Score
Conciseness	The bulk is tight, command-focused content, but the opening marketing paragraph ("helps businesses understand their customers better...") and phrases like "burn less tokens and make communication more secure" are unnecessary explanation, matching the score-3 anchor of mostly efficient with some tightening needed.	3 / 5
Actionability	Concrete copy-paste commands (npm install, membrane login, connection ensure, action list/run, request) with a popular-actions table provide mostly executable guidance, but action inputs only show a placeholder `{"key": "value"}` with no worked end-to-end example, leaving the minor gaps of score 4 rather than fully copy-paste-ready score 5.	4 / 5
Workflow Clarity	A clear install→authenticate→connect→poll→search→run sequence with state checks (READY/BUILDING/CLIENT_ACTION_REQUIRED) and a poll-again feedback loop is present, but cross-references to an unlabeled "Step 2" and a stray "1b" subsection create minor sequencing gaps, fitting score 4.	4 / 5
Progressive Disclosure	The body is well-organized with clear section headers and no nested external references (no bundle files exist), and the popular-actions and proxy-flag tables are appropriately inline; minor organization gaps (the "Step 2"/"1b" labeling) keep it at score 4 rather than the cleanly-navigable score 5.	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 clearly scoped to a distinct brand and includes both a what and a when, but its action verbs are generic and trigger coverage is thin with no synonyms or concrete trigger phrases. It sits at a solid mid-to-upper level with distinctiveness as its main strength.

Suggestions

Replace the generic verb "Manage" with specific concrete actions (e.g., "enrich, resolve, map, and delete Person and Organization identity records").

Expand the trigger clause with concrete phrases users would actually say, e.g. "Use when the user wants to enrich a person/company, resolve identity, or manage FullContact records."

Dimension	Reasoning	Score
Specificity	"Manage Persons, Organizations" names the domain and two concrete entity types, but "Manage" is generic and the action coverage is not comprehensive, matching the score-3 anchor rather than the multi-action score-4 anchor.	3 / 5
Completeness	Both a "what" (FullContact integration, manage Persons/Organizations) and a "when" ("Use when the user wants to interact with FullContact data") are present, but the trigger clause is generic rather than concrete phrases, matching score 4 rather than the explicit-trigger score 5.	4 / 5
Trigger Term Quality	"Use when the user wants to interact with FullContact data" surfaces the core "FullContact" keyword but offers no synonyms or variations, fitting the score-3 anchor with some relevant keywords rather than the broad coverage expected at score 4.	3 / 5
Distinctiveness Conflict Risk	"FullContact" is a specific named brand with a clear niche, so it is highly distinguishable from other skills with minimal conflict risk, matching the score-5 anchor.	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/fullcontact/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.