Name: anymail-finder
Rating: 55.2 (1 reviews)
Author: membranedev

anymail-finder

Anymail Finder integration. Manage data, records, and automate workflows. Use when the user wants to interact with Anymail Finder 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/anymail-finder/SKILL.md

Quality

Content

75%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, actionable integration guide with concrete membrane CLI commands and a clear connection-state workflow including retry checkpoints. Its main weaknesses are minor verbosity in a few prose passages, unfilled placeholders in the action examples, and a monolithic single-file structure with inlined reference tables that could be split out.

Suggestions

Trim explanatory prose such as the 'focus on the integration logic rather than auth plumbing' and 'fastest way to get a connection' sentences so every line earns its place.

Fill the Popular actions Description column and provide at least one concrete run example with real parameter JSON (e.g. a find-person-email call) so the action guidance is fully copy-paste ready.

Consider moving the full Popular actions and proxy-flag reference tables into a separate reference file linked one level deep, to bring progressive disclosure closer to the ideal split for a skill of this length.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with executable CLI commands and little padding, but a few prose passages ('so you can focus on the integration logic rather than auth plumbing', 'This is the fastest way to get a connection') could be trimmed, fitting the efficient-with-minor-overexplanation anchor.	4 / 5
Actionability	It provides concrete, copy-paste-ready commands for install, auth, connection, action search/run, and proxy, but the Popular actions table has empty Description columns and run examples use unfilled placeholders (CONNECTION_ID, actionId), leaving minor gaps versus fully-specified examples.	4 / 5
Workflow Clarity	The connection flow is a clear state machine with explicit checkpoints and a retry loop (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR, 'poll again'), but the document is not a single end-to-end numbered workflow and lacks a final result-validation step, matching the clear-sequence-with-minor-gaps anchor.	4 / 5
Progressive Disclosure	The body is a single self-contained file (no references/ scripts/ assets/ bundles exist) organized into clear sections; at ~140 lines it exceeds the simple-skill threshold, and the inlined Popular actions and proxy-flag tables are bulk reference material, so it fits good-structure-with-minor-organization-gaps rather than the ideal one-level-deep split.	4 / 5
	Total	16 / 20 Passed

Description

50%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 an explicit 'Use when' clause and is anchored to a distinct product name, but it relies on generic verbs ('manage data, records, automate workflows') and lacks the natural trigger phrases users would actually say. Tightening it to name concrete email-finding/verification actions and triggers would raise specificity and trigger-term quality.

Suggestions

Replace the generic 'Manage data, records, and automate workflows' with concrete Anymail Finder actions such as 'Find verified email addresses by name, domain, or LinkedIn URL; verify email deliverability; enrich company and decision-maker contacts.'

Expand the 'when' clause with natural user triggers, e.g. 'Use when the user wants to find or verify an email address, look up contact emails for a company, or enrich lead/candidate contact data.'

Add file-format or synonym keywords users naturally say ('email address', 'B2B leads', 'verify email', 'LinkedIn email') to improve trigger-term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	It names the Anymail Finder domain but the actions 'Manage data, records, and automate workflows' are generic and not tied to the product's actual email-finding/verification capabilities, fitting the anchor for minimal or generic actions.	2 / 5
Completeness	It states both a 'what' (Anymail Finder integration, manage data/records/workflows) and an explicit 'when' ('Use when the user wants to interact with Anymail Finder data'), but the trigger is generic rather than concrete phrases, matching the anchor where 'when' could be more explicit.	4 / 5
Trigger Term Quality	Beyond the brand name 'Anymail Finder' and the jargon phrase 'interact with Anymail Finder data', there are none of the natural terms a user would actually say ('find email', 'verify email', 'email address'), placing it just below the midpoint anchor.	2 / 5
Distinctiveness Conflict Risk	The brand anchor 'Anymail Finder' keeps it distinct from other skills despite the generic 'manage data, records, automate workflows' phrasing, fitting the anchor for mostly-distinct skills with minor overlap risk.	4 / 5
	Total	12 / 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/anymail-finder/SKILL.md
Commit: f484c82

Reviewed: 3 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.