Name: replyio
Rating: 58.4 (1 reviews)
Author: membranedev

replyio

Reply.io integration. Manage Persons, Organizations, Leads, Activities, Notes, Files and more. Use when the user wants to interact with Reply.io data.

Quality

67%

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/replyio/SKILL.md

Quality

Content

61%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 action-oriented with executable Membrane CLI commands and a well-checkpointed connection flow. It loses points for some padding, the "Popular actions" placeholder, and missing validation/verification steps for action execution.

Suggestions

Add a verify step after running actions (e.g., check the `output` field or re-query the entity to confirm the change landed), especially for create/update/delete operations on Persons, Organizations, and Leads.

Trim the opening descriptive paragraph about what Reply.io is and remove the empty "Popular actions" stub or populate it with 3-5 concrete example actions.

Move the proxy flag reference table into a references file (e.g., PROXY.md) to keep SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with lean executable command blocks, but the opening marketing paragraph about what Reply.io is and filler like "Use action names and parameters as needed" could be trimmed.	3 / 5
Actionability	Provides copy-paste-ready commands for install, login, connection ensure, action list/run, and proxy requests with a flag table; the "Popular actions" section only points to discovery rather than enumerating specific Reply.io actions.	4 / 5
Workflow Clarity	The install→authenticate→connect→wait→search→run sequence is clear and the connection state handling (READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) is well checkpointed, but action execution on Persons/Leads has no validation or verify-the-result feedback loop, capping batch/destructive workflows at 3.	3 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections with no bundle files present; minor gap is that the proxy flag table and detailed state-handling could optionally live in a reference file, though inline placement is reasonable.	4 / 5
	Total	14 / 20 Passed

Description

73%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 cleanly identifies a distinct product niche and answers both what and when, with good trigger keywords. Its main weakness is the generic "Manage" action verb and a "when" clause that could be more specific.

Suggestions

Replace the generic "Manage" with 2-3 concrete verbs (e.g., "Create and update Persons, Organizations, and Leads, log Activities, attach Notes and Files").

Tighten the "Use when" clause with concrete triggers (e.g., "Use when the user wants to manage Reply.io prospects, sequences, or lead data").

Dimension	Reasoning	Score
Specificity	It names the domain and many concrete entities ("Persons, Organizations, Leads, Activities, Notes, Files"), but the action verb is the single generic "Manage ... and more" rather than several distinct concrete actions.	3 / 5
Completeness	Both "what" ("Manage Persons, Organizations, Leads, Activities, Notes, Files and more") and "when" ("Use when the user wants to interact with Reply.io data") are present, but the "when" clause is moderately generic and could name concrete triggers like email sequences or lead management.	4 / 5
Trigger Term Quality	Good keyword coverage centered on the product name "Reply.io" plus its core entity types, with a natural "Use when ... interact with Reply.io data" trigger; a few synonymous phrasings are missing but coverage is strong for a single-product skill.	4 / 5
Distinctiveness Conflict Risk	"Reply.io integration" is a clear niche tied to a specific SaaS product with distinct triggers, giving minimal overlap risk with other skills.	5 / 5
	Total	16 / 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/replyio/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.