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

grammarly

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

This is a solidly actionable, well-structured integration skill whose command examples and connection-state workflow are genuinely useful and Membrane-specific. Its main weaknesses are an unnecessary intro explaining Grammarly, a "Popular actions" section that underdelivers, and the absence of verification steps around destructive proxy requests.

Suggestions

Remove or trim the opening paragraph that defines what Grammarly is; Claude already knows this and it consumes context for no gain.

Either populate "Popular actions" with a few real Grammarly actions (e.g. fetch suggestions for a document) or rename the section to reflect that it only covers action discovery.

Add a verification/check step after proxy requests and action runs that mutate state, so destructive operations include a confirm-or-check feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient command documentation, but the opening paragraph ("Grammarly is an AI-powered writing assistant that helps users improve their grammar...") explains what Grammarly is — something Claude already knows — and the sparse "Grammarly Overview" list plus "Use action names and parameters as needed" add little.	3 / 5
Actionability	It provides copy-paste-ready membrane commands (login, connection ensure, action list/run, request) with a clear flags table, but the "Popular actions" heading promises specific actions and delivers only a discovery command — a minor gap.	4 / 5
Workflow Clarity	The connection workflow is clearly sequenced with explicit state-based checkpoints and polling feedback loops (BUILDING → READY / CLIENT_ACTION_REQUIRED → re-poll), though the later action-run and proxy sections lack verification steps for potentially destructive HTTP methods.	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections (Install, Authentication, Connecting, Searching, Popular actions, Proxy, Best practices) with no nested references, but at ~140 lines all material is inlined in SKILL.md with no bundle files to offload detail.	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 brand-specific domain with an explicit 'Use when' trigger, but its capabilities are stated in generic CRUD terms rather than the concrete writing-assistant actions that distinguish Grammarly. Tightening the action list and trigger phrasing to reference grammar, writing suggestions, and documents would lift it notably.

Suggestions

Replace generic actions ("Manage data, records, and automate workflows") with concrete Grammarly capabilities such as checking grammar, retrieving writing suggestions, or analyzing documents.

Expand the trigger to natural user phrasing, e.g. "Use when the user wants to check grammar, get writing suggestions, or interact with Grammarly documents."

Drop the vague "interact with Grammarly data" wording in favor of specific trigger terms users actually say.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Grammarly integration") but its actions are generic — "Manage data, records, and automate workflows" — rather than concrete Grammarly capabilities like grammar checking, writing suggestions, or document analysis.	2 / 5
Completeness	Both a "what" (manage data, records, automate workflows) and an explicit "when" ("Use when the user wants to interact with Grammarly data") are present, though the "when" trigger is generic and could be far more specific.	4 / 5
Trigger Term Quality	It includes the strong brand keyword "Grammarly" plus "data," "records," and "workflows," but misses the natural use-case terms a user would actually say (grammar, writing, suggestions, documents).	3 / 5
Distinctiveness Conflict Risk	The brand name "Grammarly" gives it a clear niche with minimal conflict risk, but the generic surrounding phrasing ("interact with Grammarly data") leaves minor overlap risk 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/grammarly/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.