Name: textcortex
Rating: 52.8 (1 reviews)
Author: membranedev

textcortex

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

Quality

59%

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/textcortex/SKILL.md

Quality

Content

68%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-organized, mostly executable integration guide with concrete commands and a strong connect/poll state-handling flow. Its main weakness is workflow clarity: step numbering is inconsistent and the destructive-capable action-run/proxy path lacks verification checkpoints, capping that dimension at 3.

Suggestions

Add an explicit validation/verify checkpoint after running actions or proxy requests (e.g. check the `output`/error fields and confirm success before reporting to the user), especially for batch or destructive operations.

Fix the step numbering — label the connect flow as Step 1 (with 1a for ensure and 1b for polling) and define what "Step 2" refers to, or remove the dangling cross-references.

Make the "Popular actions" section deliver on its title by listing a few named high-value TextCortex actions with example `action run` commands, or remove the heading if it only restates discovery.

Dimension	Reasoning	Score
Conciseness	The body is largely lean with command examples and a compact flags table, but the opening "TextCortex is an AI writing assistant..." paragraph and the throwaway "When to use which actions: Use action names and parameters as needed" line could be trimmed, fitting the score-4 anchor of efficient with minor over-explanation.	4 / 5
Actionability	It provides concrete copy-pasteable commands for install, auth, connect, search, run, and proxy plus a flags table, but the "Popular actions" header promises named actions yet only repeats the discovery command, leaving a minor gap that keeps it at score 4 rather than 5.	4 / 5
Workflow Clarity	The connect-and-poll flow is well sequenced with explicit state handling and error recovery, but step numbering is inconsistent ("skip to Step 2" with no labeled Step 1; a "1b" with no 1a) and the core action-run/proxy workflow lacks validation checkpoints for potentially destructive or batch operations, which per the rubric caps this at 3.	3 / 5
Progressive Disclosure	There are no bundle files and none are referenced, but the single-file integration guide is organized into clear, well-signaled sections (Overview, Working with TextCortex, Best practices) with no nested references, matching score-4 good structure rather than 5 (the detailed clientAction reference and best-practices could arguably be split out).	4 / 5
	Total	15 / 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 answers both what and when and is anchored to a distinct product name, but it relies on generic verbs ("manage data, records, automate workflows") and lacks concrete, natural trigger terms. Specificity and trigger-term quality are the weakest dimensions.

Suggestions

Replace generic verbs with concrete TextCortex capabilities, e.g. "Generate blog posts, marketing copy, and documents; apply templates and manage projects."

Add natural trigger terms users would actually say, such as "writing copy," "marketing content," "blog posts," or "content generation," beyond repeating the product name.

Tighten the "Use when" clause to name the content types or workflows (e.g. "Use when the user wants to generate or edit marketing copy, blog posts, or other TextCortex content").

Dimension	Reasoning	Score
Specificity	The description names the TextCortex domain but its actions ("Manage data, records, and automate workflows") are minimal and generic abstract verbs rather than concrete capabilities like generating blog posts or marketing copy, matching the score-2 anchor.	2 / 5
Completeness	It provides a clear "what" (TextCortex integration managing data/records and automating workflows) and an explicit "when" ("Use when the user wants to interact with TextCortex data"), though the trigger could be more specific, matching the score-4 anchor rather than 3 (both present) or 5 (not concrete enough).	4 / 5
Trigger Term Quality	Keywords are essentially just the product name repeated ("TextCortex integration", "interact with TextCortex data") with no natural user phrases, synonyms, or content-type terms, fitting the score-2 anchor of one or two generic keywords missing common variations.	2 / 5
Distinctiveness Conflict Risk	Anchoring to the specific product name "TextCortex" gives it a clear niche with low conflict risk, but the generic surrounding verbs leave minor overlap risk, matching score-4 rather than 5 (verbs too generic for minimal conflict) or 3.	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/textcortex/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.