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

marketstack

Marketstack integration. Manage data, records, and automate workflows. Use when the user wants to interact with Marketstack 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/marketstack/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 strong: executable commands, a full proxy-options table, and a state-machine workflow with explicit recovery loops. Its main weaknesses are mild intro padding, placeholder proxy paths, and an undefined "Step 2" reference that slightly breaks navigation.

Suggestions

Define "Step 2" explicitly (e.g., add a "## Step 2: Search for actions" header) and reconcile the "1b" subheading with a corresponding "1a" or top-level step so the workflow numbering is coherent.

Replace the proxy placeholder path with a concrete Marketstack endpoint example, e.g. `membrane request CONNECTION_ID /eod --query "symbols=AAPL"`.

Trim the opening "Marketstack is a real-time stock market data API..." paragraph to a one-line context note to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands and minimal concept explanation, but the opening "Marketstack is a real-time stock market data API" paragraph and the Membrane-auth overview include mild over-explanation that could be trimmed, matching the score-4 anchor of efficient content with minor instances to cut.	4 / 5
Actionability	It provides copy-paste-ready commands with flags for install, login, connection, action list/run, and proxy, plus a full options table — mostly executable — but the proxy example uses a placeholder path and "Step 2" is referenced without a concrete target, leaving minor gaps versus the score-5 anchor.	4 / 5
Workflow Clarity	The connection flow is clearly sequenced with explicit state handling (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and polling recovery loops, but the undefined "Step 2" reference and the orphaned "1b" heading (with no 1/1a) are minor navigation gaps, fitting the score-4 anchor.	4 / 5
Progressive Disclosure	With no bundle files present, the single ~155-line SKILL.md is well-organized into clear sections (install, auth, connecting, searching, running, proxy, best practices) with no nested references, but it exceeds the 50-line simple-skill threshold so it stays at the score-4 anchor rather than 5.	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 answers both what and when and is brand-anchored, but its action verbs are generic and it lacks the natural trigger terms (stocks, ticker, EOD) a user would actually say. Specificity and trigger-term quality are the weakest dimensions.

Suggestions

Replace generic verbs with concrete Marketstack capabilities, e.g. "Fetch EOD and intraday stock prices, look up tickers and exchanges, query historical market data."

Add natural user-facing trigger terms such as stocks, ticker, EOD, quotes, and market data to the description.

Make the when-clause more specific, e.g. "Use when the user wants stock prices, ticker lookups, or historical/intraday market data from Marketstack."

Dimension	Reasoning	Score
Specificity	Names the domain (Marketstack) but the actions — "Manage data, records, and automate workflows" — are generic and not concrete API capabilities, matching the score-2 anchor of naming the domain with minimal/generic actions.	2 / 5
Completeness	It states both what ("Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Marketstack data"), but the when clause is generic and could be more specific, matching the score-4 anchor and falling short of the explicit concrete triggers needed for a 5.	4 / 5
Trigger Term Quality	The only trigger keywords are the brand name and "Marketstack data"; natural user phrases like stocks, ticker, EOD, quotes, or market data are missing, fitting the score-2 anchor of one or two generic keywords with the natural phrases absent.	2 / 5
Distinctiveness Conflict Risk	The Marketstack brand name anchors a clear niche and the "interact with Marketstack data" trigger is distinct, with only minor overlap risk against other generic data skills, matching the score-4 anchor.	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/marketstack/SKILL.md
Commit: f484c82

Reviewed: 6 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.