Name: rainforest-qa
Rating: 58.4 (1 reviews)
Author: membranedev

rainforest-qa

Rainforest QA integration. Manage data, records, and automate workflows. Use when the user wants to interact with Rainforest QA 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/rainforest-qa/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 body is highly actionable with copy-paste CLI commands and a solid connection-state workflow, but it is held back by some introductory padding and command redundancy, a destructive-proxy section lacking validation steps, and a dangling "Step 2" reference. Adding verification guidance for destructive proxy calls would most improve the score.

Suggestions

Add a validation/verification step before destructive proxy requests (e.g. dry-run or GET-before-DELETE confirmation) and a retry-on-error loop, since `membrane request` supports DELETE/PUT/PATCH.

Fix the dangling "skip to Step 2" / "1b" numbering by labeling the subsequent sections as explicit steps or removing the cross-reference.

Trim the introductory paragraph defining Rainforest QA and the "so you can focus on the integration logic" line, and deduplicate the action-list command between "Searching for actions" and "Popular actions".

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient commands, but the introductory paragraph explaining what Rainforest QA is ("a no-code testing platform...") and the "so you can focus on the integration logic rather than auth plumbing" line are unnecessary padding, and the "Popular actions" section repeats the action-list command from "Searching for actions" — fitting the mostly-efficient-but-could-be-tightened anchor rather than a 4.	3 / 5
Actionability	Commands are copy-paste ready and cover the common cases — install, login (including headless completion), connection ensure/get --wait, action list/run with --input, and request with a full flags table — fully executable with concrete placeholders.	5 / 5
Workflow Clarity	The connection flow has a clear state-based sequence with a poll-and-retry feedback loop (READY/BUILDING/CLIENT_ACTION_REQUIRED), but the proxy section supports destructive methods (DELETE, PUT, PATCH) with no validation or verification guidance, which caps workflow clarity at 3 per the destructive-operations rule; the dangling "Step 2" reference is also a minor sequencing gap.	3 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections (install, auth, connecting, searching, running, proxy, best practices) with all material appropriately inline for a CLI integration skill and no nested references, but at ~140 lines with no external file split it sits at good-structure rather than the ideal one-level-deep reference pattern.	4 / 5
	Total	15 / 20 Passed

Description

66%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..." trigger and names a distinct product niche, but its capability list is generic (manage data/records, automate workflows) and lacks concrete action verbs. Tightening the action list would lift specificity and trigger-term quality.

Suggestions

Replace generic verbs with concrete Rainforest QA capabilities (e.g. "create and run tests, manage run groups, filter and tag tests, view test runs").

Expand the trigger phrase with natural synonyms users say (e.g. "Use when the user wants to run Rainforest QA tests, check test runs, or manage Rainforest QA environments and sites").

Drop the filler clause "Manage data, records, and automate workflows" in favor of specific QA actions to raise specificity.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Rainforest QA domain plus a few actions, but the verbs (manage, automate) and nouns (data, records, workflows) are generic rather than concrete capabilities — matching the domain-plus-1-2-actions anchor without being comprehensive.	3 / 5
Completeness	Both halves are present — a what ("Manage data, records, and automate workflows") and an explicit when ("Use when the user wants to interact with Rainforest QA data"), but the when clause is somewhat generic rather than packed with concrete trigger phrases, so it sits at the both-present-but-could-be-more-specific anchor rather than a 5.	4 / 5
Trigger Term Quality	The only natural keyword is the product name "Rainforest QA" in "Use when the user wants to interact with Rainforest QA data"; relevant but missing common variations or synonyms, fitting the some-keywords-but-incomplete anchor.	3 / 5
Distinctiveness Conflict Risk	"Rainforest QA integration" names a specific SaaS product with a distinct trigger, giving it a clear niche with minimal risk of firing for an unrelated skill.	5 / 5
	Total	15 / 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/rainforest-qa/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.