Name: llama-ai
Rating: 60 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

llama-ai

Llama AI integration. Manage Organizations. Use when the user wants to interact with Llama AI data.

Quality

68%

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/llama-ai/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 body is well-structured and highly actionable, with copy-paste-ready CLI commands covering setup, connection, action discovery, execution, and proxy fallback. Its main weakness is conciseness, due to an unnecessary background paragraph and a few padded asides.

Dimension	Reasoning	Score
Conciseness	Quotes: "Llama AI is a platform that provides AI-powered solutions for generating and understanding natural language. It's used by businesses and developers to automate tasks like content creation, chatbots, and text analysis." and "so you can focus on the integration logic rather than auth plumbing". The bulk is tight CLI commands, but the opening background paragraph and a few explanatory asides are unnecessary padding Claude does not need; matches the 3 anchor and not a 4 because of these trimmable explanatory passages.	3 / 5
Actionability	Quotes: "npx @membranehq/cli@latest login --tenant", "npx @membranehq/cli@latest connect --connectorId=CONNECTOR_ID --json", "npx @membranehq/cli@latest action run --connectionId=CONNECTION_ID ACTION_ID --json", and the proxy flag table. Commands are copy-paste ready with real flags and cover the common cases (login, connect, list, discover, run, proxy); matches the 5 anchor for fully executable guidance.	5 / 5
Workflow Clarity	Quotes: "### First-time setup", "### Connecting to Llama AI", "### Getting list of existing connections", "### Searching for actions", "### Running actions". The setup → connect → discover → run sequence is clearly ordered with a conditional checkpoint ("If a Llama AI connection exists, note its connectionId"); matches the 4 anchor and not a 5 because there are no explicit validate-then-proceed feedback loops.	4 / 5
Progressive Disclosure	The body is organized into clearly headed sections (Overview, Working with Llama AI, Popular actions, Best practices) with no bundle files present and no nested references needed; matches the 4 anchor for good structure with minor organization gaps and not a 5 because, at over 50 lines, some reference material (e.g. the proxy flag table or best practices) could be split out.	4 / 5
	Total	16 / 20 Passed

Description

62%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 states both what it does and when to use it and is clearly tied to the Llama AI platform, but it is thin on concrete actions and natural trigger terms. It names only 'Manage Organizations', which does not reflect the chat and image-generation capabilities the skill actually supports.

Suggestions

List concrete capabilities in the description, e.g. 'Create chat sessions and messages, generate images, and run Llama AI actions.' instead of the generic 'Manage Organizations'.

Add natural trigger phrases users would say, such as 'Use when the user wants to chat with Llama AI, generate images, or query Llama AI data.'

Replace the generic 'interact with Llama AI data' with specific triggers (chat, message, image generation) to improve both completeness and distinctiveness.

Dimension	Reasoning	Score
Specificity	Quotes: "Llama AI integration", "Manage Organizations", "interact with Llama AI data". It names the domain and one concrete action (Manage Organizations) plus a generic verb, matching the anchor for 1-2 concrete actions but not comprehensive coverage; not a 4 because actions are minimal and 'Manage Organizations' does not reflect the chat/image-generation capabilities actually offered.	3 / 5
Completeness	Quotes: "Llama AI integration. Manage Organizations." (what) and "Use when the user wants to interact with Llama AI data." (when). Both what and when are present and the when is explicit, matching the 4 anchor; not a 5 because the 'what' is thin and the 'when' lacks concrete trigger phrases like chat or image generation.	4 / 5
Trigger Term Quality	Quotes: "Llama AI", "Organizations", "interact with Llama AI data". "Llama AI" is a natural keyword, but the description misses common variations or synonyms (chat, messages, image generation, prompts); matches the 'some relevant keywords but missing variations' anchor and not a 4 due to thin natural-term coverage.	3 / 5
Distinctiveness Conflict Risk	Quotes: "Llama AI integration", "interact with Llama AI data". The named platform gives a clear niche with minimal conflict risk against non-Llama skills, matching the 4 anchor; not a 5 because the trigger phrasing ('interact with Llama AI data') is somewhat generic and could overlap with other Llama AI skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: membranedev/application-skills
Path: skills/llama-ai/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.