Name: metatextai-inference-api
Rating: 54.400000000000006 (1 reviews)
Author: membranedev

metatextai-inference-api

Metatext.AI Inference API integration. Manage data, records, and automate workflows. Use when the user wants to interact with Metatext.AI Inference API data.

Quality

61%

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/metatextai-inference-api/SKILL.md

Quality

Content

61%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 a concrete, mostly lean CLI usage guide with executable commands and a useful connection-state workflow. It is held back by an unnecessary intro overview, confusing step numbering, and missing validation on the action-run path.

Suggestions

Trim the opening overview paragraph about what the API is and who uses it; assume Claude's competence and lead directly with the Membrane CLI workflow.

Fix the step numbering (define an explicit 'Step 2' and renumber '1b') so the connection workflow reads as a clean sequence.

Add a validation/check step after `membrane action run` (e.g., inspect the `output` field and handle non-zero/error states) so the run workflow has a feedback checkpoint.

Dimension	Reasoning	Score
Conciseness	The bulk is lean CLI commands, but the opening overview paragraph explaining what the API is and who uses it, plus vague filler like 'Use action names and parameters as needed', is unnecessary explanation Claude could infer.	3 / 5
Actionability	Concrete, executable commands are provided throughout (install, login, connection ensure/get, action list/run, proxy) with a flags reference table; minor gaps are unfilled placeholders and a thin, redundant 'Popular actions' section.	4 / 5
Workflow Clarity	A connect-then-poll-then-run sequence exists with a polling feedback loop, but step numbering is confusing ('skip to Step 2' with no Step 2, an out-of-order '1b') and the action-run path has no validation or error-handling checkpoint.	3 / 5
Progressive Disclosure	No bundle files exist and the single SKILL.md is organized into clearheaded sections with no nested references; minor organization gaps (the numbering inconsistency and the redundant Popular actions block) keep it from a 5.	4 / 5
	Total	14 / 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 follows the recommended what-plus-when structure with an explicit trigger clause and a clearly named niche. Its main weakness is generic, non-concrete action language and limited trigger-term variety.

Suggestions

Replace generic verbs with concrete API operations (e.g., 'Run inference jobs, list and manage models, submit text generation/summarization/translation requests') to lift specificity.

Expand the 'Use when...' clause with natural trigger phrases users would actually say (e.g., 'Use when the user wants to run Metatext inference, generate or summarize text via Metatext, or manage Metatext models').

Add file-extension or endpoint-style cues if applicable to widen trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Metatext.AI Inference API integration') and lists several actions ('Manage data, records, and automate workflows'), but the verbs are generic rather than concrete API-specific operations.	3 / 5
Completeness	It answers both 'what' (integration; manage data/records/workflows) and 'when' with an explicit 'Use when...' clause, but the 'what' is generic and the trigger is a single phrase rather than comprehensive.	4 / 5
Trigger Term Quality	The trigger is largely the product name restated ('interact with Metatext.AI Inference API data'); relevant keywords are present but natural synonyms or variations users might say are missing.	3 / 5
Distinctiveness Conflict Risk	The named API establishes a clear, distinct niche with minimal conflict risk, though the generic action verbs ('manage data, records') leave some overlap with broader data skills.	4 / 5
	Total	14 / 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/metatextai-inference-api/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.