Name: chef
Rating: 54.400000000000006 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

chef

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

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/chef/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 content is highly actionable with concrete Membrane CLI commands and a solid connection-state workflow, but it is held back by an unnecessary Chef intro, some marketing prose, a broken "Step 2" reference, and missing verification for destructive action/proxy operations. Adding validation checkpoints and trimming boilerplate would lift it.

Suggestions

Add a verification step after running actions and before destructive proxy requests (e.g. inspect the `output` field, confirm affected ids, or dry-run GET before mutating calls) so the workflow clears the validation cap.

Fix the broken "skip to Step 2" cross-reference by labeling the action search/run sections as Step 2 or removing the dangling reference.

Remove the Chef definition paragraph and Membrane marketing lines, and consolidate the duplicated action-list command in "Searching for actions" and "Popular actions" into one place.

Dimension	Reasoning	Score
Conciseness	The body is mostly command-driven and efficient, but it opens by explaining what Chef is ("Chef is an automation platform that transforms infrastructure into code..."), includes marketing-flavored lines ("so you can focus on the integration logic rather than auth plumbing", "This will burn less tokens"), and repeats the action-list command in both "Searching for actions" and "Popular actions".	3 / 5
Actionability	It provides concrete, copy-paste-ready commands throughout (install, login, connection ensure, action list/run, request) with realistic flags and a proxy flag table, with only minor gaps such as no fully worked end-to-end example with a concrete actionId.	4 / 5
Workflow Clarity	The connect flow has a real sequence with state polling and error handling (READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), but the "skip to Step 2" reference points to a non-existent Step 2, and running actions plus proxy requests (POST/PUT/DELETE) lack result verification — the rubric caps destructive/batch workflows without validation at 3.	3 / 5
Progressive Disclosure	There are no bundle files; content lives in a single SKILL.md with clear section headers (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices) and no nested references, giving good organization with minor gaps like the thin/redundant "Popular actions" section.	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 correctly pairs a what statement with an explicit "Use when" trigger and is anchored to a distinct platform, but its actions and trigger terms are generic and lack synonyms. Tightening the actions to concrete Chef operations and broadening trigger phrasing would raise it.

Suggestions

Replace generic verbs ("Manage data, records, and automate workflows") with concrete Chef operations such as managing nodes, cookbooks, recipes, roles, and run-lists.

Expand the trigger clause with natural synonyms users say, e.g. "Use when the user wants to manage Chef nodes, run cookbooks/recipes, or automate infrastructure with Chef."

Avoid the broad term "Chef data" which overlaps with general data skills; reference Chef-specific artifacts (nodes, cookbooks, run-lists) to improve distinctiveness.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Chef domain with a few actions, but the actions are generic ("manage data", "records") rather than concrete, matching the anchor for domain plus 1-2 actions that are not comprehensive.	3 / 5
Completeness	It states both a what ("Manage data, records, and automate workflows") and an explicit when ("Use when the user wants to interact with Chef data"), but the when is somewhat generic rather than listing concrete triggers, matching the anchor where both are present but when could be more specific.	4 / 5
Trigger Term Quality	The trigger "Use when the user wants to interact with Chef data" surfaces the main keyword "Chef" and one natural phrase, but it lacks synonyms or common variations, fitting the anchor for some relevant keywords with missing variations.	3 / 5
Distinctiveness Conflict Risk	"Chef integration" targets a specific named platform with a distinct trigger, giving a clear niche, though the generic "manage data, records" wording leaves minor overlap risk with adjacent 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/chef/SKILL.md
Commit: f484c82

Reviewed: 3 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.