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

replicated

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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/replicated/SKILL.md

Quality

Content

67%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 delivers strong, executable CLI guidance with a well-validated connection workflow and clean sectioning. Weaknesses are minor prose padding, placeholder-only command examples, and a broken 'Step 2' reference with no post-action verification.

Suggestions

Trim inferable prose such as the Replicated platform explainer and the 'auth plumbing' aside so every line earns its place.

Fix the dangling 'skip to Step 2' reference by labeling the numbered steps or removing the cross-reference.

Add a verification/check step after `membrane action run` and proxy requests, since these can be destructive or batch operations.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient executable commands, but includes unnecessary prose such as the opening paragraph explaining what Replicated is and 'so you can focus on the integration logic rather than auth plumbing', fitting the 'mostly efficient but includes some unnecessary explanation' anchor; it is not 4 because several sentences pad concepts Claude can infer.	3 / 5
Actionability	Concrete, copy-paste-ready bash commands cover install, login, connection, action search/run, and proxying, matching 'mostly executable guidance with minor gaps'; it is not 5 because commands rely on placeholders (CONNECTION_ID, agentType, QUERY, actionId) the agent must substitute without a worked end-to-end example.	4 / 5
Workflow Clarity	The connection workflow is clearly sequenced with explicit state-feedback checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a re-poll loop, matching 'clear sequence with most checkpoints present'; it is not 5 because the 'skip to Step 2' reference points to an unlabeled step and running/proxy actions lack verification steps.	4 / 5
Progressive Disclosure	The ~140-line body is well organized into clear sections with no nested or buried references, matching 'good structure; most content appropriately placed'; it is not 5 because all content is inline with no one-level-deep reference files for the larger proxy-flag/API detail, and it exceeds the under-50-line simple-skill exception.	4 / 5
	Total	15 / 20 Passed

Description

57%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' with an explicit 'Use when' trigger tied to a distinct product niche, but its capability phrasing is generic rather than concrete. Tightening the action list and broadening trigger synonyms would raise it.

Suggestions

Replace generic verbs with concrete Replicated capabilities, e.g. 'Manage deployments, inspect release notes, and automate customer workflows' to lift specificity.

Add natural trigger variations users might say, such as 'on-premise delivery', 'application distribution', or 'kOTS/Replicated releases', to improve trigger term coverage.

Sharpen the 'when' clause with concrete triggers, e.g. 'Use when the user wants to deliver or manage on-premise applications via Replicated'.

Dimension	Reasoning	Score
Specificity	The verbs 'Manage data, records, and automate workflows' name the domain but the actions are generic rather than concrete, matching the 'names the domain but actions are minimal or generic' anchor; it does not reach 3 because no truly concrete capability (e.g. 'create deployments', 'inspect release notes') is listed.	2 / 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 Replicated data'), matching the anchor where both are present but the 'when' could be more specific; it is not 5 because the 'when' trigger is narrow and the 'what' is generic.	4 / 5
Trigger Term Quality	'Replicated' is the key natural brand term users would say, but the surrounding terms ('data', 'records', 'workflows') are generic and lack common variations or synonyms, fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Tying triggers to the specific product 'Replicated' gives it a clear niche with minimal conflict risk, but the generic 'manage data, records, automate workflows' phrasing leaves minor overlap with adjacent data-integration skills, so it sits at 4 rather than 5.	4 / 5
	Total	13 / 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/replicated/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.