cloud-claw-launch-agent

Use this skill when the user wants to launch a new AltClaw, OpenClaw, PicoClaw, or Ottie deployment through Cloud Claw. Covers the same user-facing fields and constraints exposed in the Cloud Claw UI, using the local altllm cloud-claw-* commands. Do NOT use for post-launch lifecycle tasks like start/stop/delete/logs; use cloud-claw-manage-vm.

Quality

83%

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

Quality

Content

80%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 concise and well-structured with good progressive disclosure, delegating examples to a real reference file. Its main weakness is workflow clarity: the deploy flow is presented as rules rather than an explicit sequenced workflow with validation checkpoints.

Suggestions

Add a short numbered launch workflow (e.g., 1. run preflight via ../_shared/cloud-claw-preflight.md, 2. deploy with altllm cloud-claw-deploy, 3. verify the success response / surface failure codes) so the sequence and checkpoints are explicit in the body.

Inline at least one complete altllm cloud-claw-deploy invocation (with flags) in the body so the core path is copy-paste ready without opening the reference.

Add an explicit verify step pointing to the response/failure-code section in references/cli-reference.md to close the validation gap for the deploy operation.

Dimension	Reasoning	Score
Conciseness	Lean table plus bullet rules; it assumes Claude's competence and avoids explaining what Cloud Claw or Telegram bots are, with every line earning its place.	5 / 5
Actionability	Provides the concrete command ('altllm cloud-claw-deploy'), name regex, agentType enum, env-var and model constraints, but defers the full copy-paste invocations to the reference file, leaving a minor gap in the body itself.	4 / 5
Workflow Clarity	Content is organized as rules rather than a numbered preflight -> deploy -> verify sequence, and the preflight checkpoint is only implicit ('Before using this skill, read ...'), with validation delegated to external shared files.	3 / 5
Progressive Disclosure	Clear overview with a well-signaled one-level-deep reference (references/cli-reference.md, verified present) holding payload examples and responses, with the body appropriately limited to rules and the agent-type table.	5 / 5
	Total	17 / 20 Passed

Description

87%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.

A strong description: it states the capability concretely, gives clear positive and negative trigger guidance, and disambiguates from the sibling manage-vm skill. Only minor gains are available from adding natural synonyms like 'deploy'.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete mechanism ('launch a new ... deployment through Cloud Claw', 'using the local altllm cloud-claw-* commands') plus the agent types and UI fields/constraints, but centers on a single capability rather than multiple distinct actions, so it sits just below the comprehensive anchor.	4 / 5
Completeness	Explicitly answers what ('launch a new ... deployment ... using the local altllm cloud-claw-* commands' covering UI fields/constraints) and when ('Use this skill when the user wants to launch ...'), with concrete trigger phrases and a negative boundary.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'launch a new ... deployment' and 'Cloud Claw' alongside named agent types (OpenClaw, PicoClaw, Ottie) give good coverage, though a few common synonyms such as 'deploy' or 'spin up' are absent.	4 / 5
Distinctiveness Conflict Risk	The explicit anti-trigger ('Do NOT use for post-launch lifecycle tasks like start/stop/delete/logs; use cloud-claw-manage-vm') carves a clear niche of new launches with minimal overlap against the sibling management skill.	5 / 5
	Total	18 / 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: internet-court/internet-court-skill
Path: vendored/altlayer/cloud-claw-launch-agent/SKILL.md
Commit: fa89195

Reviewed: 4 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.