hosted-agents

This skill should be used when designing hosted or background agent infrastructure: sandboxed execution, remote coding environments, warm pools, session persistence, multiplayer collaboration, self-spawning agents, or Modal-style sandboxes.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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 actionable with strong progressive disclosure, but it is somewhat verbose with repeated motivations and lacks explicit validation/feedback checkpoints in its risky workflows, which caps workflow clarity and conciseness at the mid level.

Suggestions

Remove the redundant restatement of the local-execution-limits / three-layer motivation between the opening paragraph and the 'Core Concepts' section to tighten conciseness.

Add explicit validation/feedback checkpoints to destructive or irreversible workflows, e.g. 'verify token validity before PR creation' and 'confirm snapshot succeeded before sandbox termination' as numbered validate-then-proceed steps.

Tighten the 'because' justification clauses scattered through Detailed Topics; keep the directive, drop the repeated rationale where Claude can infer it.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly earns its place, but restates concepts across sections (the intro and 'Core Concepts' both re-explain the same three-layers / local-limits motivation) and leans on 'because' justifications that pad length. It is mostly efficient but could be tightened, matching the 'mostly efficient but includes some unnecessary explanation' anchor rather than the lean top anchor.	2 / 3
Actionability	Concrete, specific guidance throughout: image rebuild 'every 30 minutes', 'default 4 hours' timeout, explicit git config steps, and a numbered sandbox-to-API flow (1-4). As an instruction/design skill the absence of inline executable code is not penalized because the guidance is specific and copy-applicable.	3 / 3
Workflow Clarity	Multi-step processes are sequenced (numbered sandbox-to-API flow, ordered example lifecycle, explicit design checklist), but validation checkpoints are largely missing for risky/irreversible operations (PR creation, sandbox teardown, token-sensitive steps). Per the rubric, missing validation in destructive/batch operations caps this at 2 rather than 3.	2 / 3
Progressive Disclosure	Clear overview with a one-level-deep, well-signaled reference to ./references/infrastructure-patterns.md (verified real file) plus external links and related skills, each tagged with 'Read when:' guidance. Content is appropriately split and easy to navigate.	3 / 3
	Total	10 / 12 Passed

Description

100%

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 is strong: it explicitly states what the skill does, when to use it, lists concrete capabilities, and uses distinctive niche triggers. It does not fall into the missing-trigger cap because an explicit 'This skill should be used when...' clause is present and uses third person.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete capabilities/domains: 'sandboxed execution, remote coding environments, warm pools, session persistence, multiplayer collaboration, self-spawning agents, or Modal-style sandboxes.' This matches the 'Lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('designing hosted or background agent infrastructure') and when ('This skill should be used when...'), with an explicit trigger clause matching the top anchor.	3 / 3
Trigger Term Quality	Natural domain terms a target user would say are well covered ('hosted or background agent infrastructure', 'warm pools', 'sandboxed execution', 'Modal-style sandboxes', 'multiplayer collaboration'). It is not merely technical jargon; these are the terms practitioners use when reaching for this skill.	3 / 3
Distinctiveness Conflict Risk	Clear niche with distinct, named triggers (warm pools, Modal-style sandboxes, session persistence, self-spawning agents) making it unlikely to fire for adjacent skills.	3 / 3
	Total	12 / 12 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: muratcankoylan/Agent-Skills-for-Context-Engineering
Commit: c578e85

Reviewed: 7 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.