hosted-agents
This skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed execution", "implement multiplayer agent", or mentions background agents, sandboxed VMs, agent infrastructure, Modal sandboxes, self-spawning agents, or remote coding environments.
62
53%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/hosted-agents/SKILL.mdQuality
Discovery
37%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is fundamentally incomplete - it functions as a trigger-term list rather than a skill description. While it excels at providing natural keywords users might say, it completely fails to explain what the skill actually does, making it impossible for Claude to understand the skill's capabilities or for users to know what to expect.
Suggestions
Add a clear 'what' statement at the beginning describing concrete actions, e.g., 'Creates and configures background coding agents with sandboxed VM execution using Modal infrastructure.'
Restructure to lead with capabilities before trigger conditions: '[What it does]. Use when [trigger conditions].'
Include specific deliverables or outcomes the skill produces, such as 'deploys self-spawning agents', 'configures Modal sandbox environments', or 'sets up remote execution pipelines'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions - it only lists trigger phrases without explaining what the skill actually does. There are no verbs describing capabilities like 'creates', 'configures', or 'deploys'. | 1 / 3 |
Completeness | The description only addresses 'when' (trigger conditions) but completely omits 'what' - there is no explanation of what capabilities or actions this skill provides. The 'what' is entirely missing. | 1 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'build background agent', 'create hosted coding agent', 'set up sandboxed execution', 'Modal sandboxes', 'remote coding environments'. These are specific and varied. | 3 / 3 |
Distinctiveness Conflict Risk | The trigger terms are fairly specific to background/sandboxed agent infrastructure, but without knowing what the skill does, it could overlap with general agent-building or infrastructure skills. Terms like 'agent infrastructure' are somewhat broad. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured architectural skill that excels at workflow clarity and progressive disclosure. The main weakness is the lack of executable code examples - the skill describes patterns and approaches thoroughly but doesn't provide copy-paste ready implementations. Some explanatory content could be trimmed to improve token efficiency.
Suggestions
Add executable code examples for key operations like git config setup, snapshot creation, and warm pool management
Remove explanatory phrases like 'The critical insight is...' and 'because this prevents the agent from hallucinating' - state the guidance directly
Include a concrete code snippet for the sandbox-to-API event flow showing actual implementation patterns
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some explanatory content that could be tightened. Phrases like 'The critical insight is...' and 'because this prevents the agent from hallucinating about its own capabilities -- an underrated failure mode' add context Claude doesn't need. However, most content is substantive and actionable. | 2 / 3 |
Actionability | The skill provides good conceptual guidance and architectural patterns but lacks executable code examples. Instructions like 'Set git config user.name and user.email' and 'Use WebSocket connections with hibernation APIs' describe what to do without showing how. No copy-paste ready code snippets are provided. | 2 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation points. The 'Sandbox-to-API Flow' section provides numbered steps, and the Gotchas section addresses failure modes with recovery strategies. The image registry pattern and snapshot/restore workflows are well-structured with clear checkpoints. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear section hierarchy. References are one level deep and clearly signaled with 'Read when:' guidance. The skill appropriately links to related skills and external resources without burying critical information in nested files. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Commit
3ab8c94
- Reviewed
Table of Contents
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.