host-code-execution

Guide safe use of code_execution_remote for shell-backed execution on the connected A0 CLI host. Use when the user asks for their computer, local terminal, CLI host, remote shell, not Docker, or host-side Python/Node/terminal commands.

Quality

87%

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

86%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.

An exemplarily lean, well-organized instruction skill: every bullet is tool-specific and actionable, and error paths map to concrete recovery steps. The only improvements are a sample tool invocation and naming the specific CLI toggle referenced in the disabled-execution path.

Suggestions

Include one concrete example tool call (e.g., a code_execution_remote invocation with runtime, session, and a command) to make the happy path copy-paste ready.

Name the exact CLI setting or menu item for enabling remote execution instead of 'the required CLI toggle', and clarify when to poll with runtime=output versus escalating to runtime=reset.

Dimension	Reasoning	Score
Conciseness	37 lines of dense, bullet-form, tool-specific guidance with zero padding and no explanation of concepts Claude already knows; every line (runtime values, session semantics, F3 toggle, PowerShell-on-Windows caveat) adds non-obvious knowledge.	5 / 5
Actionability	Concrete and executable throughout — exact runtime values, reset vs. reset:true semantics, input_remote with keyboard+session, and exact recovery instructions like 'switch local file access to Read&Write with F3' — with only minor gaps: no sample tool-call payload and 'explain the required CLI toggle' never names the actual toggle.	4 / 5
Workflow Clarity	Failure Handling gives an explicit condition-to-action map (disabled error, blocked runtimes, stuck session, timeout/disconnect) and the Runtimes section separates output, reset, and reset:true cases; minor gap in that the ordering between polling runtime=output and escalating to runtime=reset is implicit.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, no external references needed; four well-organized sections (Boundary, Access Modes, Runtimes, Failure Handling) with clear headers, satisfying the rubric's simple-skill exception for a full score.	5 / 5
	Total	18 / 20 Passed

Description

82%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 with an explicit 'Use when' trigger clause, concrete natural-language trigger terms, and clear disambiguation from Docker and server-side execution. The only weakness is that the 'what' states a single capability (guide safe use) rather than enumerating the concrete actions the skill supports.

Suggestions

Enumerate 2-3 concrete capabilities in the description (e.g., runs shell/Python/Node commands on the host, manages sessions, handles failures) to raise specificity beyond a single action.

Add common trigger synonyms such as 'my machine', 'local machine', or 'run on my computer' to broaden natural-term coverage.

Dimension	Reasoning	Score
Specificity	Names the tool ("code_execution_remote"), the mode ("shell-backed execution"), and the host ("connected A0 CLI host"), but describes only one action ("Guide safe use") rather than listing several concrete capabilities, matching the 'names domain and 1-2 concrete actions' anchor.	3 / 5
Completeness	Explicitly answers both what ("Guide safe use of code_execution_remote for shell-backed execution on the connected A0 CLI host") and when ("Use when the user asks for their computer, local terminal, CLI host, remote shell, not Docker...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrasing ("their computer", "local terminal", "remote shell", "not Docker", "host-side Python/Node/terminal commands") but misses common synonyms like "my machine", "run on my computer", or "shell access".	4 / 5
Distinctiveness Conflict Risk	Anchors on a unique tool name and host context, and explicitly disambiguates from Docker and server-side execution ("not Docker"), giving it a clear niche with minimal conflict risk.	5 / 5
	Total	17 / 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: agent0ai/agent-zero
Path: plugins/_a0_connector/skills/host-code-execution/SKILL.md
Commit: e3051fb

Reviewed: 10 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.