CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/_a0_connector/skills/host-code-execution/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 a well-structured, lean reference that gives concrete runtime parameters and clear failure-handling branches, scoring well across conciseness, actionability, and workflow clarity. The only notable gaps are minor redundancy on the disabled-execution point and a few unnamed CLI flags/commands.

Suggestions

Name the exact CLI flag or command for enabling remote execution instead of the generic 'the required CLI toggle' to close the actionability gap.

Consolidate the disabled-execution guidance so it appears once, removing the mild redundancy between Access Modes and Failure Handling.

DimensionReasoningScore

Conciseness

The body is lean, avoids explaining basic concepts (shells, runtimes, Docker), and assumes Claude's competence, but there is minor redundancy between the Access Modes and Failure Handling sections on the disabled-execution case that could be consolidated, keeping it just below the leanest anchor.

4 / 5

Actionability

Concrete parameter values ('runtime=terminal/python/nodejs/output/reset', 'reset: true', F3) and a specific list of shell launchers to avoid make the guidance mostly executable, but references like 'the required CLI toggle' and 'enable remote execution in the CLI' leave the exact flag or command unspecified, a minor gap.

4 / 5

Workflow Clarity

The Failure Handling section forms a clear conditional sequence (no CLI -> disabled -> access blocked -> timeout/disconnect) with a poll-once checkpoint and a reconnect feedback action, and the simple routing action is unambiguous; it lacks a full validate->fix->retry loop, so it does not reach the top anchor.

4 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references, and is cleanly organized into well-labeled sections (Boundary, Access Modes, Runtimes, Failure Handling), meeting the simple-skill exception for well-organized structure without bundle files.

5 / 5

Total

17

/

20

Passed

Description

78%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 is strong: it pairs an explicit 'what' with a concrete 'Use when...' trigger clause and active disambiguation, yielding high completeness and distinctiveness. Its main weakness is specificity, since the action verb 'Guide safe use' is generic and no enumerated concrete capabilities are listed.

Suggestions

Replace the generic verb 'Guide safe use' with concrete capabilities the skill performs, e.g. 'Run shell, Python, and Node snippets on the A0 CLI host via code_execution_remote'.

Add a couple of natural synonyms to the trigger clause (e.g. 'my machine', 'run locally', 'on the host') to broaden trigger coverage.

DimensionReasoningScore

Specificity

Names the domain precisely ('code_execution_remote for shell-backed execution on the connected A0 CLI host') plus one concrete action, but the wrapper verb 'Guide safe use' is generic and no multi-action list is given, fitting the domain-plus-1-2-actions anchor rather than the minimal-action (2) or several-actions (4) anchors.

3 / 5

Completeness

It explicitly answers both 'what' ('Guide safe use of code_execution_remote for shell-backed execution on the connected A0 CLI host') and 'when' with an explicit 'Use when...' clause and concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

The 'Use when...' clause surfaces natural phrases users say ('their computer', 'local terminal', 'CLI host', 'remote shell', 'not Docker', 'host-side Python/Node/terminal commands') with good disambiguation, but a few natural synonyms (e.g. 'my machine', 'run locally') are missing, so it does not reach comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

A clear niche is staked via the named tool and host plus the 'not Docker' disambiguation, but broad trigger phrases like 'their computer' and 'local terminal' create minor overlap risk with other local-execution skills, keeping it just below minimal-conflict.

4 / 5

Total

16

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
agent0ai/agent-zero
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.