CtrlK
BlogDocsLog inGet started
Tessl Logo

setup-review-sandbox

One-time setup of the sandbox prerequisites used by the reproduce-issue skill and the reproduce-verifier agent — Docker, the isolation runtime (gVisor on Linux / Colima on macOS), healthy container networking, and the nx-review-sandbox toolchain image (built from the repo's mise.toml). Idempotent; re-run any time to verify or repair. Use when the user says "set up the review sandbox", "install the sandbox prereqs", "build the sandbox image", or a reproduce-issue preflight reports something MISSING.

79

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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 tight, executable setup runbook with explicit validation checkpoints and error-recovery feedback loops. It assumes Claude's competence and confines prose to genuinely non-obvious gotchas, scoring at the top of every dimension.

DimensionReasoningScore

Conciseness

Lean and command-driven throughout; inline prose is limited to non-obvious gotchas (e.g., 'do NOT pass . … which would ship the whole monorepo', 'a login shell resets PATH, dropping the mise dirs') that Claude would not already know, so every token earns its place.

3 / 3

Actionability

Every step is fully executable, copy-paste bash with concrete flags and paths (docker info checks, apt-get runsc install, docker build with minimal context, smoke-test one-liner), not pseudocode or abstract direction.

3 / 3

Workflow Clarity

A clearly numbered 1–5 sequence with explicit OK/MISSING validation checkpoints at each step and feedback loops for error recovery (veth BTF mismatch → reboot then persist via modules-load.d; re-check runtime after install).

3 / 3

Progressive Disclosure

Single-purpose, well-organized into five clearly headed sections with no nested or multi-level file references; no external references are needed, matching the well-organized-sections path to the top anchor.

3 / 3

Total

12

/

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 third-person, specific, and complete with an explicit 'Use when' trigger clause. It names concrete components and natural trigger phrasings, hitting the top anchor on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete prerequisites — 'Docker, the isolation runtime (gVisor on Linux / Colima on macOS), healthy container networking, and the nx-review-sandbox toolchain image (built from the repo's mise.toml)' — naming specific actions and components rather than vague language.

3 / 3

Completeness

Clearly answers both what (one-time setup of named sandbox prerequisites) and when (an explicit 'Use when...' clause with several trigger phrasings), satisfying the highest anchor.

3 / 3

Trigger Term Quality

Explicit natural-language triggers users would say: "set up the review sandbox", "install the sandbox prereqs", "build the sandbox image", plus a preflight MISSING condition — good coverage of common phrasings.

3 / 3

Distinctiveness Conflict Risk

A clearly bounded niche (sandbox prerequisites for the reproduce-issue skill / reproduce-verifier agent) with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
nrwl/nx
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.