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.

72

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A thorough, executable setup runbook with strong validation checkpoints and error-recovery feedback loops across a clear 6-step sequence. It is slightly let down by a few trimmable narrative passages, an unset $RUNTIME placeholder in the smoke test, and a monolithic single-file structure.

Suggestions

Trim the narrative anecdote in step 4 ('went unnoticed for two weeks, costing ~25 minutes of package downloads') to a one-line factual rationale for not gating on an existence check; keep the rule, drop the story.

Make the step-5 smoke test fully copy-paste by replacing the $RUNTIME placeholder with an explicit Linux/macOS branch or a one-liner derived from `uname -s`, so no manual interpolation is required.

Move or shorten the step-6 disk-reclaim / pnpm-poisoning rationale — it is tangential to one-time setup and could live in a short Maintenance reference or be condensed to the two commands plus their safety guard.

DimensionReasoningScore

Conciseness

Mostly efficient and it assumes Claude's competence (no explaining what Docker/gVisor are), and the operational rationale is largely load-bearing, but a few passages are trimmable — e.g. the 'went unnoticed for two weeks, costing ~25 minutes' anecdote in step 4 and the tangential pnpm-poisoning discussion in step 6.

4 / 5

Actionability

Concrete, mostly copy-paste-ready commands throughout (docker info, docker run --rm --network none alpine true, the apt/gVisor block, bash tools/review-sandbox/build-image.sh), with minor gaps: the smoke test leaves $RUNTIME as an unset placeholder and the build delegates to an external script not shown inline.

4 / 5

Workflow Clarity

A clearly sequenced 6-step process where every step has an explicit OK/MISSING validation check, a dedicated smoke-test verification (step 5, 'Green when …'), and feedback loops for error recovery (re-check runsc; veth BTF mismatch → modprobe → reboot). Validation is present, so the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

Well-organized into six numbered, headed sections with no nested reference chain and no bundle files to navigate, but it is a single ~100-line monolithic file with all detail inlined and no overview/quickstart split, which is slightly above the simple-skill threshold.

4 / 5

Total

17

/

20

Passed

Description

100%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, third-person description that states concrete prerequisites, marks idempotency, and gives multiple natural trigger phrases including a preflight-failure case. It cleanly answers both 'what' and 'when' with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete prerequisites and actions — '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)' plus 'verify or repair' — giving comprehensive coverage of what the setup covers.

5 / 5

Completeness

Explicitly answers both what ('One-time setup of the sandbox prerequisites … Idempotent; re-run any time to verify or repair') and when ('Use when the user says …') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Provides several natural phrases a user would actually say — 'set up the review sandbox', 'install the sandbox prereqs', 'build the sandbox image' — plus the preflight 'reports something MISSING' trigger, covering the realistic invocation surface.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (review-sandbox prerequisites for the reproduce-issue skill / reproduce-verifier agent) with distinct, specific triggers, so overlap with other skills is minimal.

5 / 5

Total

20

/

20

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.