CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-pr

Deep, findings-first review of one nrwl/nx pull request from a PR reference or associated Linear task, including drafts. Uses four fixed Sol/xhigh lanes, exact merge-base scope, inert snapshots, optional sandboxed checks, and produces one private record holding a postable review draft, without posting it.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

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.

An exceptionally actionable, well-sequenced orchestration procedure with real validation checkpoints and error-recovery loops at every phase, and a clean two-file reference split. Its main weakness is density: ~450 lines of repetitive legalistic prose where several trust-boundary and private-material rules are restated multiple times and could be consolidated.

Suggestions

Consolidate the repeated untrusted-code and sandbox-ownership rules (currently stated in the Trust boundary, section 4, and section 5) into a single authoritative statement, cross-referencing it from later sections.

Move the detailed adjudication heuristics and close-without-merge evidence rules into references/review-policy.md, keeping the body focused on orchestration order and command sequences.

Mention scripts/snapshot.mjs where snapshot behavior is described (or note that reviewctl.mjs invokes it) so every bundle file is accounted for in the body.

DimensionReasoningScore

Conciseness

The body never explains concepts Claude already knows and nearly every sentence is task-specific policy, but it is ~450 lines of dense, legalistic prose with noticeable repetition: untrusted-code execution rules appear in the Trust boundary, the section 4 dispatch instructions, and twice in section 5; private-material handling rules in section 2 ("never quote, paraphrase, attribute, or allude to private content") reappear in section 6; and sandbox ownership rules are stated in both the Trust boundary and section 5. This is more than the "minor instances" of the 4 anchor — the document could be meaningfully tightened by deduplication — but there is no generic padding, so it sits above the 2 anchor.

3 / 5

Actionability

Guidance is fully executable: exact copy-paste commands with argument placeholders for every phase ("node .agents/skills/review-pr/scripts/reviewctl.mjs begin --pr <PR_NUMBER_OR_URL>", verify-evidence, sandbox-up, finalize, abort, polygraph-context), the sandbox exec pattern "tools/review-sandbox/sandbox exec <SANDBOX> -- bash -s < <HEAD_SCRIPT>", and a concrete dispatch input block naming every artifact path. Common cases (success, retry, abort, recovery, denied approval) are each covered with specific steps.

5 / 5

Workflow Clarity

The seven numbered sections give a clear sequence (Preflight → Freeze → Close-check → Charter → Dispatch → Runtime checks → Adjudicate → Finalize/Abort), and validation checkpoints with feedback loops are pervasive: verify-evidence after each lane with one correction request then abort on retry failure, finalize failure handled by "correct the input or environment and rerun", an explicit cybersecurity-interruption recovery procedure, and a defined abort path with a reason file. This matches the 5 anchor (explicit validation, error-recovery feedback loops) and clearly exceeds the 4 anchor.

5 / 5

Progressive Disclosure

The bundle structure is good: both references (review-policy.md, output-contract.md) are real files, clearly signaled with an imperative read-first instruction, and exactly one level deep; scripts are invoked by path throughout. It falls short of the 5 anchor because the body itself retains substantial inline policy detail — adjudication rules, close-without-merge heuristics, sandbox lifecycle minutiae — that could partly live in the policy reference, and scripts/snapshot.mjs is present in the bundle but never referenced from the body, leaving a minor organization gap.

4 / 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.

A strong, niche-scoped description that clearly conveys what the skill does and what inputs trigger it, with concrete outcomes and boundaries (draft included, never posted). Its main weaknesses are internal jargon ("Sol/xhigh lanes", "inert snapshots") that a user cannot interpret, and the absence of an explicit "Use when..." trigger phrase.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to review, vet, or sanity-check a specific nrwl/nx pull request (by URL, number, or linked Linear task), including draft PRs."

Replace or gloss internal jargon such as "four fixed Sol/xhigh lanes" and "inert snapshots" with user-meaningful capability language (e.g. "four parallel specialized reviewer agents" and "read-only code snapshots").

Include natural synonym phrases users would say — "code review", "PR review", "review this nx PR" — to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description names several concrete actions — "Deep, findings-first review of one nrwl/nx pull request", "produces one private record holding a postable review draft, without posting it" — plus concrete mechanisms (merge-base scope, sandboxed checks). It falls short of the 5 anchor because terms like "four fixed Sol/xhigh lanes" and "inert snapshots" are internal jargon that communicate implementation detail rather than comprehensively covering user-meaningful capabilities.

4 / 5

Completeness

The "what" is clear and detailed (findings-first review of one nrwl/nx PR producing a private record with a postable draft, never posted), and a "when" exists through explicit input triggers — "from a PR reference or associated Linear task" — which counts as equivalent trigger guidance, avoiding the 3-cap for a missing 'Use when' clause. It stays at 4 rather than 5 because the when-conditions are implicit in the input spec rather than stated as explicit concrete trigger phrases like "Use when the user asks to review an nx PR".

4 / 5

Trigger Term Quality

Natural trigger terms are present: "pull request", "PR reference", "Linear task", "including drafts" — phrases a user of this workflow would plausibly say. A few common variations are missing, e.g. "code review" as a phrase and the bare repo name "nx", so it does not reach the comprehensive synonym coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche — scoped to "one nrwl/nx pull request", Linear-task association, draft handling, and a specific produce-a-draft-without-posting outcome — so it is highly distinguishable from generic code-review or PR skills with minimal conflict risk. It clearly matches the 5 anchor ("clear niche with distinct triggers") and is more specific than the 4 anchor's "minor overlap risk with closely related skills".

5 / 5

Total

17

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

nrwl/nx

Path

.agents/skills/review-pr/SKILL.md

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.