CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review

Review changed code for correctness, security, code quality, and performance. Use when the user asks to review code changes, a PR, or specific files. Invoke with `/review`, `/review <pr-number>`, `/review <file-path>`, `/review <pr-number> --comment` to post inline comments on the PR, `/review --fix` to apply the findings to your working tree, or `/review <pr-number> --resume` to continue an interrupted review of that PR at an unmoved head (a re-review after new commits is a plain `/review <pr-number>`). Add `--effort low|medium|high` to trade depth for speed (defaults to high for PRs, medium for local changes). Add `--topology minimal` to run the single-pass A/B comparison arm instead of the pipeline.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/core/src/skills/bundled/review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 skill body is supremely actionable and rigorously gated, but it is buried in one of the most verbose skill documents possible — incident narratives, historical justifications, and edge-case essays inflate it to ~100K tokens, defeating the token budget its own design philosophy implies. The reference-file gating pattern that works for posting/persistence/aone should have been applied to most of the remaining body.

Suggestions

Move the per-incident rationale out of SKILL.md entirely: every "(measured; DESIGN.md — …)" narrative and dated war story (PR #9729, #8368, the 22-minute serial verification) already lives in DESIGN.md for maintainers — keep at most a one-line pointer, cutting a large fraction of the 416KB body.

Apply the existing posting/persistence/aone reference pattern to the remaining monolith: split Step 1's argument-parsing and prose-resolution rules, Step 4's witness/capability catalog (probe, base-tree, impact sweep, isolation-by-elimination), and Step 5's reverse-audit scheduling into gated one-level-deep reference files loaded only when the run's verdict needs them.

Convert multi-thousand-character single paragraphs into short imperative rules with a one-line rationale (or a bullet list); executable rules like the cleanup prefix-collision contract are currently buried mid-paragraph in narrative, which is what makes an otherwise clear 9-step pipeline hard to trace.

DimensionReasoningScore

Conciseness

The body is ~416KB (~1234 lines averaging 336 characters, with single paragraphs over 7,000 characters) — a context-window-consuming monolith. Nearly every rule carries an inline incident narrative ("measured; DESIGN.md — The transcribed argument file", "measured on PR #9729") and multi-clause historical justification, i.e. heavily padded, and it explains at length concepts a competent model knows (heredoc termination, POSIX parameter expansion, why git diff misses untracked files). This matches the severely-verbose/heavily-padded anchor, not merely "several padded sections".

1 / 5

Actionability

Guidance is fully executable throughout: exact copy-paste commands ("${QWEN_CODE_CLI:-qwen}" review parse-args --stdin --out .qwen/tmp/qwen-review-parse-args.json), exact file paths, exit-code semantics (0/3/4/5/6/7 with prescribed responses), explicit JSON verdict field meanings, and concrete output templates (the "Review complete: <target> — <disposition>" contract). This matches the copy-paste-ready top anchor.

5 / 5

Workflow Clarity

The 9-step sequence is clearly ordered with deterministic gates, explicit validation (verifier shards, convergence pairs, exit-code-driven fail-closed handling) and error-recovery feedback loops — well above the missing-checkpoint anchors. It falls short of the top anchor because at least five orthogonal axes (effort level × topology × platform × review profile × target type) are interwoven through continuous 3,000–7,000-character prose with no scannable checklists or per-path summaries, making any single execution path genuinely hard to trace.

4 / 5

Progressive Disclosure

The three existing references (references/posting.md, references/persistence.md, references/aone.md) are real files, one level deep, and exceptionally well-gated ("Load it when, and only when, posting is live for this run") — better signaling than the 3 anchor describes. But the overwhelming bulk of conditional detail (Step 1's ~330 lines of parsing/prose-resolution rules, Step 4's witness/capability catalog, Step 5's audit scheduling) is inlined in a monolithic body that dwarfs the reference files (416KB vs 111KB), so content that clearly belongs in separate files is inline.

3 / 5

Total

13

/

20

Passed

Description

88%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: concrete actions, explicit when-to-use guidance, and distinctive invocation syntax, with only minor gaps in synonym coverage and separation from neighboring review-oriented skills. The flag documentation adds specificity without becoming vague fluff, though some of it duplicates the argument-hint field.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions with comprehensive coverage: "Review changed code for correctness, security, code quality, and performance", "post inline comments on the PR", "apply the findings to your working tree", and "continue an interrupted review of that PR at an unmoved head", plus flag-level behaviors. It matches the anchor for multiple specific concrete actions; nothing is generic or abstract.

5 / 5

Completeness

It explicitly answers both what ("Review changed code for correctness, security, code quality, and performance") and when ("Use when the user asks to review code changes, a PR, or specific files") with concrete trigger phrases, plus concrete invocation forms. This matches the top anchor exactly.

5 / 5

Trigger Term Quality

"Use when the user asks to review code changes, a PR, or specific files" provides good natural keyword coverage ("review code changes", "a PR", "specific files"), but common phrasings like "code review", "pull request" spelled out, or "review my diff/changes" are absent. It sits between good (4) and comprehensive synonym coverage (5), closer to 4.

4 / 5

Distinctiveness Conflict Risk

The invocation syntax (/review with --comment/--fix/--resume/--effort/--topology) and the resume/topology semantics carve a clear niche, but the core trigger phrases ("review code changes", "review a PR") are exactly what any competing code-review skill would also claim, leaving minor overlap risk with closely related skills. Not the generic conflict of lower anchors, but not minimal-risk either.

4 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1235 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

QwenLM/qwen-code

Path

packages/core/src/skills/bundled/review/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.