skill-code-review

Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-code-review/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with executable bash and clearly sequenced workflows backed by checklists, but it is verbose and monolithic — large script blocks are inlined and file references resolve to nothing in the bundle.

Suggestions

Move the stub-detection and PR-posting bash scripts into separate reference files under scripts/ or references/ and link to them from SKILL.md to improve progressive disclosure and reduce inline token weight.

Tighten or remove the 'MANDATORY COMPLIANCE — DO NOT SKIP' prohibition list, which largely restates behavior already implied by the pipeline description.

Verify referenced paths (agents/personas/code-reviewer.md, .claude/references/stub-detection.md, skills/blocks/codex-host-adapter.md) actually exist in the bundle, or drop the references.

Dimension	Reasoning	Score
Conciseness	The body runs ~290 lines with lengthy inline bash blocks (stub detection ~60 lines, PR posting) and a coercive 'MANDATORY COMPLIANCE' section that is partly padding; content is mostly task-relevant but could be tightened, matching the mostly-efficient-but-could-be-tighter anchor.	2 / 3
Actionability	Provides fully executable, copy-paste-ready bash throughout — orchestrate.sh invocations, git diff file selection, grep-based stub checks, and `gh pr comment` posting — meeting the anchor for concrete executable commands.	3 / 3
Workflow Clarity	Multi-step processes are clearly numbered and sequenced (Quick Mode grasp→tangle, Post-Review Steps 1–2, Stub Detection Steps 1–3) with checklists (blocking vs non-blocking issues, verification levels L1–L4) and an ask-first guard for outward PR posting.	3 / 3
Progressive Disclosure	Content is a single monolithic file with large inline bash blocks that belong in separate reference files, and its references point to non-existent bundle paths (no references/scripts/assets directories exist), so structure is present but content is not appropriately split.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and distinctive, clearly stating what the skill does, but its trigger guidance is vague — 'use for thorough quality and security analysis' describes rigor rather than concrete situations when to invoke it.

Suggestions

Replace the 'use for thorough quality and security analysis' clause with explicit natural triggers, e.g. 'Use when the user asks to review a pull request, audit code for security issues, or wants a multi-model code review.'

Add common trigger variations users actually say ('pull request', 'review this PR', 'security audit', 'vulnerabilities') to broaden trigger-term coverage.

Clarify the 'when' with a concrete scenario list so completeness reaches the explicit-trigger anchor.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'multi-AI code review', 'inline PR comments', 'quality and security analysis' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	The 'what' is clear, and a 'use for thorough quality and security analysis' clause exists, but it reads as a quality descriptor rather than a concrete trigger situation, leaving the 'when' only weakly specified (not the level-3 explicit trigger guidance).	2 / 3
Trigger Term Quality	Includes natural terms a user would say ('code review', 'PR comments', 'security analysis') but misses common variations such as 'pull request', 'review this PR', 'audit', or 'vulnerabilities', so coverage is not comprehensive.	2 / 3
Distinctiveness Conflict Risk	The 'multi-AI' synthesis framing combined with 'inline PR comments' carves a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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: nyldn/claude-octopus
Path: .claude/skills/skill-code-review/SKILL.md
Commit: 9f39f0c

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.