CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-code-review

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

57

Quality

66%

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

Fix and improve this skill with Tessl

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

Quality

Content

57%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 body is actionable and well-structured at the section level, but is verbose due to inlined scripts and templates, under-sequences its core multi-LLM pipeline, and over-relies on inline content that should live in reference files. Tightening and externalizing detail would lift conciseness and progressive_disclosure.

Suggestions

Move the full stub-detection bash loop and mock review-output template into a referenced file (e.g., references/stub-detection.md) and keep only a concise summary inline to improve conciseness and progressive_disclosure.

Add an explicit numbered sequence for the full multi-LLM review pipeline (grasp → ... → tangle → synthesis) with validation checkpoints, rather than only showing the Quick Mode subset.

Clearly distinguish internal skill-bundle references from external plugin paths (${HOME}/.claude-octopus/plugin/...) so navigation and file ownership are unambiguous.

DimensionReasoningScore

Conciseness

Task-specific and not over-explaining concepts, but the inlined multi-check stub-detection bash loop and full mock review-output template are substantial padding that could be trimmed or moved out.

3 / 5

Actionability

Provides concrete, largely copy-pasteable commands (orchestrate.sh invocations, git/gh stub-detection and PR-posting scripts) with only minor gaps around assumed env vars and partially-wired pipeline phases.

4 / 5

Workflow Clarity

Sub-processes (stub detection, PR posting) are clearly sequenced with validation and blocking gates, but the headline multi-LLM review pipeline itself is never laid out as an explicit checkpointed sequence despite the MANDATORY framing.

3 / 5

Progressive Disclosure

Has clear section headers and references, but large content (stub-detection bash, mock output) that belongs in separate files is inlined, and reference paths mix internal skill bundles with external plugin locations without clear signaling; no bundle files are actually present.

3 / 5

Total

13

/

20

Passed

Description

75%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 solid, third-person description that states concrete capabilities and an explicit use-for trigger, carving a reasonably distinct multi-AI review niche. It could reach 5 by adding more concrete trigger phrases and a more comprehensive action list.

Suggestions

Add concrete trigger phrases users naturally say (e.g., "Use when the user asks to check a PR, audit code for vulnerabilities, or review staged changes") to lift completeness and trigger_term_quality.

Expand the action list to mention architecture/performance/TDD review explicitly for comprehensive coverage.

Include common synonyms ("audit", "sanity check", "review staged changes") to broaden trigger_term_quality beyond "code review".

DimensionReasoningScore

Specificity

Names the domain (multi-AI code review) and several concrete actions (inline PR comments, quality analysis, security analysis), with only minor gaps in coverage compared to the body's fuller capability list.

4 / 5

Completeness

Has both a clear "what" (multi-AI code review with inline PR comments) and an explicit "use for" clause, though the "when" is broad rather than concrete trigger phrases.

4 / 5

Trigger Term Quality

Includes natural phrases users would say ("code review", "PR comments", "security analysis"), but misses common synonyms and variations like "check this PR" or "audit" that appear only in the body.

4 / 5

Distinctiveness Conflict Risk

The "multi-AI" synthesis framing and inline PR-comment niche distinguish it from generic single-model review skills, with only minor overlap risk against other review-related skills.

4 / 5

Total

16

/

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
nyldn/claude-octopus
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.