Automated summary
Performs a code review of a pull request using Great-Tables-specific standards, with two additional specialized agents.
Strengths
- Applies project-specific coding standards (8 detailed standards)
- Audits programming patterns for non-idiomatic usage
- Scoring weighted toward project priorities
- Review is not posted, displayed in console for human evaluation
Limitations
- Requires standard files to be present in `.claude/skills/code-standards/`
- Depends on the generic `/code-review:code-review` skill
- Can be slow due to two parallel Opus agents
Use this skill for any pull request on the Great-Tables repository to ensure a review aligned with project standards.
Do not use it for generic code reviews outside the Great-Tables project or when the standard files are missing.
Security analysis
SafeThe skill orchestrates code review by calling another skill and adding two agents that read code standards and analyze patterns. No execution of shell commands, no network requests, no data exfiltration. It prints review to console, not risky.
No concerns found
How this analysis is madeExamples
Review pull request #42 on the great-tables repository.Code review PR https://github.com/posit-dev/great-tables/pull/42name: gt-review description: Code review a PR using great-tables-specific standards. Use when reviewing pull requests on this repo. argument-hint: "[PR number or URL]"
Great-Tables Code Review
Run /code-review:code-review with two additional Opus agents that apply project-specific review standards.
Show all results, even if they score below threshold.
Instructions
- First, use the Skill tool to invoke
/code-review:code-review(i.e., call the Skill tool withskill: "code-review:code-review"). Follow its instructions, but add the following two agents to the set of parallel review agents (step 4):
Agent #6 (Opus): Great-Tables Standards Review
Read all files in .claude/skills/code-standards/ (SKILL.md plus the 8 detail files 01-.md through 08-.md). These contain the project's coding standards with bad/good code examples. Then review the PR diff against every standard. Return issues with:
- Which standard was violated (by number and name)
- File path and line number
- A concrete description of the problem
- Severity: "must-fix" (blocks merge) vs "should-fix" (address before or after merge)
Agent #7 (Opus): Programming Patterns Audit
Read the changed files in full (not just the diff) and identify:
- What programming patterns are used (e.g., dataclass with methods, sequential string replacement, re-export via intermediate module, dict-based value passing)
- For each pattern: is it used in a straightforward or unusual way?
- Flag any pattern that is unusual, non-idiomatic, or inconsistent with how similar patterns are used elsewhere in the codebase
- Return issues only for patterns that are genuinely problematic, not just unfamiliar
-
During scoring (step 5), use this adjusted rubric for issues from agents 6 and 7:
- Issues flagged as violating a specific named standard (1-8) should score at least 60 if verified real
- Issues about unusual programming patterns should score at least 50 if the agent identified a concrete inconsistency with the rest of the codebase
- The threshold for posting remains 80, but the scorer should weigh project-specific standards more heavily than generic code quality
-
Do not post the review as a PR comment. Print the final review to the console so the user can evaluate it first.
-
Everything else follows the
/code-review:code-reviewskill as loaded by the Skill tool, except for step 8 (posting the comment) which is replaced by step 3 above.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/great-tables-code-review-mm78noge/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/great-tables-code-review-mm78noge' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/great-tables-code-review-mm78noge/download' --output '.skill-downloads/great-tables-code-review-mm78noge/SKILL.md.part' && mv '.skill-downloads/great-tables-code-review-mm78noge/SKILL.md.part' '.skill-downloads/great-tables-code-review-mm78noge/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/great-tables-code-review-mm78noge/SKILL.md' && test -s '.skill-downloads/great-tables-code-review-mm78noge/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/gt-review' && cp -R '.skill-downloads/great-tables-code-review-mm78noge' '.claude/skills/gt-review'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/great-tables-code-review-mm78noge'openskills read 'great-tables-code-review-mm78noge'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/great-tables-code-review-mm78noge/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.