review
Use this skill to review an existing Git diff for correctness, regressions, unsafe behavior, stale assumptions, missing validation, and focused test gaps…
Skill by lukky06
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lukky06-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/review
What's inside
- Skill name
review- Description
- Use this skill to review an existing Git diff for correctness, regressions, unsafe behavior, stale assumptions, missing validation, and focused test gaps before the change is accepted.
- License
- Apache-2.0
- Instructions
- 42 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Skill: Code Review ## When to use Use this skill to review an existing Git diff for correctness, regressions, unsafe behavior, stale assumptions, missing validation, and focused test gaps before the change is accepted. ## Review scope Review only the current diff and the smallest surrounding source or tests needed to judge it. Keep the review read-only. ## Evidence order 1. Inspect the current Git diff first. 2. Read changed functions, classes, configuration, or tests that directly determine the changed behavior. 3. Inspect callers or adjacent state only when the finding depends on them. 4. Use repository tests and conventions as evidence when they define intended behavior. 5. Stop expanding scope once a finding can be proven or dismissed. ## Finding standard Report only findings that are actionable and supported by repository evidence. Use these severities: - `P0`: data loss, security issue, destructive behavior, or a change that makes the repository broadly unusable. - `P1`: likely functional regression, broken recovery or persistence semantics, incorrect state transition, or a focused test that should fail. - `P2`: meaningful maintainability or robustness issue that can cause future defects, with a concrete local fix. Do not report style-only preferences, speculative concerns, or unrelated pre-existing issues. ## Review discipline - Prefer one precise finding over several weak findings. - Include the affected file and symbol or local region when known. - Explain the concrete failure mode and the condition that triggers it. - Check whether an existing focused test already covers the behavior before claiming a missing-test issue. - Do not modify files, run mutation tools, start worktree workers, or suggest broad redesigns unless the diff itself makes them necessary. ## Output convention If findings exist, list them in severity order using concise entries such as: `P1 path/to/file.py: concrete failure mode and trigger.` Finish with one gate recommendation: - `Gate recommendation: FAIL` when any P0 or P1 remains. - `Gate recommendation: PASS WITH NOTES` when only P2 findings remain. - `Gate recommendation: PASS` when no actionable finding is supported.
From lukky06/MiniCode, Apache-2.0.
More from lukky06/MiniCode
- 0.547score
repo-explain
lukky06
Use this skill to explain project structure, architecture, module responsibilities, or code flow.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
unit-test
lukky06
Use this skill when creating, repairing, or reviewing focused automated tests for a function, class, module, component, or small behavior boundary.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
web-controller-test
lukky06
Use this skill when the task asks to test an HTTP route, controller, request handler, resolver, middleware boundary, or API endpoint in any web framework.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
code-debug
lukky06
Use this skill for failing tests, compiler or interpreter errors, runtime exceptions, incorrect behavior, build failures, and regression diagnosis in any…
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
refactor
lukky06
Use this skill when the task asks for refactoring, simplification, restructuring, or cleanup while preserving behavior.
SkillBFreshness: B★ 1Claude Code +9 - 0.517score
test-generation
lukky06
Use this skill when the task asks to add new automated tests, expand branch coverage, reproduce a defect, or create a regression test in any language or…
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 17, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/lukky06/MiniCode
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lukky06
- 0.547score
repo-explain
lukky06
Use this skill to explain project structure, architecture, module responsibilities, or code flow.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
unit-test
lukky06
Use this skill when creating, repairing, or reviewing focused automated tests for a function, class, module, component, or small behavior boundary.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
web-controller-test
lukky06
Use this skill when the task asks to test an HTTP route, controller, request handler, resolver, middleware boundary, or API endpoint in any web framework.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
code-debug
lukky06
Use this skill for failing tests, compiler or interpreter errors, runtime exceptions, incorrect behavior, build failures, and regression diagnosis in any…
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
refactor
lukky06
Use this skill when the task asks for refactoring, simplification, restructuring, or cleanup while preserving behavior.
SkillBFreshness: B★ 1Claude Code +9 - 0.517score
test-generation
lukky06
Use this skill when the task asks to add new automated tests, expand branch coverage, reproduce a defect, or create a regression test in any language or…
SkillBFreshness: B★ 1Claude Code +9
Cite this page
review skill. Agent Mart. https://agentmart.dev/skills/lukky06-review (last updated 2026-10-24)