code-review
Use when completing a task, reviewing a branch or PR, before merging, when the user asks to 'review since X', when publishing a GitHub PR review with inline…
Skill by Leostruka
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/leostruka-code-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: productivity
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/code-review
What's inside
- Skill name
code-review- Description
- Use when completing a task, reviewing a branch or PR, before merging, when the user asks to 'review since X', when publishing a GitHub PR review with inline comments/suggestions, or when the user receives code review feedback and needs to decide how to act on it.
- License
- MIT
- Instructions
- 56 lines in SKILL.md · view on GitHub
Files (8)
- SKILL.md
- code-reviewer.md
- dependency-bumps.md · modes/
- giving.md · modes/
- post-merge-audit.md · modes/
- pr-audit.md · modes/
- pr-inline.md · modes/
- receiving.md · modes/
SKILL.md (first lines)
# Code Review Six modes; full detail in `modes/<mode>.md`. Read it when you enter the mode. `code-reviewer.md` is the reviewer subagent brief. | Mode | When | Detail | |---|---|---| | **Giving** | Completing a task, reviewing a branch/PR, before merge, "review since X" | `modes/giving.md` | | **PR-inline** | Publishing a GitHub review with inline ` ```suggestion ` comments | `modes/pr-inline.md` | | **Receiving** | Deciding how to act on review feedback you received | `modes/receiving.md` | | **PR-audit** | Auditing an untrusted contributor PR before merge: claim verification, prompt-injection resistance, hostile-change and supply-chain review | `modes/pr-audit.md` | | **Post-merge audit** | Auditing the combined default-branch tree after merges, before deploy/release | `modes/post-merge-audit.md` | | **Dependency bumps** | Fast-path merge of bot-authored dependency-only PRs | `modes/dependency-bumps.md` | ## Giving — essentials - Review the diff against the spec, not your memory of it. - Two-axis review where the repo defines it (Standards vs Spec). - Every finding cites file:line and the rule it violates. - Verify claims with tools before reporting — no "looks fine" without evidence. - Independent reviewer subagent (`reviewer`/`qa-ci`) for unbiased assessment on high-risk diffs. ## PR-inline — essentials - Cycle: CHECK → COMMENT/SUGGEST → NEXT. One concern per cycle; never post before confirming the target line in the PR head. - `gh api` with `--field` for per-line positioning (not `gh pr review`). - ` ```suggestion ` blocks must be applicable in one click. - Don't edit the PR's code locally; comments only. - Comment language follows the repository. - Every comment gets a gate in the ledger (see `gates`). ## Receiving — essentials Verify before implementing; ask before assuming; technical correctness over social comfort. 1. READ the feedback completely without reacting. 2. UNDERSTAND — restate the requirement or ask. 3. VERIFY against codebase reality. 4. EVALUATE — technically sound for THIS codebase? 5. RESPOND — technical acknowledgment or reasoned pushback. 6. IMPLEMENT — one item at a time, test each. Classify each item: **pushed** (reviewer cites a concrete violation → verify against the cited source, fix, test) vs **pulled** (reviewer points to a skill/convention/gate you should have used → pull that source first, apply, verify). Repeated missing pulled patterns → add to your pre-review checklist. ## Cross-skills - `security` — escalate to the security skill when the diff touches auth, secrets, input handling, or public endpoints. - `a11y-audit` — escalate when the diff touches frontend markup/ARIA/keyboard paths.
From Leostruka/devin-bundle, MIT.
More from Leostruka/devin-bundle
- 0.570score
debugging
Leostruka
Use when the user says 'diagnose', 'debug this', reports something broken/throwing/failing/slow, when encountering a bug/test failure/unexpected behavior and…
SkillAFreshness: AClaude Code +9 - 0.565score
ask-bundle
Leostruka
Use when deciding which skill or flow fits your situation — the meta-router entry point for this bundle (direct specialist skills, multi-skill flows, local…
SkillAFreshness: AClaude Code +9 - 0.565score
ai-tools
Leostruka
Use when running local, offline-first ML tooling — mechanistic interpretability PoCs like refusal-direction ablation on local safetensors or the HF cache, or…
SkillAFreshness: AClaude Code +9 - 0.565score
animation-direction
Leostruka
Use when turning narrated video/audio into synced code-rendered motion graphics — narration -> timestamped transcript -> scene plan -> approval gate ->…
SkillAFreshness: AClaude Code +9 - 0.565score
architecture
Leostruka
Use when designing modules, seams, and adapters, when evaluating module depth and identifying deepening opportunities in a codebase, or when modernizing…
SkillAFreshness: AClaude Code +9 - 0.565score
architecture-diagrams
Leostruka
Use when the deliverable is a physical diagram artifact (.svg/.png) — C4 models, dense class diagrams, network topology rendered via PlantUML.
SkillAFreshness: AClaude Code +9 - 0.565score
computer-use
Leostruka
Use when you need to see or control the local screen (screenshots, screen recording with video + contact sheet for catching transient bugs/animations, mouse…
SkillAFreshness: AClaude Code +9 - 0.565score
context-hygiene
Leostruka
Use when context is growing large or the agent forgets earlier instructions, when deciding clear vs compact, when processing documents/logs >50k tokens, when…
SkillAFreshness: AClaude Code +9 - 0.565score
cu-realtime
Leostruka
Use when computer-use or terminal automation needs the fastest reaction the runtime allows - event waits instead of screenshot polling, text perception…
SkillAFreshness: AClaude Code +9 - 0.560score
ascii-art
Leostruka
Use when generating animated ASCII art for artifacts the agent produces - README banners (SVG), CLI splash screens, loading/404 states or decorative pieces in…
SkillAFreshness: AClaude Code +9 - 0.539score
data-analyst
Leostruka
Use when the user asks to query a database, analyze data, create charts/visualizations, explore data patterns, or asks business questions about data.
SkillAFreshness: AClaude Code +9 - 0.539score
database
Leostruka
Use when the user wants to design, migrate, query, or optimize a database.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Sep 29, 2026 (28 days ago)
- Last release
- Oct 24, 2026 (4 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Leostruka/devin-bundle
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Leostruka
- 0.570score
debugging
Leostruka
Use when the user says 'diagnose', 'debug this', reports something broken/throwing/failing/slow, when encountering a bug/test failure/unexpected behavior and…
SkillAFreshness: AClaude Code +9 - 0.565score
ai-tools
Leostruka
Use when running local, offline-first ML tooling — mechanistic interpretability PoCs like refusal-direction ablation on local safetensors or the HF cache, or…
SkillAFreshness: AClaude Code +9 - 0.565score
ask-bundle
Leostruka
Use when deciding which skill or flow fits your situation — the meta-router entry point for this bundle (direct specialist skills, multi-skill flows, local…
SkillAFreshness: AClaude Code +9 - 0.565score
animation-direction
Leostruka
Use when turning narrated video/audio into synced code-rendered motion graphics — narration -> timestamped transcript -> scene plan -> approval gate ->…
SkillAFreshness: AClaude Code +9 - 0.565score
architecture
Leostruka
Use when designing modules, seams, and adapters, when evaluating module depth and identifying deepening opportunities in a codebase, or when modernizing…
SkillAFreshness: AClaude Code +9 - 0.565score
architecture-diagrams
Leostruka
Use when the deliverable is a physical diagram artifact (.svg/.png) — C4 models, dense class diagrams, network topology rendered via PlantUML.
SkillAFreshness: AClaude Code +9
Cite this page
code-review skill. Agent Mart. https://agentmart.dev/skills/leostruka-code-review (last updated 2026-10-24)