review
Review in three modes — code (diff vs standards/spec), design (NOTES + tech-spec before planning), drift (implementation vs tech-spec before ship).
Skill by yugasun
Chalk Labs
Need help deploying review?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/yugasun-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: design, 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/review
What's inside
- Skill name
review- Description
- Review in three modes — code (diff vs standards/spec), design (NOTES + tech-spec before planning), drift (implementation vs tech-spec before ship). Pick mode from Flow Conductor phase or user intent; do not mix artifact types.
- License
- Apache-2.0
- Instructions
- 183 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Review Three modes. Each mode has its own inputs, axes, and output artifact. **Do not mix modes in one file.** ## Mode selection | Mode | Trigger | Agent | Output | | --- | --- | --- | --- | | **code** | `delivery` sub-phase, user asks to review diff/PR | code-reviewer | `.scratch/<slug>/REVIEW.md` | | **design** | `design_review` phase, user asks to review design | design-reviewer | `.scratch/<slug>/DESIGN_REVIEW.md` | | **drift** | `drift_check` phase (after delivery, before ship) | design-reviewer | `.scratch/<slug>/DRIFT_REPORT.md` | When unsure: Flow Conductor phase name wins. Direct invocation defaults to **code** unless the user names design or drift. --- ## Code mode Review `git diff <fixed-point>...HEAD`: - **Standards** — matches repo coding standards? - **Spec** — matches originating issue/PRD? - **Constitution** (optional) — when `CONSTITUTION.md` exists at repo root, violates any non-negotiable principle? Run `/aiops-setup` if `docs/agents/issue-tracker.md` is missing. ### Process 1. **Pin fixed point** — commit, branch, tag, or `main`. Confirm ref resolves and diff is non-empty. 2. **Find spec** — issue refs in commits (`docs/agents/issue-tracker.md`), user path, or `docs/`/`.scratch/` PRD. No spec → Spec axis skips. 3. **Find standards** — `CODING_STANDARDS.md`, `CONTRIBUTING.md`, etc. 4. **Find constitution** — `CONSTITUTION.md` at repo root. Missing → Constitution axis skips. 5. **Parallel sub-agents** — one per active axis. Each under 400 words, cite sources. 6. **Aggregate** — one section per axis verbatim. One-line summary per axis; don't merge axes. A change can pass one axis and fail another — keep axes separate. ### Output: REVIEW.md ```markdown # Code Review: <feature-slug> ## Summary <overall assessment> ## Design Alignment - [ ] 实现符合 NOTES.md 设计决策 - [ ] 接口符合 tech-spec.md 规格 - [ ] 无超出 scope 的变更 ## Findings ### Blocking (必须修复) #### B1: <file:line> — <title> - **问题**: … - **建议**: … ### Non-blocking (建议改进) #### N1: <file:line> — <title> - **问题**: … - **建议**: … ## Verdict **APPROVE** | **REQUEST_CHANGES** ``` Gate: `review_approve` requires `REVIEW.md` contains `APPROVE`. --- ## Design mode Review design artifacts **before** planning or implementation. No code diff — review `NOTES.md` + `tech-spec.md` only. Vocabulary for depth/seam/deletion-test checks: [design-vocabulary.md](../architect-design/design-vocabulary.md). ### Inputs - `.scratch/<slug>/NOTES.md` - `.scratch/<slug>/tech-spec.md` - `CONTEXT.md` (project root or per-area) - `docs/adr/` - `.scratch/<slug>/mockups/` (if UI mockups exist) ### Process 1. Read NOTES.md decisions — each must list at least one rejected alternative. 2. Read tech-spec.md module inventory — apply deletion test and depth assessment per [design-vocabulary.md](../architect-design/design-vocabulary.md). 3. Cross-check CONTEXT.md vocabulary and existing ADRs — flag conflicts unless explicitly justified. 4. If `CONSTITUTION.md` exists, check design against non-negotiable principles. 5. Independent second perspective — do not rubber-stamp architect reasoning. Do not review implementation details (that is code mode). ### Output: DESIGN_REVIEW.md ```markdown # Design Review: <feature-slug> ## Summary <one paragraph> ## Design Soundness - [ ] 每个设计决策列出了至少一个被否决的替代方案及原因 - [ ] 模块通过 deletion test(非 pass-through) - [ ] 接口设计遵循 depth 原则:小接口 + 深实现 - [ ] 依赖分类正确,seam 位置合理(≥2 adapters 才有真实 seam) - [ ] 接口定义与 CONTEXT.md 领域模型一致 - [ ] 无与现有 ADR 的冲突(或冲突已记录并有充分理由) - [ ] Open Questions 全部解决或明确标记为非阻塞 - [ ] 无过早优化或过度设计 - [ ] Scope 边界清晰,out-of-scope 明确排除 ## Findings ### Blocking (必须修正才能进入规划) #### D1: <title> - **问题**: … - **建议**: …
From yugasun/aiops, Apache-2.0.
More from yugasun/aiops
- 0.569score
lean
yugasun
Minimal solution discipline: YAGNI ladder, stdlib and native first, shortest working diff.
SkillBFreshness: B★ 4Claude Code +9 - 0.521score
aiops
yugasun
Flow Conductor for the aiops bundle.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
code-graph
yugasun
Build and query a persistent code graph for the target project.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
gitops
yugasun
Git operations wrapper: sync, stage, commit, push.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
architect-design
yugasun
Structured design process for the architect agent.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
domain-modeling
yugasun
Build and sharpen a project's domain model — glossary, ubiquitous language, ADRs.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
file-refactor
yugasun
Keep source files under 500 lines.
SkillCFreshness: C★ 4Claude Code +9 - 0.516score
aiops-setup
yugasun
Configure a target project for the aiops bundle — issue tracker, triage labels, domain doc layout.
SkillCFreshness: C★ 4Claude Code +9 - 0.514score
prune
yugasun
Review diffs for over-engineering only.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
to-issues
yugasun
Break a plan or PRD into vertical-slice issues on the project issue tracker.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
aiops-implement
yugasun
Delivery overlay — orchestrates lean ladder, tdd, prune, review with sub-phase gates; commits only on user approval.
SkillCFreshness: C★ 4Claude Code +9 - 0.513score
prototype
yugasun
Throwaway prototype to answer a design question — terminal logic explorer or multi-variant UI on one route.
SkillCFreshness: C★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Jul 2, 2026 (4 months ago)
- Last release
- Jul 20, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/yugasun/aiops
- Website
- aiops.yugasun.com/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from yugasun
- 0.569score
lean
yugasun
Minimal solution discipline: YAGNI ladder, stdlib and native first, shortest working diff.
SkillBFreshness: B★ 4Claude Code +9 - 0.521score
aiops
yugasun
Flow Conductor for the aiops bundle.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
file-refactor
yugasun
Keep source files under 500 lines.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
code-graph
yugasun
Build and query a persistent code graph for the target project.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
domain-modeling
yugasun
Build and sharpen a project's domain model — glossary, ubiquitous language, ADRs.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
architect-design
yugasun
Structured design process for the architect agent.
SkillCFreshness: C★ 4Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get review running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
review skill. Agent Mart. https://agentmart.dev/skills/yugasun-review (last updated 2026-10-24)