Chalk Labs
Need help deploying code-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/snbc-qihang-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
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
- 评审固定 diff、Pull Request 或阶段门禁,按仓库规范与需求识别有证据的问题。
- License
- MIT
- Instructions
- 19 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- evidence-and-stage-audit.md · references/
- security-seams.md · references/
- smell-baseline.md · references/
SKILL.md (first lines)
本 skill 仅使用当前 `engineering-assistant` 的能力与 Runtime。平台已选本 skill 时直接执行,不重复路由或跨插件推进同一运行。 # 代码评审 先固定比较点,再分别依据仓库规范和原始需求检查变化的行为。按变更风险选择足够的证据。 1. 固定 base、head、merge-base、diff、需求及用户限制;可调查事实先自行核对,不为已给出的比较点重复请求确认。 2. 从 diff 和相关入口追踪成功、失败、边界、数据及外部影响。可用索引已经返回的内容不重复扫描;工具不可用时沿已知路径定向补齐。 3. 评估正确性、复杂度、冗余、性能、架构和测试质量,报告明确的触发条件、影响、文件位置与验证方法。测试未变不等于覆盖缺失,只有风险需要时补充检查;相关验证通过后不无依据扩大全量测试。 4. 可执行的 active persisted quality node 才提交 `QualitySnapshot` 并遵守六维门禁;内联评审记录判断及不适用理由,不为了获得六个 pass 创建 flow、基准测试或形式化产物。 5. 只有决定性证据闭合触发条件、失败行为和阶段影响时才认定 blocker。证据不足标未核实或未评估,继续独立可完成部分;普通代码走查不以需求 ID 或外部设计源为前提。 需要代码异味判断且仓库规则不足时读取 [异味基线](references/smell-baseline.md)。行为触及身份或授权状态、秘密或持久化合同,读取 [安全 seam](references/security-seams.md) 并闭合数据全部扇出路径。 阶段状态审计、历史产物、工具能力缺口或证据冲突时读取 [证据与阶段审计](references/evidence-and-stage-audit.md)。技术状态与人工批准分别记录,不能用技术通过替代既有人工门禁。 平台已选本 skill 时直接执行内联评审;仅在确实需要持久化门禁或任务超出本原语时进入 Runtime 路由。用户中途修正目标时更新受影响结论并继续未取消的工作。
From snbc-qihang/agent-skills, MIT.
More from snbc-qihang/agent-skills
- 0.586score
tdd
snbc-qihang
通过真实红绿反馈实现可测试的行为。适用于明确要求 TDD,或新增规则、缺陷修复适合失败测试驱动的场景;普通修改不自动触发。
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
domain-modeling
snbc-qihang
在明确的限界上下文中建立统一语言、业务规则、生命周期及战略和战术模型。适用于语义冲突、业务规则复杂、聚合或一致性边界不清,以及代码与业务语言不一致的场景。
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
engineering-assistant
snbc-qihang
将工程任务路由到最小充分的 skill 或受治理 flow。适用于请求跨越上下文、设计、实现、评审、发布或长期任务协调的场景。
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
repo-context
snbc-qihang
基于源码证据梳理仓库模块、接口、数据、依赖、可复用能力和影响范围。适用于设计或大范围变更分析之前。
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
research
snbc-qihang
基于一手资料研究工程问题,并输出有引用、有边界的结论。适用于外部项目、API、标准或不熟悉的技术事实。
SkillAFreshness: A★ 1Claude Code +9 - 0.578score
prototype
snbc-qihang
构建明确可丢弃的逻辑或界面原型,用于回答一个设计问题。适用于具体交互验证比继续抽象讨论成本更低的场景。
SkillAFreshness: A★ 1Claude Code +9 - 0.578score
wayfinder
snbc-qihang
把大型或高不确定性工程任务整理为目标、当前前沿和待决策事项。适用于工作超过一次会话或尚不能安全切片的场景。
SkillAFreshness: A★ 1Claude Code +9 - 0.578score
codebase-design
snbc-qihang
设计小接口、高杠杆、变更局部化的深模块和清晰 seam。适用于架构边界、可测试性或重构结构设计。
SkillAFreshness: A★ 1Claude Code +9 - 0.578score
decision-interview
snbc-qihang
在查明仓库事实后,与用户一起解决相互依赖的产品或设计决策。适用于范围、取舍或验收标准仍不明确的场景。
SkillAFreshness: A★ 1Claude Code +9 - 0.578score
diagnosing-bugs
snbc-qihang
通过复现、最小化、可证伪假设、定向观测、修复和回归证据诊断疑难缺陷或性能退化。
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 19, 2026 (11 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/snbc-qihang/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from snbc-qihang
- 0.586score
tdd
snbc-qihang
通过真实红绿反馈实现可测试的行为。适用于明确要求 TDD,或新增规则、缺陷修复适合失败测试驱动的场景;普通修改不自动触发。
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
domain-modeling
snbc-qihang
在明确的限界上下文中建立统一语言、业务规则、生命周期及战略和战术模型。适用于语义冲突、业务规则复杂、聚合或一致性边界不清,以及代码与业务语言不一致的场景。
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
engineering-assistant
snbc-qihang
将工程任务路由到最小充分的 skill 或受治理 flow。适用于请求跨越上下文、设计、实现、评审、发布或长期任务协调的场景。
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
repo-context
snbc-qihang
基于源码证据梳理仓库模块、接口、数据、依赖、可复用能力和影响范围。适用于设计或大范围变更分析之前。
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
research
snbc-qihang
基于一手资料研究工程问题,并输出有引用、有边界的结论。适用于外部项目、API、标准或不熟悉的技术事实。
SkillAFreshness: A★ 1Claude Code +9 - 0.578score
prototype
snbc-qihang
构建明确可丢弃的逻辑或界面原型,用于回答一个设计问题。适用于具体交互验证比继续抽象讨论成本更低的场景。
SkillAFreshness: A★ 1Claude 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 code-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
code-review skill. Agent Mart. https://agentmart.dev/skills/snbc-qihang-code-review (last updated 2026-10-24)