skills/review-codebase/SKILL.md
Review given file/dir/repo for current-state code organization: module boundaries, design patterns, cross-module dependencies, tech debt, and interface stability. Scope-only atomic skill; output is a findings list.
npx skillsauth add nesnilnehc/ai-cortex review-codebaseInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
对给定路径(单文件 / 目录 / 仓库)的当前状态做 scope-only 原子审查。与 review-diff(仅审查 git 变更)成对作为 orchestrate-code-review 的 scope 步候选——本技能看快照,review-diff 看变更。
不做:安全 / 性能 / 架构等 cognitive 维度(由 cognitive 步的原子技能 review-security / review-performance / review-architecture 承接),也不做语言或框架特定分析(由 language / framework 步承接)。
首要目标:产出 scope-only findings list,识别给定路径的结构性问题(边界、模式、依赖、技术债、接口)。
成功标准(必须全部满足):
file:line 引用scope)/ severity / title / description / suggestion本技能负责:
本技能不负责:
review-diff)orchestrate-code-review)review-<lang> / review-<framework>)review-security / review-performance / review-architecture)交接点:findings 输出后,作为 orchestrate-code-review 的 scope 步聚合输入;或交给用户决定后续(重构 / 进一步深审)。
src/auth/ 看当前结构与依赖review-diff 二选一| 项目 | 默认 | 用户偏离方式 | |---|---|---| | 路径 | 仓库根 | 选择:[仓库根] / [当前文件目录] / [列出顶级目录选择] | | 大范围处理 | 按层(模块 / 目录)输出 | 选择优先子集(从顶级目录列表选) |
运行前必须确认两件事:(1) 审查路径;(2) 大范围时按层 vs 优先子集。
对范围内代码(按用户选定的层 / 子集),输出以下维度的 findings:
每条 finding 必须含 file:line 引用。
如果在分析中发现属于安全 / 性能 / 架构 / 语言 / 框架的具体问题:标记并提示对应原子技能,但不展开分析。例:
检测到潜在 SQL 注入风险(user input 未转义直接拼接),建议运行
review-security
file:line 引用的 finding不做(其他原子技能负责):
review-difforchestrate-code-reviewreview-<lang>review-<framework>review-security / review-performance / review-architecturesrc/auth/auth.go:42 类引用;遇到加密弱算法仅标记并提示 review-securitypkg/validator/validator.godevelopment
Generate an LLM agent test suite (golden cases, mock-LLM unit tests, evaluator harness) from an agent implementation and its agent-test contract. Use when an agent has no tests, or a contract exists but the test code is missing.
development
After code changes, auto-detect the project's build system and local deployment method for a given directory, then build the project and restart its locally-deployed environment (Docker Compose / systemd / process manager). Never assumes — asks only when detection is ambiguous. Caches detected commands per project in .cortex/redeploy-local.yaml; re-invocations on the same project skip re-scanning until signal files change, the cache expires (30 days), or the skill version bumps.
tools
Publish a NATS message conforming to a cross-team contract, using NATS MCP tools. Authors the contract on first use if missing. Reads project-level cache (.cortex/nats.yaml) to avoid re-prompting basics across sessions.
tools
Drain pending NATS messages from a producer contract via NATS MCP tools (default batch / drain-style). Applies Tolerant Reader semantics and per-message ack/nak/term, returning aggregated stats. Reads project-level cache (.cortex/nats.yaml) to avoid re-prompting.