Skip to main content

review-component

Review component code or changes of any generation (v0, v1, agentic, primitive, or native-backed) without editing files. Classifies each changed surface, applies the matching checklists and native overlay, and reports evidence-backed findings with validation status.

来源信息

仓库
microsoft/fluentui-react-native
最近来源活动
2026年10月23日 22:33
检测到的 SKILL.md 语言
英语
星标
1,448
Forks
179

安装方式

默认使用会先检查来源的 Prompt;你也可以切换为直接命令,或下载本地副本。

检查来源文件

决定是否安装前,请先阅读 SKILL.md,以及 SkillsMP 当前展示的配套文件。

正在显示 SKILL.md

SKILL.md
来源说明 · 只读预览
name
review-component
description
Review component code or changes of any generation (v0, v1, agentic, primitive, or native-backed) without editing files. Classifies each changed surface, applies the matching checklists and native overlay, and reports evidence-backed findings with validation status.
license
MIT
# Review a component change - **R-REVIEW-001:** A review is read-only. Do not edit files, update snapshots, commit, or invoke an implementation workflow unless the user asks for fixes after receiving the review. - **R-REVIEW-002:** Report only evidence-backed findings. Cite `path:line`, the violated rule ID or contract requirement ID, and whether the finding was verified (executed or confirmed in source) or inferred. ## Workflow 1. Establish the scope: the named files, the working-tree diff, or the branch diff against its base. 2. Classify each changed surface with the [classification guide](../../../references/agents/components/classification.md): task intent, implementation model, public compatibility, and native obligations (R-CLASSIFY-001, R-CLASSIFY-002). 3. Load only the checklists for the surfaces present: | Surface | Checklist | | ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | v0 | [v0 review checklist](../../../references/agents/components/v0.md#review-checklist) | | v1 | [v1 review checklist](../../../references/agents/components/v1.md#review-checklist) | | Agentic higher-order | [Package](../../../packages/agentic/components/AGENTS.md) and [higher-order component](../../../packages/agentic/components/references/higher-order-components.md) invariants; the component's `SPEC.md` and `spec/`; and the review checklists in [types and slots](../../../packages/agentic/components/references/types-and-slots.md#review-checklist), [state and accessibility](../../../packages/agentic/components/references/state-and-accessibility.md#review-checklist), [styles and tokens](../../../packages/agentic/components/references/styles-and-tokens.md#review-checklist), and [rendering](../../../packages/agentic/components/references/rendering.md#review-checklist) for the areas changed | | Agentic primitive | [Primitive invariants](../../../packages/agentic/components/references/primitives.md), the primitive's `CONTRACT.md`, and [primitive contracts](../../../packages/agentic/components/references/types-and-slots.md#primitive-contracts) | | Tests and stories | [Tests and stories](../../../packages/agentic/components/references/tests-and-stories.md) for agentic code; [legacy test apps](../../../references/agents/components/legacy-test-apps.md) for v0 and v1 | | Contract or provenance | [Contract authoring](../agentic-component-contract-authoring/SKILL.md) workflow, the [contracts reference](../../../packages/agentic/components/references/contracts.md), and only the [source adapters](../../../packages/agentic/components/references/README.md) matching the changed evidence | | Focus or keyboard | [Required focus evidence](../../../references/agents/focus/common.md#required-evidence-before-shipping) and the affected platform file | | Native code or roots | [Native overlay checklist](../implement-native-component/SKILL.md#native-overlay-checklist); for iOS or macOS, also [Apple and Office rules](../../../references/agents/native/apple-office.md) | | Framework-base pattern | [Framework-base instructions](../../../packages/framework-base/AGENTS.md) | 4. Check repository-wide rules: explicit exports (R-REPO-001), platform fork imports (R-REPO-002), changesets (R-REPO-003), no copied private source (R-REPO-004), and the code-scanning patterns: linear-time regular expressions and no values spliced into executed code (R-SCAN-001, R-SCAN-002). 5. Inspect validation claims. Run non-mutating checks only when they add evidence, preferring focused tests over the whole suite (R-VALID-004); never run snapshot-update or fix modes. Record each check as passed, failed, skipped, not run, or unsupported (R-VALID-002). ## Output 1. **Scope and classification:** one line per changed surface. 2. **Findings**, highest severity first. For each: `path:line`, the problem, the rule or requirement ID, verified or inferred, and a suggested correction. 3. **Validation:** commands run with results, and checks not run with the reason. When nothing qualifies, say so and list what was checked. Do not pad the review with style preferences.
在 GitHub 查看