Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问clear审计异常

fpf-reviewFPF 评论

Agent Skill

fpf-review 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

374

周安装

15

GitHub Stars

264

下载量

121
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:fpf-review(FPF 评论)
来源仓库:https://github.com/athola/claude-night-market
仓库路径:skills/fpf-review
安装命令:
npx skills add https://github.com/athola/claude-night-market --skill fpf-review
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/athola/claude-night-market --skill fpf-review

简介

fpf-review 用于查找、检索和筛选相关信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中根据任务场景定位候选结果。
  • 可通过 npx skills add 命令从指定仓库安装并使用。
  • 安装前需确认权限范围、维护状态及是否触发联网或文件操作。
  • 建议结合原始 README 核验具体用法和功能细节。

SKILL.md

Table of Contents

Run verification after review: make lint && make test to confirm no regressions.

FPF Architecture Review

Conduct architecture reviews using the FPF (Functional Programming Framework) methodology, evaluating codebases through three complementary perspectives.

Philosophy

Architecture reviews should be systematic and multi-dimensional. FPF provides three lenses:

  • Functional: What the system does (capabilities, behaviors)
  • Practical: How well it works (performance, usability)
  • Foundation: What it's built on (principles, patterns)

This lighter skill-based approach replaces heavyweight tooling with focused analysis.

Quick Start

# Full FPF review
/fpf-review

# Specific perspective
/fpf-review --perspective functional
/fpf-review --perspective practical
/fpf-review --perspective foundation

# Focused scope
/fpf-review --scope plugins/sanctum

The Three Perspectives

1. Functional Perspective

Question: What does this system do?

Evaluates:

  • Feature completeness
  • Capability coverage
  • Behavior correctness
  • Integration points

Outputs:

  • Feature inventory
  • Capability gaps
  • Behavior anomalies

2. Practical Perspective

Question: How well does this system work?

Evaluates:

  • Performance characteristics
  • Usability patterns
  • Operational concerns
  • Scalability considerations

Outputs:

  • Performance assessment
  • Usability issues
  • Operational recommendations

3. Foundation Perspective

Question: What is this system built on?

Evaluates:

  • Architectural patterns
  • Design principles
  • Code quality
  • Technical debt

Outputs:

  • Pattern analysis
  • Principle adherence
  • Debt inventory

Workflow

Phase 1: Discovery (fpf-review:discovery-complete)

  1. Scan codebase structure - Identify components, modules, layers
  2. Map dependencies - Internal and external relationships
  3. Identify entry points - Public APIs, commands, interfaces

Phase 2: Functional Analysis (fpf-review:functional-complete)

  1. Inventory features - What capabilities exist
  2. Trace behaviors - How features work end-to-end
  3. Identify gaps - Missing or incomplete functionality

Phase 3: Practical Analysis (fpf-review:practical-complete)

  1. Assess performance - Latency, throughput, resource usage
  2. Evaluate usability - Developer experience, API design
  3. Check operations - Logging, monitoring, error handling

Phase 4: Foundation Analysis (fpf-review:foundation-complete)

  1. Pattern recognition - What patterns are used
  2. Principle check - SOLID, DRY, KISS adherence
  3. Debt assessment - Technical debt inventory

Phase 5: Synthesis (fpf-review:synthesis-complete)

  1. Cross-reference findings - Connect issues across perspectives
  2. Prioritize recommendations - Based on impact and effort
  3. Generate report - Structured findings and actions

Output Format

FPF Review Report

# FPF Architecture Review: [Project/Component]

**Date:** [DATE]
**Scope:** [what was reviewed]
**Reviewer:** Claude Code with FPF skill

## Executive Summary

[2-3 sentence overview of findings]

## Functional Perspective

### Features Inventory

| Feature | Status | Notes |
|---------|--------|-------|
| [Feature 1] | Complete | - |
| [Feature 2] | Partial | Missing edge case handling |

### Capability Gaps

1. [Gap 1] - [Impact]
2. [Gap 2] - [Impact]

## Practical Perspective

### Performance Assessment

| Metric | Current | Target | Status |
|--------|---------|--------|--------|
| [Metric 1] | [value] | [target] | PASS/FAIL |

### Usability Issues

1. [Issue 1] - [Severity]
2. [Issue 2] - [Severity]

## Foundation Perspective

### Pattern Analysis

| Pattern | Usage | Assessment |
|---------|-------|------------|
| [Pattern 1] | [where used] | Appropriate/Problematic |

### Technical Debt

| Item | Severity | Effort | Priority |
|------|----------|--------|----------|
| [Debt 1] | High | Medium | P1 |

## Recommendations

### High Priority

1. **[Recommendation 1]**
   - Impact: [what improves]
   - Effort: [estimate]
   - Rationale: [why]

### Medium Priority

2. **[Recommendation 2]**
   ...

## Action Items

- [ ] [Action 1] - Owner: TBD
- [ ] [Action 2] - Owner: TBD

Configuration

# .fpf-review.yaml
scope:
  include:
    - src/
    - plugins/
  exclude:
    - tests/
    - docs/
    - node_modules/

perspectives:
  functional:
    enabled: true
    depth: "full"  # full, summary
  practical:
    enabled: true
    depth: "full"
  foundation:
    enabled: true
    depth: "full"

output:
  format: "markdown"
  create_issues: false  # Create GitHub issues for findings
  severity_threshold: "medium"  # Report medium+ severity

Guardrails

  1. Scope boundaries - Stay within configured scope
  2. Evidence-based - Every finding needs supporting evidence
  3. Actionable output - Recommendations must be actionable
  4. Balanced perspectives - Don't over-index on one perspective

Required TodoWrite Items

  1. fpf-review:discovery-complete
  2. fpf-review:functional-complete
  3. fpf-review:practical-complete
  4. fpf-review:foundation-complete
  5. fpf-review:synthesis-complete

Integration Points

  • pensive:code-reviewer: Detailed code-level review
  • imbue:review-core: Review methodology patterns
  • imbue:feature-review: Feature-specific analysis

References


Status: Skeleton implementation. Requires:

  • Detailed analysis algorithms
  • Pattern recognition logic
  • Report generation templates

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude Code

31.19%
按下载量换算38

OpenCode

21%
按下载量换算25

Cursor

15.89%
按下载量换算19

Codex

11.74%
按下载量换算14

Antigravity

8.29%
按下载量换算10

Gemini CLI

3.71%
按下载量换算4

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。

来源信息

继续浏览同类 Skills