跳到正文
cccskills
免费在 GitHub 公开

firebase-development

This skill should be used when working with Firebase projects, including initializing projects, adding Cloud Functions or Firestore collections, debugging emulator issues, or reviewing Firebase code. Triggers on "firebase", "firestore", "cloud functions", "emulator", "firebase auth", "deploy to firebase", "firestore rules".

中文简介正在准备中。当前显示原文说明。

集成工具Firebase
查看安装方法

包含的文件(6)

  • SKILL.md6.2 KB
  • add-feature/SKILL.md6.5 KB
  • debug/SKILL.md5.6 KB
  • project-setup/SKILL.md6.2 KB
  • skill-report.json202.7 KB
  • validate/SKILL.md6.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Firebase Development

Overview

This skill system guides Firebase development using proven patterns from production projects. It routes to specialized sub-skills based on detected intent.

Sub-skills:

  • firebase-development:project-setup - Initialize new Firebase projects
  • firebase-development:add-feature - Add functions/collections/endpoints
  • firebase-development:debug - Troubleshoot emulator and runtime issues
  • firebase-development:validate - Review Firebase code for security/patterns

When This Skill Applies

  • Starting new Firebase projects
  • Adding Cloud Functions or Firestore collections
  • Debugging emulator issues or rule violations
  • Reviewing Firebase code for security and patterns
  • Setting up multi-hosting configurations
  • Implementing authentication (API keys or Firebase Auth)

Routing Logic

Keywords by Sub-Skill

project-setup:

  • "new firebase project", "initialize firebase", "firebase init"
  • "set up firebase", "create firebase app", "start firebase project"

add-feature:

  • "add function", "create endpoint", "new tool", "add api"
  • "new collection", "add feature", "build", "implement"

debug:

  • "error", "not working", "debug", "emulator issue"
  • "rules failing", "permission denied", "troubleshoot", "deployment failed"

validate:

  • "review firebase", "check firebase", "validate", "audit firebase"
  • "look at firebase code", "security review"

Routing Process

  1. Analyze Request: Check for routing keywords
  2. Match Sub-Skill: Identify best match based on keyword density
  3. Announce: "I'm using the firebase-development:[sub-skill] skill to [action]"
  4. Route: Load and execute the sub-skill
  5. Fallback: If ambiguous, use AskUserQuestion with 4 options

Fallback Example

If intent is unclear, ask:

Question: "What Firebase task are you working on?"
Options:
  - "Project Setup" (Initialize new Firebase project)
  - "Add Feature" (Add functions, collections, endpoints)
  - "Debug Issue" (Troubleshoot errors or problems)
  - "Validate Code" (Review against patterns)

Reference Projects

Patterns are extracted from three production Firebase projects:

ProjectPathKey Patterns
oneonone/Users/dylanr/work/2389/oneononeExpress API, custom API keys, server-write-only
bot-socialmedia/Users/dylanr/work/2389/bot-socialmedia-serverDomain-grouped functions, Firebase Auth + roles
meme-rodeo/Users/dylanr/work/2389/meme-rodeoIndividual function files, entitlements

Pattern Summaries

Multi-Hosting Setup

Three options based on needs:

OptionWhen to UseKey Feature
site: basedMultiple independent URLsSimple, no build coordination
target: basedNeed predeploy hooksBuild scripts run automatically
Single + rewritesSmaller projectsAll under one domain

Details: See docs/examples/multi-hosting-setup.md

Authentication

PatternWhen to UseExample
Custom API keysMCP tools, server-to-serveroneonone
Firebase Auth + rolesUser-facing appsbot-socialmedia
HybridBoth patterns neededWeb UI + API access

Details: See docs/examples/api-key-authentication.md

Cloud Functions Architecture

PatternWhen to UseStructure
Express appAPI with middleware, routingapp.post('/mcp', handler)
Domain-groupedFeature-rich appsposts.ts, journal.ts
Individual filesMaximum modularityOne function per file

Details: See docs/examples/express-function-architecture.md

Security Model

ModelWhen to UseComplexity
Server-write-onlyLight-write apps, high securitySimple rules
Client-write + validationHigh-volume writes, real-timeComplex rules

Strongly prefer server-write-only for light-write applications.

Details: See docs/examples/firestore-rules-patterns.md

Emulator-First Development

Always develop locally with emulators:

firebase emulators:start
# Access UI at http://127.0.0.1:4000

Key settings in firebase.json:

  • singleProjectMode: true - Essential for emulators to work together
  • ui.enabled: true - Access debug UI

Details: See docs/examples/emulator-workflow.md

Modern Tooling Standards

All Firebase projects follow these standards:

ToolPurposeConfig File
TypeScriptType safetytsconfig.json
vitestTestingvitest.config.ts
biomeLinting + formattingbiome.json

ABOUTME Comment Pattern

Every TypeScript file starts with 2-line ABOUTME comment:

// ABOUTME: Brief description of what this file does
// ABOUTME: Second line with additional context

Testing Requirements

  • Unit tests: Test handlers/utilities in isolation
  • Integration tests: Test with emulators running
  • Both required for every feature

Common Gotchas

IssueSolution
Emulator ports in uselsof -i :5001, kill process
Admin SDK vs Client SDKAdmin bypasses rules, client respects rules
Cold start delaysFirst call takes 5-10s, normal
Data persistenceUse Ctrl+C (not kill) to export data
CORS in functionsapp.use(cors({ origin: true }))

Summary

This orchestrator routes to specialized sub-skills:

  1. Detects intent via keywords
  2. Routes to appropriate sub-skill
  3. Sub-skills use TodoWrite checklists
  4. All reference shared patterns in docs/examples/

Sub-Skills:

  • firebase-development:project-setup - Initialize new projects
  • firebase-development:add-feature - Add functions/collections
  • firebase-development:debug - Troubleshoot issues
  • firebase-development:validate - Review code

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

中文简介正在准备中。当前显示原文说明。

aiskillstore/marketplace4402026年10月21日 更新

Trigger for: explaining current FAR, DFARS, or agency-supplement text; determining documented acquisition-policy status for an agency and FAR part; comparing codified text, RFO model text, and agency deviations; tracing acquisition rulemaking; finding procurement comment periods; analyzing public comments; refreshing prior policy analysis; or producing an Acquisition Policy Impact Brief. Use published federal sources and supplied policy documents without making legal or procurement-specific applicability determinations. Do not use for clause selection, market research execution, opportunities, pricing, grants, or cooperative agreements.

中文简介正在准备中。当前显示原文说明。

aiskillstore/marketplace4402026年10月21日 更新

Systematic framework for extracting actionable items from documents and organizing them into prioritized, trackable checklists. Use when converting reports, meeting notes, audits, or any document with embedded action items into structured TODO lists.

中文简介正在准备中。当前显示原文说明。

aiskillstore/marketplace4402026年10月21日 更新

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

中文简介正在准备中。当前显示原文说明。

aiskillstore/marketplace4402026年10月21日 更新

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

中文简介正在准备中。当前显示原文说明。

aiskillstore/marketplace4402026年10月21日 更新

Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

中文简介正在准备中。当前显示原文说明。

aiskillstore/marketplace4402026年10月21日 更新

查看 aiskillstore 的全部技能

报告此技能的问题