API安装
- 作者仓库星标 19,859
- 许可证 AGPL-3.0
- 作者更新于 实时读取
- 作者仓库 daily
- 领域
- AI 智能
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 94 / 100 · 已通过审计
- 作者 / 版本 / 许可
- @dailydotdev · AGPL-3.0
- Token 消耗评级
- 中等消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- macOS · Linux · Windows
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 读取环境变量
- 网络行为
- 允许外网请求
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: daily.dev
description: Overcome LLM knowledge cutoffs with real-time developer content. daily.dev aggregates articles f…
category: AI 智能
runtime: 无特殊运行时
---
# daily.dev 输出预览
## PART A: 任务判断
- 适用问题:提示词、Agent 工作流、模型评估或自动化推理。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“Security / Setup / Secure Token Storage (Recommended)”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于提示词、Agent 工作流、模型评估或自动化推理,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Security / Setup / Secure Token Storage (Recommended)”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、执行终端命令、读取环境变量、会按任务需要访问外部网络、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、执行终端命令、读取环境变量;会按任务需要访问外部网络;通常不需要额外 API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 原文出现了 `/tags`、`/feeds`、`/profile`、`/bookmarks`、`/posts` 这类斜杠命令;如果你的 Agent 支持命令触发,优先用命令开场,再补充目标和边界。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件、执行终端命令、读取环境变量。
先用一个小任务确认它会围绕“Security / Setup / Secure Token Storage (Recommended)”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: daily.dev
description: Overcome LLM knowledge cutoffs with real-time developer content. daily.dev aggregates articles f…
category: AI 智能
source: dailydotdev/daily
---
# daily.dev
## 什么时候使用
- 把 AI / Agent方向的常用动作沉淀成 Agent 可调用的技能 适合处理AI Agent、提示词、模型评估与自动化推理,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任务拆成可执行、可检查…
- 面向提示词、Agent 工作流、模型评估或自动化推理,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Security / Setup / Secure Token Storage (Recommended)」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件、执行终端命令、读取环境变量;会按任务需要访问外部网络;通常不需要额外 API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "daily.dev" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Security / Setup / Secure Token Storage (Recommended)
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件、执行终端命令、读取环境变量 | 会按任务需要访问外部网络
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} daily.dev API for AI Agents
Overcome LLM knowledge cutoffs with real-time developer content. daily.dev aggregates articles from thousands of sources, validated by community engagement, with structured taxonomy for precise discovery.
Security
CRITICAL: Your API token grants access to personalized content. Protect it:
- NEVER send your token to any domain other than
api.daily.dev - Never commit tokens to code or share them publicly
- Tokens are prefixed with
dda_- if you see this prefix, treat it as sensitive
Setup
- Requires Plus subscription - Get one at https://app.daily.dev/plus
- Create a token at https://app.daily.dev/settings/api
- Store your token securely (environment variables, secrets manager)
User can use environment variable or choose one of the secure storage methods below per operating system.
Secure Token Storage (Recommended)
macOS - Keychain
# Store token
security add-generic-password -a "$USER" -s "daily-dev-api" -w "dda_your_token"
# Retrieve token
security find-generic-password -a "$USER" -s "daily-dev-api" -w
# Auto-load in ~/.zshrc or ~/.bashrc
export DAILY_DEV_TOKEN=$(security find-generic-password -a "$USER" -s "daily-dev-api" -w 2>/dev/null)
Windows - Credential Manager
# Store token (run in PowerShell)
$credential = New-Object System.Management.Automation.PSCredential("daily-dev-api", (ConvertTo-SecureString "dda_your_token" -AsPlainText -Force))
$credential | Export-Clixml "$env:USERPROFILE\.daily-dev-credential.xml"
# Retrieve token - add to PowerShell profile ($PROFILE)
$cred = Import-Clixml "$env:USERPROFILE\.daily-dev-credential.xml"
$env:DAILY_DEV_TOKEN = $cred.GetNetworkCredential().Password
Or use the Windows Credential Manager GUI: Control Panel → Credential Manager → Windows Credentials → Add a generic credential
Linux - Secret Service (GNOME Keyring / KWallet)
# Requires libsecret-tools
# Ubuntu/Debian: sudo apt install libsecret-tools
# Fedora: sudo dnf install libsecret
# Store token
echo "dda_your_token" | secret-tool store --label="daily.dev API Token" service daily-dev-api username "$USER"
# Retrieve token
secret-tool lookup service daily-dev-api username "$USER"
# Auto-load in ~/.bashrc or ~/.zshrc
export DAILY_DEV_TOKEN=$(secret-tool lookup service daily-dev-api username "$USER" 2>/dev/null)
Resolving the API token
Check if DAILY_DEV_TOKEN environment variable is available. If not set, try to retrieve it from the OS secure storage before asking the user for help:
macOS:
export DAILY_DEV_TOKEN=$(security find-generic-password -a "$USER" -s "daily-dev-api" -w 2>/dev/null)
Linux:
export DAILY_DEV_TOKEN=$(secret-tool lookup service daily-dev-api username "$USER" 2>/dev/null)
Windows (PowerShell):
$cred = Import-Clixml "$env:USERPROFILE\.daily-dev-credential.xml" 2>$null; $env:DAILY_DEV_TOKEN = $cred.GetNetworkCredential().Password
If the token is still empty after trying secure storage, direct the user to the Setup section above.
Authentication
Authorization: Bearer $DAILY_DEV_TOKEN
Base URL
https://api.daily.dev/public/v1
API Reference
Full OpenAPI spec: https://api.daily.dev/public/v1/docs/json
To fetch details for a specific endpoint (e.g. response schema):
curl -s https://api.daily.dev/public/v1/docs/json | jq '.paths["/feeds/foryou"].get'
To fetch a component schema (replace def-17 with schema name from $ref):
curl -s https://api.daily.dev/public/v1/docs/json | jq '.components.schemas["def-17"]'
Available Endpoints
!curl -s https://api.daily.dev/public/v1/docs/json | jq -r '.paths | to_entries | map(.key as $path | .value | to_entries | map(.key as $method | {tag: (.value.tags[0] // "other"), line: ("\(.key | ascii_upcase) \($path)" + (if .value.description then " - \(.value.description)" else "" end) + (if (.value.parameters | length) > 0 then "\n Params: " + ([.value.parameters[] | "\(.name)(\(.in)): \(.description // .schema.type)"] | join("; ")) else "" end) + (if .value.requestBody then "\n Body: " + (.value.requestBody.content["application/json"].schema | if .properties then ([.properties | to_entries[] | "\(.key)"] | join(", ")) elif ."$ref" then (."$ref" | split("/") | last) else "object" end) else "" end))})) | flatten | group_by(.tag) | map("#### \(.[0].tag)\n" + (map(.line) | join("\n\n"))) | join("\n\n")'
Agent Use Cases
Why daily.dev for agents? LLMs have knowledge cutoffs. daily.dev provides real-time, community-validated developer content with structured taxonomy across thousands of sources. Agents can use this to stay current, get diverse perspectives, and understand what the developer community actually cares about.
These examples show how AI agents can combine daily.dev APIs with external context to create powerful developer workflows.
🔍 GitHub Repo → Personalized Feed
Scan a user's GitHub repositories to detect their actual tech stack from package.json, go.mod, Cargo.toml, requirements.txt, etc. Then:
- Fetch
/tagsto see all available tags for deterministic matching - Auto-follow matching tags via
/feeds/filters/tags/follow - Create a custom feed tuned to their stack with
/feeds/custom/ - Surface trending articles about their specific dependencies
Trigger: "Set up daily.dev based on my GitHub projects"
🛠️ GitHub → Auto-fill Stack Profile
Analyze a user's GitHub activity to build their daily.dev tech stack profile automatically:
- Scan repositories for languages, frameworks, and tools actually used in code
- Search
/profile/stack/searchto find matching technologies on daily.dev - Populate their stack via
POST /profile/stack/organized by section (languages, frameworks, tools) - Update
/profile/bio based on their primary technologies and contributions
Trigger: "Build my daily.dev profile from my GitHub"
🚀 New Project → Curated Onboarding
When a user initializes a new project or clones a repo:
- Analyze the tech choices from config files
- Create a dedicated custom feed filtered to exactly those technologies
- Build a "Getting Started" bookmark list with foundational articles
- Block irrelevant tags to keep the feed focused on the project scope
Trigger: "Help me learn the stack for this project"
📊 Weekly Digest → Synthesized Briefing
Compile a personalized weekly summary by:
- Fetching
/feeds/foryouand/feeds/popularfiltered by user's followed tags - Cross-referencing with their GitHub activity to prioritize relevant topics
- Summarizing key articles and trending discussions
- Delivering as a structured briefing with links to full posts
Trigger: Scheduled, or "Give me my weekly dev news"
📚 Research Project Workspace
When a user wants to deep-dive into a topic (e.g., "I want to learn Kubernetes"):
- Create a custom feed via
/feeds/custom/filtered to that topic - Set up a matching bookmark list via
POST /bookmarks/liststo collect the best finds - As the user reads, save articles to the list with
POST /bookmarks/ - Track learning progress: compare bookmarked posts vs. new feed items
- Adjust feed filters over time as understanding deepens (beginner → advanced content)
Trigger: "Start a research project on [topic]"
🧠 Agent Self-Improvement Feed
Agents can overcome their knowledge cutoff by maintaining their own custom feed:
- Create a custom feed via
/feeds/custom/for technologies the agent frequently assists with - Periodically fetch
/feeds/custom/{feedId}to ingest recent articles - Use
/posts/{id}to read full summaries and key points - Agent can now provide advice with current information: "As of this week, the recommended approach is..."
- Continuously adapt the feed filters based on what users are asking about
Trigger: Agent background process, or "What's new in [technology] since your training?"
🔀 Multi-Source Synthesis
Get balanced perspectives by aggregating content across publishers:
- Search
/search/postsfor a topic to find coverage from multiple sources - Use
/search/sourcesto identify authoritative publishers on the topic - Fetch posts from different sources via
/feeds/source/{source} - Synthesize diverse viewpoints into a balanced summary with citations
- Surface where sources agree vs. disagree on best practices
Trigger: "What are the different perspectives on [topic]?" or "Compare approaches to [problem]"
📈 Trending Radar
Help users stay ahead by monitoring community signals:
- Fetch
/feeds/popularto detect what's gaining traction right now - Cross-reference with user's followed tags to surface relevant trends
- Use
/feeds/discussedto find topics sparking active debate - Alert users when technologies in their stack are trending (new releases, security issues, paradigm shifts)
- Use
/tagsto fetch the full tag catalog and/search/tagsto explore adjacent trending topics
Trigger: "What should I be paying attention to?" or "What's trending in [area]?"
Rate Limits
- 60 requests per minute per user
Check response headers:
X-RateLimit-Limit- Maximum requests allowed per windowX-RateLimit-Remaining- Requests remaining in current windowX-RateLimit-Reset- Unix timestamp when the window resetsRetry-After- Seconds to wait (only when rate limited)
Errors
| Code | Meaning |
|---|---|
| 401 | Invalid or missing token |
| 403 | Plus subscription required |
| 404 | Resource not found |
| 429 | Rate limit exceeded |
Error Response Format:
{
"error": "error_code",
"message": "Human readable message"
}
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核