惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

U
Unit 42
N
News and Events Feed by Topic
S
Schneier on Security
G
GRAHAM CLULEY
Scott Helme
Scott Helme
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
GbyAI
GbyAI
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
C
CERT Recently Published Vulnerability Notes
T
The Exploit Database - CXSecurity.com
C
Cisco Blogs
T
The Blog of Author Tim Ferriss
Cisco Talos Blog
Cisco Talos Blog
P
Privacy & Cybersecurity Law Blog
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
博客园 - 司徒正美
Blog — PlanetScale
Blog — PlanetScale
Project Zero
Project Zero
MyScale Blog
MyScale Blog
Recent Commits to openclaw:main
Recent Commits to openclaw:main
Apple Machine Learning Research
Apple Machine Learning Research
小众软件
小众软件
The Last Watchdog
The Last Watchdog
Vercel News
Vercel News
The Cloudflare Blog
C
Check Point Blog
Help Net Security
Help Net Security
Microsoft Security Blog
Microsoft Security Blog
AI
AI
Simon Willison's Weblog
Simon Willison's Weblog
云风的 BLOG
云风的 BLOG
M
MIT News - Artificial intelligence
Stack Overflow Blog
Stack Overflow Blog
腾讯CDC
NISL@THU
NISL@THU
S
Security @ Cisco Blogs
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
S
SegmentFault 最新的问题
MongoDB | Blog
MongoDB | Blog
C
CXSECURITY Database RSS Feed - CXSecurity.com
T
Threatpost
AWS News Blog
AWS News Blog
Cloudbric
Cloudbric
N
News and Events Feed by Topic
PCI Perspectives
PCI Perspectives
S
Securelist
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
V
Vulnerabilities – Threatpost
S
Secure Thoughts

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店 GitHub - EdoardoBambini/Agent-Armor-Iaga: AI agents are getting tool access — shell, file system, databases, APIs, secrets. But **nobody is governing what they actually do with it**. Frameworks like LangChain, CrewAI, AutoGen, and Claude Code give agents the power to execute. Agent Armor gives you the power to control, audit, and approve every single action before it happens. HN Vibes — Week 15, Apr 7–13 2026 GitHub - chojs23/ec: Easy terminal-native 3-way git mergetool vim-like workflow GitHub - SethPyle376/hiraeth: Local AWS emulator focused on fast integration testing, with SQS support, SQLite-backed state, and a debug-friendly web UI. GitHub - JakOb-dotcom/cloud-sandbox-security-analysis: Technical analysis and Proof of Concept (PoC) regarding environment variable exfiltration in containerized cloud sandboxes via side-channel data leaks. Springboards - Flint Alpha Show HN: A simpler coding agent harness GitHub - audiodude/sudomake-friends GitHub - 256thFission/mini-mythos: OSS clone of Anthropic’s Mythos harness to locate C/C++ memory vulnerabilities Show HN: OpenParallax: OS-level privilege separation for AI agent execution Hacker News Sorted - Chrome 应用商店 Show HN: How to Install Docker on Ubuntu 24.04 LTS: Complete 2026 Guide GitHub - himanshudongre/smriti GitHub - sverrirsig/claude-control: macOS desktop dashboard for monitoring and managing multiple Claude Code sessions GitHub - ory/dockertest: Write better integration tests! Dockertest helps you boot up ephermal docker images for your Go tests with minimal work. Chiral - Chrome 应用商店 Show HN: Two Claudes collaborating through shared memory on a $100 mini-PC GitHub - pmichaillat/latex-cv: Minimalist LaTeX template for academic CVs GitHub - oguzbilgic/posse: A web UI for Anthropic Managed Agents. GitHub - sshiraz/depsly: Dependency risk analysis tool for npm packages ABI Add safari/agent-harness — Safari browser automation via safari-mcp by achiya-automation · Pull Request #212 · HKUDS/CLI-Anything GitHub - Halfblood-Prince/trustcheck: Verify PyPI package attestations and improve Python supply-chain security GitHub - oguzbilgic/kern-ai: Agents that do the work and show it. GitHub - bruits/satteri: High-performance Markdown and MDX processing for the JavaScript ecosystem GitHub - tylergibbs1/feedstock: High-performance web crawler and scraper for TypeScript, powered by Bun and Playwright GitHub - Grimm67123/grimmbot: The self-improving sandboxed and open-source AI agent. With persistent memory and scheduling. GitHub - whitevanillaskies/whitebloom: Local whiteboard that blooms. GitHub - hwdsl2/docker-whisper: Docker image for a self-hosted Whisper speech-to-text server with speaker diarization and OpenAI-compatible transcription and translation APIs. Powered by faster-whisper. Supports all Whisper models, NVIDIA GPU (CUDA) acceleration, JSON/SRT/VTT output, SSE streaming, offline mode, and multi-arch (amd64, arm64). GitHub - yisding/reviewwiggum GitHub - MarwanAlsoltany/serrors: Structured errors for Go: sentinel hierarchies, typed data, custom formatting, and slog integration. GitHub - soatok/age-php GitHub - Luthiraa/markitme GitHub - stagas/rtdiff: realtime git diff gui and AI-assisted commits GitHub - tombedor/excalicharts GitHub - wh1le/excalidraw-edit: Open and edit .excalidraw files from the terminal. Offline, auto-saves to disk. MalExt Sentry - Malicious Extension Scanner - Chrome 应用商店 GitHub - syi0808/asciianimesvg: Generate animated ASCII art SVGs from text. CLI, Rust library, WASM, and web editor. GitHub - zaina-ml/ml_forge: A visual-based graph node editor for training computer vision models. GitHub - anakin87/llm-rl-environments-lil-course: 🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models GitHub - takaakit/superpowers-uml: Superpowers-UML modifies Superpowers to ensure a software development workflow in which AI agents design through UML modeling. AdriByte Studio - Sviluppo Web e Soluzioni Digitali GitHub - chouligi/angel-copilot: Your personalized Angel Investment Advisor Show HN: MoodSense AI (ML and FastAPI and Gradio, Deployed on Hugging Face) Moodsense Ai - a Hugging Face Space by aman179102 GitHub - agenteractai/lodmem: Level Of Detail Context Management for Agents GitHub - ostefani/subnetlens: A fast, concurrent network scanner with a TUI and plain-text CLI, built in Go. It discovers live hosts on your network, scans their open ports, resolves hostnames, and fingerprints operating systems—delivered. Cyber Pulse: Agentic Intel - Apps on Google Play Whisper API: Self-Hostable Speech to Text Transcription The Agent-Web Protocol Stack: A Research Thesis GitHub - msmarkgu/RelayFreeLLM: A restful API designed to route user prompts to various AI model providers. Show HN: Provepy – A Python decorator that proves your code using Lean and LLMs Show HN: Pardonned.com – A searchable database of US Pardons GitHub - patrickdappollonio/dux: Dux is a terminal UI that lets you run multiple AI coding agents side by side, each in its own git worktree, with full companion terminals, macros, commit generation, and a command palette that knows more tricks than you do. kMC Crystal Simulator Show HN: HyperFlow – A self-improving agent framework built on LangGraph GitHub - stef41/vibescore: 🎵 Grade your vibe-coded project. One command, instant letter grade across security, quality, dependencies, and testing. GitHub - stef41/lmscan: 🔍 Detect AI-generated text and fingerprint which LLM wrote it. Open-source GPTZero alternative. Zero dependencies, works offline. imgur.com GitHub - visionscaper/collabmem: Enabling long-term collaboration with Agentic AI - building up episodic and world model memory over time with in-context awareness 在 Steam 上购买 FriedrichAI: Offline AI 立省 10% GitHub - atripati/ark: AI Runtime Kernel — a context operating system for AI agents. Eliminates tool bloat, loads only what’s needed, and gives LLMs their reasoning space back. GitHub - nowork-studio/toprank: Open-source Claude Code skills for SEO, SEM, Google Ads GitHub - tacomanator/sash: Lightweight macOS menu bar app for reliably cycling through windows of the current application. Appents | Social Media Management for Product-First Teams GitHub - pnhoang/youtube-spam-blocker: Automatically detects and hides spam messages in YouTube Live chat. Set rate limits, keyword filters, and block repeat offenders. GitHub - decisionnode/DecisionNode: CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable. GitHub - AvaCodeSolutions/django-email-learning: An open source Django app for creating email-based learning platforms with IMAP integration and React frontend components. The $100K Gap in Kubernetes Security Tooling Function Calling Harness: From 6.75% to 100%
GitHub - unboundinnov/specdd: Spec-Driven Development as a single Agent Skill
diablovox · 2026-05-15 · via Hacker News: Show HN

Spec-Driven Development as a single Agent Skill. Drop it in, type naturally, ship features that don't embarrass you in two weeks.

specdd turns vague, top-of-mind feature requests into production-grade specs before code is written — without a CLI, without four config files, without ceremony you don't need. One skill, any modern AI coding agent: Claude (Code, Desktop, Web), Codex, Copilot, Cursor, Windsurf, Gemini CLI, anything else that reads SKILL.md or AGENTS.md-style instructions.

You: "build me a settings page where users can change their email"

specdd:
  → triages the scope (Feature)
  → asks the 2-3 questions you didn't think to address (verification email?
    active sessions? what's the success state?)
  → produces a tech-free spec + a 2-minute technical plan
  → only after you say "ship it" → writes code
  → runs the production-grade checklist before declaring done

No npx, no uv tool install, no specify init. Just a folder.


Why specdd exists

Two patterns broke the same way:

Vibe-coding — describe a feature in one line, get code that compiles and looks right but misses the empty state, the error state, the keyboard handling, the "what happens when the user double-clicks the button" — discovered in production.

Heavy spec frameworks like github/spec-kit — fix the rigor problem but introduce a CLI, four mandatory artifacts, and ceremony that's overkill for solo and one-off work.

specdd splits the difference. Spec-driven development that scales down to a 15-minute task and scales up to a multi-day project — same workflow, different ceremony.


What you get

  • One opinionated workflow — triage → interview → spec → plan → (tasks) → build & verify
  • Question-asking by default — interviews you for the gaps your one-liner left, instead of guessing
  • Tech-free specs — what & why for the user, separated from how for the agent
  • Production-grade checklist before "done" — empty/error/loading states, a11y, keyboard, mobile, observability
  • UX defaults baked in — five-states rule, confirmation patterns, optimistic updates, accessible focus management
  • Scales to scope — Quick (5-line inline mini-spec), Feature (spec + plan inline), Project (spec + plan + tasks as files)
  • Surface-agnostic — same skill in Claude Code, Claude.ai, Codex CLI, Cursor, Copilot, Windsurf

Install

Claude Code (recommended)

/plugin marketplace add unboundinnov/specdd
/plugin install specdd@specdd

That's it. The skill activates automatically when you ask for any feature work.

Claude Code (manual, no plugin system)

git clone --depth=1 https://github.com/unboundinnov/specdd /tmp/specdd-src
cp -r /tmp/specdd-src/plugins/specdd/skills/specdd ~/.claude/skills/
rm -rf /tmp/specdd-src

Or scope to a single project: copy into .claude/skills/ inside the project instead.

Claude.ai (Pro / Team / Enterprise / Max)

  1. Download specdd.zip from Releases (or zip plugins/specdd/skills/specdd/).
  2. Claude.ai → Settings → Capabilities → Skills → Upload skill.
  3. Upload the zip.

Codex CLI

mkdir -p ~/.codex/skills
git clone --depth=1 https://github.com/unboundinnov/specdd /tmp/specdd-src
cp -r /tmp/specdd-src/plugins/specdd/skills/specdd ~/.codex/skills/
rm -rf /tmp/specdd-src

Cursor / Copilot / Windsurf / Aider / others

These agents don't natively load SKILL.md yet. Copy the content of SKILL.md into the agent's instructions file:

  • Cursor: .cursor/rules/specdd.mdc (or legacy .cursorrules)
  • GitHub Copilot: .github/copilot-instructions.md
  • Windsurf: .windsurfrules
  • Aider: CONVENTIONS.md referenced from .aider.conf.yml

Reference files in references/ can be copied alongside or inlined.


How it works

Phase What happens
1. Triage Skip / Quick / Feature / Project — surfaced so you can correct it.
2. Interview 2–5 right questions for your request type, tappable where possible. Doesn't ask what it can infer.
3. Spec Tech-free: who / what / why / states / edge cases / out-of-scope / non-functional. You sign off.
4. Plan Tech approach: stack, files, decisions with rationale, alternatives, risks. <2 minutes to read.
5. Tasks (Project scope only) Ordered, verifiable units with explicit done-signals.
6. Build & verify Implement against spec; deviations require a spec update. Production checklist before "done".

SKILL.md is the entry point; templates, checklists, and examples are in references/.


specdd vs spec-kit

specdd github/spec-kit
Install Copy a folder, or one /plugin install uv tool install, specify init, CLI per-project
Surface Any agent that reads SKILL.md / instructions 30+ agents via Specify CLI
Ceremony Scales: 5 lines for a small change, 3 files for a project Mandatory: constitution.md, spec.md, plan.md, tasks.md
Slash commands None — conversational /speckit.specify, /speckit.plan, /speckit.tasks, /speckit.implement
UX defaults Baked in (5-states rule, a11y, confirmation patterns, motion) Project-defined in constitution.md
Best for Solo, indie, one-off features, mid-size teams Larger teams, established projects, formal SDD adoption

What specdd inherits from SDD literature (and spec-kit): the spec → plan → tasks workflow shape, the spec.md / plan.md / tasks.md filenames, the "tech-free spec" framing. These are general SDD concepts (Spec Driven Development pre-dates spec-kit), and keeping the filenames means specs migrate cleanly if you ever adopt spec-kit later.

What's specdd's own: the triage step (scale to scope), the interview phase with tappable options, the build & verify phase with the production-grade checklist, UX-first opinionation with the five-states rule, the common-sense gates. No CLI, no slash commands, no constitution.


Examples

See references/examples/:


Contributing

Issues and PRs welcome. Particularly interested in:

  • Request-type interview playbooks (the more specific, the better)
  • Surface-specific install instructions for new agents
  • Worked examples from real projects

Open an issue first for substantial changes; keep PRs focused; match the existing tone.


License

MIT. See LICENSE.


Credits

Inspired by, and respectfully different from, github/spec-kit, BMAD, and Kiro. Built on the Agent Skills format by Anthropic.

If specdd helps you ship better, a ⭐ helps people find it.