← 开源
tryproduck

produck-skills

Agent skills to help you build products your users love.

AI EngineeringPrompt & ScaffoldBuild agent workflow (SDK)HTML
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
511
Star
10
Fork
+1
本周
6
贡献者
创建于 2026-06-03 · 更新于 2026-10-10 · 今日第 18076 名
主要开发者
YuvBindalLucaXavconradlin

tryproduck/produck-skills 排名第 18,076,有 511 个星标。

同类别比较

tryproduck/produck-skills 排名第 18,076,此处有 8 个同类条目;GraphRAG-Bench/GraphRAG-Benchmark 排名第 18,080。

同类别比较
名称排名指标
seratch/ChatGPT-in-Slack18,052
语言:
Python
星标数:
512
分叉数:
178
简介:
Swift demonstration of how to build a Slack app that enables end-users to interact with a ChatGPT bot
Accenture/mcp-bench18,055
语言:
Python
星标数:
511
分叉数:
69
简介:
MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
Undertone0809/promptulate18,061
语言:
Python
星标数:
511
分叉数:
43
简介:
🚀Lightweight Large language model automation and Autonomous Language Agents development framework. Build your LLM Agent Application in a pythonic way!
gkonovalov/android-vad18,067
语言:
C
星标数:
511
分叉数:
101
简介:
Android Voice Activity Detection (VAD) library. Supports WebRTC VAD GMM, Silero VAD DNN, Yamnet VAD DNN models.
GraphRAG-Bench/GraphRAG-Benchmark18,080
语言:
Python
星标数:
510
分叉数:
58
简介:
The official repo of GraphRAG-Bench for evaluating GraphRAG models. "When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation". (ICLR'26)
JimLiu/claude-agent-kit18,082
语言:
TypeScript
星标数:
510
分叉数:
72
Muvon/octocode18,085
语言:
Rust
星标数:
510
分叉数:
59
NVIDIA-ISAAC-ROS/isaac_ros_pose_estimation18,086
语言:
C++
星标数:
510
分叉数:
58
简介:
Deep learned, NVIDIA-accelerated 3D object pose estimation
关键参数与规格
关键参数与规格
参数值
语言HTML
类别AI Engineering
子类别Prompt & Scaffold,Build agent workflow (SDK)
关键词Context engineering, Documentation, PRD, Tool use
星标数511
分叉数10
贡献者6
创建日期2026-06-03
更新日期2026-10-10
1 天星标数0
7 天星标数1
排名18,076
上次排名17,841
排名变化-235
7 天星标排名11,574
上次 7 天星标排名11,621
7 天星标排名变化47
总星标排名19,055
上次总星标排名19,027
总星标排名变化-28
README 摘录

🦆 Produck Skills **High-quality, user-experience-centered skills for your coding agents. ** This repository is our open-source, documentation-driven collection of agent skills to help you build products users love. The skills are available the next time your agent starts. | | | Act on real in-context user feedback: pull a feedback ticket's full context through the Produck MCP and drive a feedback → aligned PRD → build loop. | | | Build a premium, fully-animated product-demo / launch video from a written brief. Scene

-by-scene motion graphics with camera moves, real UI mockups, and a complete original sound kit, rendered from HTML + CSS + GSAP to MP4 via HyperFrames. Ships a runnable example film and a 25-sound synthesized SFX kit. | More user-experience skills are on the way. Screenshots were captured at with and combined into one before/after asset so the improvement is reviewable at a glance. It replaces fake dashboard polish with domain artifacts: opportunity memos, accepted/rejected evidence, and decision

briefs. Benchmark source files live in , the category-first rubric lives in , and the bespoke interaction guidance lives in . The plugin reads it at runtime; set it **before** the MCP tools will work (the skills work without it). md for the skill-authoring contract (folder layout, required frontmatter, and the PR checklist). The bar is high-quality, UX-centered skills only. ** Produck enables apps to capture in-context feedback from their users and rapidly ship features and fixes that improve

product-market fit. com 🐙 GitHub: @tryproduck License Apache-2.

常见问题

记录了多少星标和分叉?

tryproduck/produck-skills 有 511 个星标和 10 个分叉。

仓库排名是多少?

tryproduck/produck-skills 排名第 18,076。

记录的语言和类别是什么?

tryproduck/produck-skills 有 511 个星标,语言为 HTML,类别为 AI Engineering。

哪个仓库排名最接近?

tryproduck/produck-skills 与 GraphRAG-Bench/GraphRAG-Benchmark 比较,后者排名第 18,080,有 510 个星标。

README

🦆 Produck Skills

High-quality, user-experience-centered skills for your coding agents.

This repository is our open-source, documentation-driven collection of agent skills to help you build products users love. Each skill is a folder of markdown that teaches a coding agent (Claude Code, Cursor, Codex, Copilot, and others) how to ship features and fixes that your users want to improve product-market fit — starting with turning messy user requests into context-rich PRDs your agents can actually execute.


Install

One line installs every skill in this repo into your coding agent:

npx skills add tryproduck/produck-skills

That's it. It uses the open skills CLI (no global install, just npx) and works across 70+ agents — Claude Code, Cursor, Codex, Copilot, and more. The skills are available the next time your agent starts.


Skills Catalog

Skill What it does
user-alignment Turn vague or messy user requests into aligned, agent-executable PRDs — with scope, bounded phases, testable acceptance criteria, and explicit do-not-do boundaries.
produck-feedback Act on real in-context user feedback: pull a feedback ticket's full context through the Produck MCP and drive a feedback → aligned PRD → build loop. Pairs with user-alignment.
demo-studio Build a premium, fully-animated product-demo / launch video from a written brief. Scene-by-scene motion graphics with camera moves, real UI mockups, and a complete original sound kit, rendered from HTML + CSS + GSAP to MP4 via HyperFrames. Ships a runnable example film and a 25-sound synthesized SFX kit.
taste Improve website visual taste with a screenshot-driven hierarchy, trust, spacing, CTA, and consistency loop — so agents ship visibly better UI instead of generic polish.

More user-experience skills are on the way.


Taste benchmark

We ran a one-shot website improvement benchmark on the same intentionally flawed fictional SaaS landing page:

  1. Baseline — feature-led platform copy, generic dashboard UI, weak proof, and noisy hierarchy.
  2. Taste-guided improvement — the same page rebuilt with the taste skill's category thesis, worldview sequence, domain artifacts, rubric, and screenshot verification loop.

Screenshots were captured at 1440 × 1100 with npx -y chrome-devtools-axi and combined into one before/after asset so the improvement is reviewable at a glance.

Variant Category idea Worldview Hierarchy Clarity Trust Rhythm CTA gravity Domain specificity Consistency
Baseline 1 1 1 2 1 1 2 1 1
Taste-guided improvement 5 5 5 5 4 5 5 5 5

The taste-guided pass is built around one category idea — the judgment layer for product feedback — and opens with the worldview that feedback is abundant while judgment is scarce. It replaces fake dashboard polish with domain artifacts: opportunity memos, accepted/rejected evidence, and decision briefs.

Benchmark source files live in examples/taste-benchmark, the category-first rubric lives in skills/taste/references/taste-principles.md, and the bespoke interaction guidance lives in skills/taste/references/immersive-landing-pages.md.


Produck MCP & plugin

The produck-feedback skill drives the Produck MCP — a hosted server that gives your agent two tools over your own feedback:

  • search_feedback — find relevant feedback tickets (filter by domain).
  • get_feedback — load one ticket's full context: the user's written/spoken feedback, reconstructed page HTML, annotation markers, session activity, and a generated design doc.

Both installs need a Produck MCP token — mint one at tryproduck.com/app → MCP (looks like mcp_live_…). The plugin reads it at runtime; set it before the MCP tools will work (the skills work without it).

Claude Code — plugin (skills + MCP)

# 1) in your shell: save your token
mkdir -p ~/.produck && echo "mcp_live_YOUR_TOKEN" > ~/.produck/mcp_token
# 2) in Claude Code:
/plugin marketplace add tryproduck/produck-skills
/plugin install produck@produck

Codex — plugin (skills + MCP)

# 1) in your shell: export your token
export PRODUCK_MCP_TOKEN=mcp_live_YOUR_TOKEN

# 2) add the marketplace, then enable "produck" from the /plugins browser
codex plugin marketplace add tryproduck/produck-skills

Any other agent

Install the skills with npx skills add tryproduck/produck-skills, then add the MCP server using your agent's native config — see skills/produck-feedback/references/connect-mcp.md for Cursor, opencode, manual Codex, and manual Claude Code snippets.


Contributing

Want to add a skill? See CONTRIBUTING.md for the skill-authoring contract (folder layout, required frontmatter, and the PR checklist). The bar is high-quality, UX-centered skills only.


About Produck

These skills come from the team building Produck — Build products your users love.

Produck enables apps to capture in-context feedback from their users and rapidly ship features and fixes that improve product-market fit.

License

Apache-2.0

排名相邻
同类项目