Dapei Skills Pack En — Testing skill for Claude Code
Quality-gate agent skills: spec-as-contract, no-mock rule, evidence-based verification.
How to install Dapei Skills Pack En
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open shuilinh/dapei-skills-pack-en and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Dapei Skills Pack En does
Quality-gate agent skills: spec-as-contract, no-mock rule, evidence-based verification. Three SKILL.md skills + shared check library. Works with Claude Code / Cursor / pi / any agent that reads SKILL.md — bilingual triggers (EN + ZH).
Alternatives in Testing
- Pua — Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completi 19.5k ★
- Deslop Reborn — One iteration of the IronClaw Reborn de-slop loop — take ONE Reborn crate, fan out parallel review sub-agents 12.6k ★
- Langgraphjs — by langchain-ai - Offers comprehensive build and test commands with detailed TypeScript style guidelines, laye 2.7k ★
README
Dapei · General Quality Skills Pack (agent-skills-quality-pack)
A pack of general-purpose skills for AI coding agents: the methodology of "spec is contract, no mock implementations, evidence-based acceptance" solidified into SKILL.md assets that agents can read.
Included
| Skill | Role |
|---|---|
project-skeleton |
Every application must first have the three-layer universal foundation (engineering / interface skeleton / basic functions) |
project-completeness |
Complete implementation: spec-as-contract, no fake implementations, cross-feature collaboration, full lifecycle |
strict-verification |
Acceptance must come with evidence; verbal "all green" is forbidden |
shared/anti-patterns-and-checks.md |
Shared anti-pattern & acceptance-check library — the single source of truth for the three general skills (§1 Basic functions / §2 Interaction / §3 Resilience & security / §4 Active hunt / §5 Hard-fail criteria) |
Note: `dapei-assembler` is a repo-level skill (it depends on the assembler repo's `src/lib/skillGates.ts` and other code). It is not shipped with this pack; it belongs to the dapei-assembler project repository itself.
Design notes
- Language: this pack is the English pack. The skill bodies are in English, but each skill's frontmatter
descriptionkeeps Chinese trigger phrases (e.g. "做应用", "开发项目", "功能出问题") on purpose — the pack is meant for a bilingual audience, and an agent serving a Chinese-speaking user must still fire when the user says "帮我做一个项目" in Chinese. English-only users see no downside: the Chinese phrases just never match. - Single source of truth: inside the pack, all anti-pattern / check content lives in
shared/anti-patterns-and-checks.md; the three SKILL.md files only reference it and never duplicate it. Edit the shared file, not the skills. - Pack vs. single-skill copies: install the whole pack directory. Copying one skill folder on its own breaks its
../shared/...and `references/
Related Skills
Flutter Mobx Kit
Agent toolkit for Flutter + MobX: AGENTS.md as the single instruction source, 15 on-demand playbooks, 17 ADRs,
Shape
Shape work through a relentless interview — interrogate an idea, a transcript, existing code, or an existing s
Writing Craft
A blind tested skill for better creative writing. Nine signals three AI judges named after scoring 50 samples
Pi Webgl Scroll Site
A verified AI-agent skill for building scroll-driven WebGL/three.js sites: working spine, measured gotchas, nu
Visual Flow Verify
以 Figma node 為節點的可重播視覺驗證:確定性 Playwright 重播、像素比對設計稿、DOM 對帳 mock 種子、失敗才 AI 裁決;GUI 給人、REST 給 AI agent|Replayable
Agentarena
Adversarial coding-agent evaluation harness that pits Claude Code, Codex, and Gemini CLI against the same repo
Related Agents
Development Orchestrator Agent
Owns everything between contract lock and Gate 2 — branch verification, conditional shared-package-agent, para
Canvas To Code Data Binder
Classifies each visual unit's data source. Decides backend (wire to an existing service) vs mock (emit a JSON
Context7 Library Checker
Use in code reviews to check library usage against up-to-date documentation. Detects deprecated APIs, best pra