一键导入
verification-loop
CDD (Compile-Driven Development) verification system. No tests — compile + LSP is the sole truth.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
CDD (Compile-Driven Development) verification system. No tests — compile + LSP is the sole truth.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | verification-loop |
| description | CDD (Compile-Driven Development) verification system. No tests — compile + LSP is the sole truth. |
| compatibility | opencode |
| metadata | {"origin":"ECC-CDD"} |
A compile-driven verification system. 不运行任何测试。唯一的验证标准是编译通过 + LSP 无 Error。
Invoke this skill:
自动检测项目类型并运行对应命令:
# TypeScript/Node.js
npx tsc --noEmit --pretty 2>&1 | head -30
# OR npm run build / pnpm build
# C# / Unity
dotnet build --no-restore 2>&1 | tail -20
# C++ / Unreal / CMake
cmake --build build/ 2>&1 | tail -20
# Rust
cargo check 2>&1 | tail -20
# Go
go build ./... 2>&1 | tail -20
# Python (type check)
pyright . 2>&1 | head -30
If build fails:
sequential-thinking for root cause analysisUse mcp-language-server to verify:
# JavaScript/TypeScript
npm run lint 2>&1 | head -30
# Python
ruff check . 2>&1 | head -30
# Check for secrets
grep -rn "sk-" --include="*.ts" --include="*.js" --include="*.cs" . 2>/dev/null | head -10
grep -rn "api_key" --include="*.ts" --include="*.js" --include="*.cs" . 2>/dev/null | head -10
# Check for debug logging
grep -rn "console.log\|Debug.Log\|UE_LOG" src/ 2>/dev/null | head -10
# Show what changed
git diff --stat
git diff HEAD~1 --name-only
Review each changed file for:
After running all phases, produce a CDD verification report:
CDD VERIFICATION REPORT
=======================
Compile: [PASS/FAIL] (Exit Code: X)
Types/LSP: [PASS/FAIL] (X errors)
Lint: [PASS/FAIL] (X warnings)
Security: [PASS/FAIL] (X issues)
Diff: [X files changed]
Overall: [READY/NOT READY] for PR
Issues to Fix:
1. ...
2. ...
For long sessions, run verification after major changes:
Set a mental checkpoint:
- After completing each function
- After finishing a component
- Before moving to next task
Run: /verify
This skill complements PostToolUse hooks but provides deeper verification. Hooks catch issues immediately; this skill provides comprehensive CDD review.
Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
Engineering operating model for teams where AI agents generate a large share of implementation output.
REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, or user says "just do it".