Verify logo

Verify

Community
jh941213
verify

작업 완료 후 코드 검증 (타입체크, 린트, 테스트, 빌드). Triggers on: 검증, verify, 테스트 돌려, 빌드 확인, 타입체크. NOT for: E2E 테스트, 코드 작성, 구현.

Overview

Publisherjh941213
Repositorymy-cc-harness
Skill nameverify
Stars
125
Forks
35
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by jh941213 on GitHub. Read the source before you install it.

Installation

Install the Verify AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jh941213/my-cc-harness.git /tmp/my-cc-harness
mkdir -p .claude/skills
cp -r /tmp/my-cc-harness/skills/verify .claude/skills/verify
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Verify in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Verify on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Verify is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

코드 검증

TaskCompleted 훅(verify-task-quality.sh)이 자동 실행하는 검증과 동일합니다. 훅 미발동 상황(수동 검증 요청, 훅 미설치 환경)에서 이 스킬을 사용하세요.

작업 완료 후 코드를 검증합니다. 순서대로 실행하며, 각 단계 통과 후 다음으로 진행.

Step 1: 프로젝트 감지

파일스택타입체크린트테스트빌드
package.jsonNode/TSnpx tsc --noEmitnpx eslint . / npx biome check .npx vitest run / npx jestnpm run build
pyproject.tomlPythonmypy . / pyright .ruff check .pytest -q
go.modGogo vet ./...golangci-lint rungo test ./...go build ./...
Cargo.tomlRustcargo clippycargo testcargo build
bash
# 자동 감지
[ -f package.json ] && cat package.json | python3 -c "import sys,json; s=json.load(sys.stdin).get('scripts',{}); print('\n'.join(f'{k}: {v}' for k,v in s.items()))"
[ -f pyproject.toml ] && echo "Python project detected"
[ -f go.mod ] && echo "Go project detected"
[ -f Cargo.toml ] && echo "Rust project detected"

Step 2: 검증 순서 (실패 시 즉시 수정)

2-1. TypeScript 타입체크

bash
npx tsc --noEmit

실패 시: 타입 에러 수정 → 재실행. 3회 실패 시 사용자에게 에스컬레이션.

2-2. 린트

bash
# ESLint
npx eslint . --max-warnings=0
# 또는 Biome
npx biome check .
# Python
ruff check .

실패 시: --fix 자동 수정 시도 → 수동 수정 → 재실행.

2-3. 테스트

bash
# Vitest
npx vitest run
# Jest
npx jest --passWithNoTests
# pytest
pytest -q

실패 시: 실패 테스트 분석 → 코드 수정 (테스트 수정은 최후 수단) → 재실행.

2-4. 빌드

bash
npm run build

실패 시: 빌드 에러 분석 → 수정 → 재실행.

2-5. 순환참조 탐지 (JS/TS 프로젝트)

bash
npx madge --circular --extensions ts,tsx src/ 2>/dev/null

순환참조 발견 시: WARNING으로 보고. 새로 추가된 순환만 수정 대상.

2-6. 데드코드 탐지 (JS/TS 프로젝트)

bash
npx knip --no-exit-code 2>/dev/null | head -50

미사용 export/파일/의존성 발견 시: INFO로 보고. 자동 수정하지 않음.

2-7. 시크릿 스캔

bash
gitleaks detect --source . --no-git -v 2>&1 | head -20

시크릿 발견 시: CRITICAL. 즉시 보고 후 수정 유도.

2-8. AI 슬롭 패턴 탐지 (ast-grep)

bash
# 불필요한 console.log
sg --pattern 'console.log($$$)' --lang ts src/ 2>/dev/null | head -10
# any 타입 사용
sg --pattern '$A as any' --lang ts src/ 2>/dev/null | head -10

발견 시: WARNING으로 보고.

Step 3: 결과 보고

단계상태상세
typecheckPASS/FAIL/SKIP에러 수 또는 "도구 미감지"
lintPASS/FAIL/SKIP경고/에러 수
testPASS/FAIL/SKIPN passed, M failed
buildPASS/FAIL/SKIP성공 또는 에러 요약
circularPASS/WARN/SKIP순환참조 수 (madge)
deadcodeINFO/SKIP미사용 export/파일 수 (knip)
secretsPASS/CRITICAL/SKIP시크릿 탐지 수 (gitleaks)
ai-slopPASS/WARN/SKIPconsole.log/any 수 (ast-grep)

판정: PASS = exit code 0, FAIL = 3회 재시도 소진, SKIP = 해당 도구 미감지 전체 판정: CRITICAL 있으면 FAIL. 모든 PASS/WARN/INFO/SKIP → PASS. typecheck/lint/test/build 중 FAIL → FAIL.

에러 카테고리별 수정 전략

카테고리우선순위수정 방법
TYPE높음출력에서 file:line 추출 → 해당 파일 Read → 타입 수정
LINT중간--fix 자동 수정 먼저 → 수동 수정
TEST높음실패 테스트 분석 → 코드 수정 (테스트 수정은 최후 수단)
BUILD높음빌드 로그 분석 → import/export 문제 우선 확인

최대 재시도

각 단계 최대 3회 시도. 3회 실패 시 멈추고 사용자에게 보고.

Frequently asked questions

What does the Verify AI skill do?

작업 완료 후 코드 검증 (타입체크, 린트, 테스트, 빌드). Triggers on: 검증, verify, 테스트 돌려, 빌드 확인, 타입체크. NOT for: E2E 테스트, 코드 작성, 구현.

Why use Verify on TypingMind?

Because you install it once and use it with any model. Verify is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Verify in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jh941213/my-cc-harness/tree/main/skills/verify. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Verify?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Verify?

As many as you like. As long as a model supports skills, you can use Verify with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Verify AI skill free?

It is published on GitHub by jh941213. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇