Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Verify Implementation · sangrokjung | DecimalAI

code reviewby sangrokjung

Verify Implementation

sangrokjung/verify-implementation

Source sangrokjung/claude-forge ↗License MIT

프로젝트의 모든 verify 스킬을 실행하여 통합 패턴 검증 보고서를 생성합니다. 기능 구현 후, PR 전, 코드 리뷰 시 사용.

SkillScore68Maintained

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

QA & Test Engineering pack

Last verified 8/14/2026

What it changes

Passed 13 of 19 test cases with the skill, and 7 of 19 without it.

Without skill36%

With skill68%

Checks it passed that the model alone missed

Matches skills using the wildcard pattern verify-auth*.
Displays status PASS for each skill and confirms readiness for code review.
Selects parallel subagents for execution when registered skill count is 6 or more.

and 6 more in the full report

8 fixed7 passed either way6 still failing1 broke

Pass-rate lift: +32 pp
Tokens: +97%
Agent turns: 0%
Response time: -49%

Model gemini-3.6-flashMeasured 8/14/2026v115 of 22 cases passed with skill · 19 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/sangrokjung-verify-implementation/SKILL.md https://app.decimal.ai/s/sangrokjung-verify-implementation/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add sangrokjung-verify-implementation, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/sangrokjung-verify-implementation/ and pins it in .decimal/skills.lock

decimalai skills add sangrokjung-verify-implementation

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/sangrokjung-verify-implementation/SKILL.md https://app.decimal.ai/s/sangrokjung-verify-implementation/SKILL.md

Raw file: /s/sangrokjung-verify-implementation/SKILL.md ↗ · machine-readable summary at /s/sangrokjung-verify-implementation.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

특정 영역의 패턴 검사만 실행하기 위해 카테고리 이름을 `auth`로 전달했을 때, 어떤 와일드카드 패턴으로 스킬 명을 필터링하나요?

What was checked, without and with the skill
Checked	Without skill	With skill
Matches skills using the wildcard pattern verify-auth*.	Missed	Passed

case-15 · gemini-3.6-flash · 8/14/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md298 linessingle file

구현 검증

목적

프로젝트에 등록된 모든 verify-* 스킬을 실행하여 통합 패턴 검증을 수행합니다:

각 스킬의 Workflow에 정의된 검사를 실행
각 스킬의 Exceptions를 참조하여 false positive 방지
발견된 이슈에 severity 레벨 분류
사용자 승인 후 수정 적용 및 재검증

verification-engine과의 역할 구분

항목	verification-engine	verify-implementation (이 스킬)
대상	기술 검증 (빌드, 타입, 린트, 테스트)	패턴 검증 (코딩 규칙, 아키텍처 패턴, 프로젝트 규약)
트리거	`/handoff-verify`	`/verify-implementation`
자동 수정	Fixable 9종 즉시 수정	사용자 승인 후 수정 (기본) 또는 `--fix`로 자동

두 시스템은 상호보완입니다. 기술 검증은 verification-engine에, 패턴 검증은 이 스킬에 위임합니다.

실행 시점

새로운 기능을 구현한 후
Pull Request를 생성하기 전
코드 리뷰 중
코드베이스 규칙 준수 여부를 감사할 때
/handoff-verify 통과 후 패턴 준수 추가 확인 시

실행 플래그

플래그	설명	기본값
`--fix`	발견 이슈 자동 수정 (사용자 확인 없이)	OFF
`--report-only`	보고서만 생성, 수정 제안 없음	OFF
`--severity <level>`	특정 심각도 이상만 보고 (CRITICAL/HIGH/MEDIUM/LOW)	LOW (전체)
`--category <name>`	특정 verify-* 스킬만 실행 (예: `--category api`)	전체

심각도 레벨

Track record

Benchmark

13 / 19

test cases passed, vs 7 / 19 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

sangrokjung / claude-forge

skills/verify-implementation/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.