Каталог навыков агентов

탭/모달의 React.lazy + Suspense + ErrorBoundary 패턴을 검증합니다. 탭 컴포넌트 추가/수정 후 사용.

Verify legacy code against QA test cases to confirm migration completeness.

Confirms or rejects findings from review-llm-artifacts before deletes or risky refactors. Loads review-verification-prot...

Prove sign-in lands the user where they should be, sign-out really ends the session so a protected page sends them back...

자율 작업 루프에서 자기 수정 동작의 가이드라인. 4-Level Completion Criteria, 재시도 전략, 루프 탈출 조건을 정의. Use when running autonomous execution loo...

Verify a change in the maestro repository on the running product - install the checkout into a scratch HOME, doctor it,...

마케팅 그룹(마케팅/셔틀관리) 탭의 핵심 기능을 검증합니다. 마케팅 관련 컴포넌트 수정 후 사용.

Use when a GitHub issue, a GitHub pull request, or a JIRA issue must have its pull request brought to a merge-ready stat...

Verification checklist to walk before declaring a tt-emule mock complete. Use after implementing a stub (typically at th...

Drive one msp-skills connector (skills/<slug>, any of the 84) the way a user does and prove it with evidence: install.sh...

Boot (or reuse) the TBox-Mock-Play AVD, install the debug APK, drive the launcher, and capture screenshots to verify UI...

PR で変えた画面を、手元の環境で Playwright を使って操作して動作を確かめ、スクリーンショットと動画を撮って PR に貼る。確認の原則・組み立て方・データの用意と後片付け・塗りつぶしの検算・撮り方・判定・報告の組み立てを持ち、共...

Verify Open Pstack through installed Codex and Claude Code skills and its shipped Bun CLIs. Use for real behavior proof,...

Prove a UI that updates before the server answers puts things back and says so when the request fails, and keeps the cha...

Verify outbound shipments against order, pick, pack, label, document, carrier, staging, and handoff evidence.

Verify the user-facing outcome, and verify that your metric can even see the defect class you care about.

Pattern for verifying your output matches required schema before completing. Use before writing final output to ensure v...

After write_file, re-read the deliverable (or ls + hexdump/line-print) and re-check the last format clauses before finis...

Never assume something you can cheaply verify. On the Max plan, token saving is NOT the priority — correctness and quali...

Prove the next page of a list, or the next batch of an infinite scroll, loads NEW rows from the server, repeats none, an...

Verify Paperclip from a source checkout, published npm install, or existing staging or production stack. Select the envi...

Verify AI agent patterns including loop safety, retry limits, tool consistency, context size, and graph cycle analysis....

역할별 탭 접근권한, 버튼 노출, 권한 체크 로직을 검증합니다. 권한/역할 관련 코드 수정 후 사용.

Verify persistence.xml configuration before git push. Use before pushing code to ensure persistence.xml uses environment...

Workflow for verifying phase completion

Use when a PlayCanvas rendering change is meant to leave the image unchanged, to prove it with deterministic captures an...

Score-based convergence loop for adversarial plan verification. Spawns dynamic agent team (3 or 5 agents) that autonomou...

Use when validating that an implementation plan covers all requirements from a spec or architecture doc. Use after writi...

Review PRD.md for gaps, contradictions and unverifiable claims, write an improved PRD.md and record the findings in PRD-...

화장품 제품 정보 검증 프로세스. 수집된 제품 정보의 진위여부를 확인하고 공식 출처를 검증합니다.

QC gate for a generated static ad image — verify the file opens, matches the requested dimensions, shows the correct pro...

Prepare and verify a production release using an exact revision, required checks, deployment evidence, health probes, an...

Validate distilled prompts preserve essential instructions

Verify a proposed architecture diagram against the actual codebase, selectively checking existing vs new components. Use...

Drive the pstack agent harness the way a session experiences it and prove its behaviors with evidence. Use for /verify-p...

Check public-facing copy against supplied evidence and current public sources, classify every material claim, and produc...

Run and verify this repo's games for real: which of them build and which are single files, how to drive a game in the br...

Verify code quality including naming conventions, organization, documentation, and general best practices. Use when aske...

React Query 캐시키/enabled/staleTime 일관성과 쿼리 패턴을 검증합니다. React Query 훅 수정 후 사용.

Read-only pre-flight verification of a staged release candidate (RC) for `<upstream>`. Checks artefact integrity (GPG si...

Create original short videos using the 角色卡验真｜四类证据锁定角色 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wan...

Use when checking whether a manuscript's references are real. Audits each citation against PubMed and CrossRef, flags fa...

Audit-only verification of manuscript references against PubMed and CrossRef. Detects fabricated or mismatched citations...

Verify regular or extended-stable OpenClaw releases against the exact publication surfaces, workflow identities, package...

Verify an MarketingClaw release is fully published across GitHub, npm, plugins, ClawHub, package smoke, and live Gateway...

Verify all stakeholder requirement reports exist and are valid before synthesis

모바일/태블릿/데스크톱 반응형 TailwindCSS 패턴 일관성을 검증합니다. UI 컴포넌트 수정 후 사용.

バックアップ → リストアを偽の HOME で通しで流し、新規マシンでリストアが成立するかを実測する。scripts/ や置き場の構成を変更した直後に使う。ユーザーが「リストアを検証して」「新規マシンで動くか確かめて」「/verify-re...

Use when a pull request has review comments or bot findings to check or address. Also use it for "are these comments rig...

Validate that a rule has all required files (analyzer, descriptor, test cases, docs) and passes tests. Use after impleme...

일정 그룹(연간일정/간트차트) 탭의 컴포넌트 구조, 데이터 흐름, 핵심 기능을 검증합니다. 일정 관련 컴포넌트 수정 후 사용.

Verify code for security issues including hardcoded secrets, input validation, error exposure, and dependency vulnerabil...

Verify that the Visions Skills architecture is functioning correctly.

Add an Artifact Verification (SscaArtifactVerification) step to an existing Harness pipeline to verify Cosign signatures...

Use before claiming work is complete - runs tests, checks git status, verifies changelog

Captures human source verification for tracks, timestamps it, and updates track files. Use when sources need human revie...

Alle Quellen und Daten in einem Topic-Factsheet-JSON gegen tatsächliche Online-Quellen prüfen. Verwenden, wenn URLs veri...

Verify that "Must Have" requirements from SPEC.md are implemented in the codebase.

VDM-SL仕様ファイルの検証（構文チェック・型チェック・証明責務生成）と、 設計文書（PROTOCOL.md、API-SIGNATURES.md）の完全性チェックを実行する。 「仕様を検証して」「VDMファイルをチェックして」「型チェック...

Use when cross-checking spec consistency between user layer and core layer, or when upstream rules changed but downstrea...

Run the behavioral spec in docs/spec/ against the real apps — a parallel, story-driven QA sweep across desktop, iOS, and...

Check a Trade Story both for structure and syntax, and for whether its trade setup can be resolved without guessing.

학생 그룹(학생관리/등록상담/학생상담/성적관리/퇴원관리/계약관리/성적표) 탭의 핵심 기능을 검증합니다. 학생 관련 컴포넌트 수정 후 사용.

User-invoked as /verify-subtask <path>. Reads the subtask spec, gathers the implementation diff, and spawns subtask-veri...

Run svelte-check (or `pnpm check`) after EVERY edit to any .svelte or .ts file under frontend/src. Triggers on: edit/sav...

Run code-verification on a specific task. Use to verify a single task's acceptance criteria after implementation.

Verify that a task's implementation meets its requirements and has adequate test coverage (happy path, sad path, edge ca...

Verify session ownership before working on existing tasks (multi-instance coordination)

Verify completed tasks with Playwright browser testing. Run after completing implementation tasks to check for JS errors...

Verify technical debt items in the verification queue

hooks/utils의 테스트 파일 존재 여부를 검증합니다. 새 훅/유틸 추가 후 사용.

Apply five concrete heuristics to detect tautological tests, mock-rubber-stamps, and tests written after production code...

Verify tests by following recorded trajectories in tests-in-verification.json. Use this skill during the verify stage to...

Formal proof of one concrete claim. Use only for an explicit verify, prove, measure, or confirm request, or when a requi...

Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and...

시간표 도메인(Math/shared)의 핵심 패턴과 규칙을 검증합니다. 시간표 컴포넌트/훅 수정 후 사용.

Execute end-to-end operational verification of the Igor trading lab ('Prove It Works'). Validates safety gates, risk kil...

Capture all manual pages and verify translations match page images using AI-powered checking. Identifies extraction fail...

Audit TypeScript code for type-safety, strictness, and idiomatic TS patterns. Enforce no-any policy, proper narrowing, d...

Prove UI work actually works by driving the app on the simulator with Argent (build/launch, tap, screenshot, read logs),...

Verify local UI changes in a running app by starting the correct dev server if needed, opening the target page in the in...

Build assets, run server, and get visual approval before committing observable changes.

Visually verify UI changes with Playwright screenshots before proceeding. Use when a change touches frontend/UI files an...

Check that a change to a web app actually works in the running app before calling it done. Drives the real page and retu...

Install, instrument and verify a web app end to end without pausing for a human. Use in an autonomous or goal-mode agent...

Verify the engineer is ready to implement a feature — a teach-back conversation over a .TICKET-REVIEW.md where they expl...

Verify EVM warp route contract source code on block explorers (implementation, ProxyAdmin, TransparentUpgradeableProxy)

Measures whether a watermark remover actually removed the mark: plant a SynthID-class watermark with your own key, run t...

Verify web application changes work by launching the app stack and testing in a real browser. This skill should be used...

Verify microflow side effects and data changes with OQL against a running app. Use after executing changes to confirm da...

Validate built features through conversational UAT

Verify completed work against requirements

Use before claiming any task is done, complete, or fixed. A final verification pass that catches unverified claims, unin...

Prove a change works with real checks before calling it done. Use before saying work is done, or when the user says "che...

Verify workflow outputs using hybrid script + LLM assessment

Verify WorldMonitor dashboard behavior with existing browser tests or a scoped manual drive. Use for panels, map layers,...

Compares implementation evidence against acceptance criteria and shows what is met, partial, missing, or untestable. Use...

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verifi...

Verifies that the lines and branches a change actually touched are executed by tests, using LCOV or Cobertura diff cover...

外部公開を想定したフレームワークにある CHANGELOG.md の内容が適切かどうかを確認するスキルです。CHANGELOG.md を更新する際、またはレビューする際に利用します。