Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before makin — from…
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before makin — from…
Before submitting code or creating a Pull Request, when about to claim that work is complete, fixed, or passed, you must run verification commands and confirm the output results…
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before makin — from…
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before makin — from…
Use before declaring any design work complete, fixed, or ready — requires running verification and confirming output before making any success claims.
Verification checkpoint before completion claims. Ensure tests pass, build succeeds, and functionality works.
Evidence-before-claims verification enforcing proof of completion before any "done" claim. Auto-activates when: completing tasks, reporting results, claiming success, writing…
Use for PocketTorch standalone C++ tests, CTest wiring, numerical tolerances, finite-difference checks, deterministic test data, regression coverage, and build verification.
Run a read-only verification pass after implementation to check whether completion claims are real, validation actually ran, and obvious edge cases or regressions were missed.
中文优先：用于验证循环相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: A comprehensive verification system for Claude Code sessions.
Evidence-based verification with gate function. Trigger: When verifying task completion or validating claims.
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase re — from…
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase re — from…
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase re — from…
4-layer verification system for task completion. Use when verifying that a task has been fully completed before marking it done.
Create or refresh project-local verification skills from repository evidence. Use when a project lacks a repeatable verification method, or its commands, surfaces, or evidence…
Use when a project has no verification skill and an agent should from now on judge, alone, the product quality of what is delivered (done as specified, usable, finished): on…
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation.
Supporto documentale all'iter di esercizio, verifiche periodiche e manutenzione degli ascensori, montacarichi e apparecchi assimilati ai sensi del DPR 162/1999 (testo vigente,…
Run a risk-adaptive, evidence-backed implementation workflow that automatically captures, deduplicates, repairs, and regression-tests discovered problems until a fresh dual review…
Use when about to claim any work is complete, fixed, passing, or shipped — before saying "done", "should work now", "that fixes it", or committing.
독립 검증 게이트를 strict 모드로 실행해 review 미실행/경고/위험을 non-zero exit 으로 차단하고, verdict 카드로 ship/no-ship 을 제시한다.
Fallback workflow for reliable file creation and verification when automated code execution fails
Automate Verifiedemail tasks via Rube MCP (Composio). Always search tools first for current schemas. — from general/automation
Drain the verification queue — pick up unverified claims emitted by the working agent, spawn isolated verifier subagents to check them, write results back to the log.
Verifikation: Beweislast, Darlegungslast und Substantiierung im Plugin Liquiditaetsplanung: 1. Welche Rolle hat die fragende Person und wer ist Gegenüber? 2.
Für Verifikation: Compliance-Dokumentation und Aktenvermerk: ordnet Akte, Belege und Lücken; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Für Verifikation: Compliance-Dokumentation und Aktenvermerk: ordnet Akte, Belege und Lücken; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Für Verifikation: Fristennotiz und nächster Schritt: prüft Frist, Form, Zuständigkeit und Eilbedarf; Ergebnis: Fristen- und Risikoampel. Fachgebiet: Fluggastrechte.
Verifikation: Fristennotiz und nächster Schritt im Fluggastrechte: 1. Welche Rolle hat die fragende Person und wer ist Gegenüber? 2.
Für Verifikation: Sonderfall und Edge-Case-Prüfung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Für Verifizierbarer: Verhandlung, Vergleich und Eskalation: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Verifizierte Mandantenentscheidung: strukturierter Entscheidungsprozess für Mandanten vor rechtlich verbindlichen Schritten — Klage, Aufhebungsvertrag, Vergleich, Widerspruch:…
Verify adoption criterion A1 (Agent Context Availability) in the current project. Reports fulfillment level 0–3.
Verify adoption criterion A2 (Agent-Authored Contributions) in the current project. Reports fulfillment level 0–3.
Verify adoption criterion A3 (Feedback Loop Closure) in the current project. Reports fulfillment level 0–3.
Verify adoption criterion A4 (Task Scope) in the current project. Reports fulfillment level 0–3.
Verify adoption criterion A5 (Workflow Integration) in the current project. Reports fulfillment level 0–3.
Verify adoption criterion A6 (Autonomous Operation) in the current project. Reports fulfillment level 0–3.
Verify adoption criterion A7 (Proactive Quality Management) in the current project. Reports fulfillment level 0–3.
Verify adoption criterion A8 (Planning Integration) in the current project. Reports fulfillment level 0–3.
QA agent: executes Epic AC (Acceptance Criteria) verification against an AC ticket or Epic. Runs all AC steps, classifies each as PASS/FAIL/MANUAL_REQUIRED/UNCERTAIN, and presents…
FRD의 AC(Acceptance Criteria) 중 UI 조작과 상태 영속이 걸린 항목을, 이미 실행 중인 앱에서 실제로 조작해 검증한다. 단위/통합/E2E 자동화 테스트 스위트와 달리 테스트 코드를 남기지 않는 1회성 실동작 확인이다 — 진입 경로(라우트) → 사전 상태 세팅 → 조작(클릭/입력) → 기대 UI…
Use when about to assert any factual claim about what code or a product does - in an answer, a doc, a commit message, or anything a user will see.
After a Sui build session, check what was built against .suiperpower/intent.md and flag drift. Use when the user wants to verify their build matches intent.
Spawn a stateless sub-agent (Claude Code Task tool, Cursor agent mode, or equivalent) with ONLY the artifact path plus the locked rubric plus read-only tools.
Use when finishing a spec-driven feature, when asked to verify nothing was missed, when approaching context limits on a long feature session, or after hearing "make sure…
Lieferergebnisse validieren und Belegnachweise aufbauen, wenn Arbeit zwischen Agenten uebergeben wird.
Spot-check a teammate's claimed work before accepting it
Ensure all required output files are created and verified before marking a task complete
仕様を実行可能テスト（verify.md）に変換し、カバレッジを分析するワークフロー。Runme.dev形式でE2E/統合テストを記述。 使用タイミング: (1) 仕様書（spec.md等）から実行可能なテストドキュメントを作成したい場合 (2) テストカバレッジを分析・可視化したい場合 (3)…
Build the checked-out branch, launch that exact app, let the user confirm the fix is really there, then push and offer merge or PR.
Use FIRST when verifying any UI state on an Android emulator or device — checking that elements rendered, text appears, state is correct, or a fix landed.
Use when verifying an Android UI state requires a real screenshot — WebView content, animations, visual fidelity (color, font, image content, alignment), or finding an element by…
현재 접근 방식이 최신/올바른지 인터넷에서 검증. 구현 전 기술 선택이나 방법론 확인할 때 사용
Verify archive integrity with self-verifying SHA-256 checksums, generate VERIFY.md, and optionally create W3C PROV provenance
Round-trip fidelity test for a generated artifact. Generates the artifact, re-ingests it into a throwaway scratch vault, diffs against the originals, and reports a fidelity score…
Iron rule — no completion claims without fresh verification evidence. Use whenever about to claim work is done, fixed, working, or passing.
Use when about to claim work is complete, fixed, or passing, before committing changes - requires running verification commands and confirming output before making any success…