Validate artifact against schema, acceptance criteria, and downstream readiness BEFORE marking a task complete.
Verification protocol for agent outputs. Use when: (1) a subagent or ACP agent claims to have completed a fix or implementation, (2) reviewing agent results before committing, (3)…
Use when re-hashing evidence and verifying against recorded hashes and OpenTimestamps proofs.
Verification by source code inspection. Searches and reads the actual compiler, ledger, and runtime source code to verify structural or architectural claims about Compact and…
Verification by running the full ZK proof pipeline: compile Compact without --skip-zk to generate PLONK keys, execute the circuit via JS runtime to get proof data, serialize with…
Verify readiness criterion C2.1 (Setup Automation) in the current project. Reports fulfillment level 0–3.
Verify readiness criterion C4.1 (Requirements Access) in the current project. Reports fulfillment level 0–3.
Verify readiness criterion C5.1 (Runnability) in the current project. Reports fulfillment level 0–2.
Verify readiness criterion C5.2 (Unit Test Coverage) in the current project. Reports fulfillment level 0–3.
Verify readiness criterion C5.3 (Integration and E2E Coverage) in the current project. Reports fulfillment level 0–3.
Verify readiness criterion C6.1 (Static Analysis) in the current project. Reports fulfillment level 0–3.
Verify readiness criterion C7.1 (Test Isolation) in the current project. Reports fulfillment level 0–2.
Verify readiness criterion C8.1 (CI/CD Automation) in the current project. Reports fulfillment level 0–3.
Verify readiness criterion C8.2 (Observability) in the current project. Reports fulfillment level 0–3.
Verification-gated model escalation — run a cheap model, verify its output with decomposed per-field checks, and escalate to a strong model only when a flag fires.
Verify that a quoted passage attributed to an Australian judgment actually appears in the decision as published by the official court publisher, reporting the paragraph or page…
Launch and drive the real cc-safety-net CLI — the hook decision path, explain, status/doctor, logs, and the local policy GUI — against an isolated home, capturing evidence.
Use immediately after completing an implementation or change, before reporting results. Defines the verification order (build/type check, lint, tests, format, manual scenarios)…
Use when you need to confirm CI is green before calling work done, when CI fails and you need to diagnose and fix, when the user says "watch CI", "wait for green", "verify CI",…
Confirm a paper actually exists (arXiv / Semantic Scholar / OpenAlex) before citing it. Use before writing any new citation into a .tex, .bib, or .md file.
Schreibt Code, findet Bugs, schreibt neu. Run '/verify-code', 'code pruefen', oder 'verification loop'.
Use when completing any implementation task, fixing a bug, or claiming tests, build, or lint pass.
Use when claiming 'done', suggesting a commit, push, or PR — runs the evidence gate so completion claims come from fresh output in this message, not memory or earlier runs.
One-shot readiness check for agentic browser/Computer-Use automation. Confirms which Computer-Use SDKs are installed vs missing, the live vision API beta header, and the local CDP…
Record proof that a task works by capturing commands, pass/fail results, changed files, artifacts, risks, and the next safest task.
Hub skill for the midnight-verify plugin. Classifies claims by domain, routes to the appropriate domain skill, dispatches sub-agents based on the domain skill's routing, and…
Verify the CRA app's build path by running the repository's prebuild checks, production build, and artifact validation before deploy or handoff.
Verify a bioprism crate is genuinely green — tests passing and clippy at zero warnings — and recognise the environment failures that masquerade as test failures.
데이터가 입력·계산·저장·재사용 전 과정에서 유효하게 흐르는지 검증한다. 검증 대상 인벤토리 합의 → 데이터 흐름 레이어 매핑(입력→계산→적용→영속→재로드) → 임시 계측 로깅 주입 → 실행 로그/스냅샷 수집 → 의도값↔저장값↔재로드값 대조 + 데이터 품질 차원(완전성·유효성·정확성·일관성·무결성·유일성) 판정 → 검증…
Use when accepting, merging, or building on work produced by a sub-agent, delegated worker, or any process you did not run yourself.
Audit an already-completed delivery against real evidence. Use when asked to review an existing completion claim, tests, Git state, readiness, or benchmark; never while…
Use to audit the real implementation of a TODO ticket with senior code review rigor (backend/frontend/DB consistency, edge cases, dead code) and create correction tickets.
Diagnose and resolve file access issues by first verifying the directory structure.
Runs lint and tests to verify a completed task or plan has no errors. Use when a task, feature, bugfix, or full planning session is finished and the user wants to confirm…
Drive a feature end to end like a person would, after a change that spans more than one layer. Trigger on "test this end to end", "verify the whole flow", "does this actually…
Snapshot test email templates using Verify to catch regressions. Validates rendered HTML output matches approved baseline. Works with MJML templates and any email renderer.
Verifica end-to-end di un endpoint REST della Todo API. Usa quando l'utente chiede di "testare", "verificare", "smoke test" o "provare" un endpoint Express del backend.
Verify changes using runtime observation instead of diff-reading or unit tests. Includes autoagent's failure taxonomy for diagnosing what went wrong when verification fails.
Run offline unit tests + ruff lint to quickly verify code changes before commit. Skips integration tests that need API keys or VAL binary.
Verify that a cited Federal Court of Australia or Federal Circuit and Family Court decision exists at the courts' official publishers, resolving FCA, FCAFC, FedCFamC, FCCA, FamCA…
Verify a ported Scala file — check conventions, compile, run tests, report status
Verify any form or input change end-to-end before declaring it done. Trigger this whenever a task touches a
Uses Goss to express the expected state of a machine or container, then validates that reality still matches the contract.
Absence of visibility is not absence of the thing — verify state, identity, and existence against the system of record, not a partial or cached view.
Use before claiming a feature is done, before merging, and before running any finishing / release skill.
驗證 Gemini 模型在 Google AI Studio 與 GCP Vertex AI 上的**實際可用性**—— 不只是「列在文件上」，而是真正可呼叫並回傳有效輸出。支援 Gemini 3.x global 端點 （gemini-3.1-pro-preview、gemini-3-flash-preview 等只在 global 端點可用）。…
Evidence-only check whether a GitHub Actions Marketplace listing is actually LIVE. Use when: is it on Marketplace, advertise the action, listing URL, marketplace 404, did we…
Reviews AI-facing behavior to ensure Blackboard facts remain grounded in local data, cached files, or tool results.
Verify that a cited High Court of Australia decision exists at the official High Court website, resolving medium-neutral HCA citations, CLR volumes 1-100 and ALJR references to…
Verifies Hermes Mobile ship claims with evidence — unit tests, continuous E2E, simulator full-suite, device Maestro.
Сверка журнала гипотез (hypotheses-log.md) по запросу вне ритма week-close. Фильтрует записи со статусом «на сверке» и наступившей датой, сверяет критерий фальсификации с…
Spawn multiple children to verify implementation meets requirements from different angles
Interpret the output of `specgraph verify` and explain what each status means and what to do next.
Verify claims about known issues in libraries or tools. Use when about to state something is a "known issue", "known bug", or "known limitation".
Verify claims about known issues in libraries or tools. Use when about to state something is a "known issue", "known bug", or "known limitation".
Fake code detection — performative implementations, test theater, misleading patterns, red flags
The live end-to-end verification for changes that touch GPU / camera / display / codec. Use when a change needs a real pipeline run (a plain Bash call dies at exit 144 in a…
Verify the OpenSEO MCP server end-to-end on a local dev server — protocol-level correctness against real DataForSEO, then a headless-agent consumer probe that tests tool…
Verify algebra, calculus, identities, equation solving, and nontrivial derivation steps with SymPy. Use when a mathematical result needs programmatic checking.
Verification checklist to walk before declaring a tt-emule mock complete. Use after implementing a stub (typically at the end of /implement-mock or /compute-llk-bringup) to catch…