The Reviewer subagent's playbook for checking a finished CRE build. Audit-cell checks, error-value scans, convention compliance, structural integrity.
Why proper nouns, addresses, and job titles are the #1 source of AI hallucinations, and how to use the 4-Point Entity Verification Ladder to prevent embarrassing mistakes.
Verify that a cited New South Wales court or tribunal decision exists on the official NSW Caselaw website, resolving medium-neutral NSW citations and NSWLR references to the…
Verify Open Pstack through installed Codex and Claude Code skills and its shipped Bun CLIs. Use for real behavior proof, routing or setup changes, orchestration bookkeeping, and…
Pattern for verifying your output matches required schema before completing. Use before writing final output to ensure validity.
Query OSS Rebuild attestations and rebuild metadata so an agent can verify whether a published package artifact matches a reproducible upstream rebuild.
Goal-backward phase verification + UAT conversational verification, consolidated. Use when checking phase achieves promised goal before milestone.
Run repository-defined PR verification skills, aggregate the results, and hand back a verification report plus any supporting artifacts without mutating GitHub directly.
Compare original and distilled prompts to verify the distillation is faithful and lossless. Checks completeness, accuracy, and appropriate conciseness.
Verify candidate proofs with the local proof verification MCP service. Use only when a full candidate proof of the entire problem has been assembled in markdown, and before…
Use when verifying, fact-checking, or auditing a quarterly connection self-evaluation for accuracy. Trigger when the user says "verify my QC", "check my quarterly connection",…
Verifies that features listed in a README (or similar documentation) are actually
Use when validating whether a send, deploy, workflow, document, trace, or product flow really landed or works.
Characterize WCET and ISR latency and verify the schedule holds under worst case. Reach for this on any timing or determinism question.
Audit-only verification of manuscript references against PubMed and CrossRef. Detects fabricated or mismatched citations and writes qc/reference_audit.json.
Level 5 verification: regime conditioning tests across VIX regimes, stress event validations (March 2020, February 2018), and A-B data source comparisons.
Use to iterate a change until tests/quality checks pass — bounded run→revise→re-run gated by a numeric threshold, then a judge confirms.
Audit issues in a "resolved" / "fixed" / "done" state that have not been closed yet, verify the fix actually exists in the current codebase, then either close them with a detailed…
Verify an RFC or design doc against the actual implementation — find drift, missing pieces, and undocumented changes.
Verify gitignored OpenClaw secret files are present and fresh in Dropbox backup.
Use before claiming work is complete - runs tests, checks git status, verifies changelog
Statically lint the dev-workflow and mobpro skill trees for SKILL.md cross-reference and output-naming invariants — dangling `§` / bold-label references, mirrored closed-list…
For solution checking: independent verification that result is correct, separate from how it was computed.
Verify task completion by checking filesystem state when execute_code_sandbox or run_shell return misleading unknown errors
Verifies the checklist summarizer end to end: runs it against TODO.md and compares the printed count with the file's items. Use after changing anything under src/ or TODO.md.
End-to-end system health verification. Checks all containers, ports, endpoints, and pipelines (logging, email, auth, socket, worker).
Verify that a task's implementation meets its requirements and has adequate test coverage (happy path, sad path, edge cases). Use before /complete-task.
Create a verifying agent to check whether a working agent's task was completed successfully. Use after a working agent finishes (transitions to "done", "stopped", "waiting", or…
Reviews Jira tickets for implementation readiness by checking acceptance criteria, missing details, dependencies, verification, and clarifications.
Use when the user wants to cross-check a CDC requirement with the TODO.md and the real code to detect gaps (false TODO, missing TODO, partial, KO).
Compact CLI tooling claim classification and method routing. Determines what kind of CLI claim is being verified and which verification method applies: CLI execution (primary for…
UI 구현이 디자인 스펙과 일치하는지 Chrome DevTools + Pencil MCP로 검증. 레이아웃, 색상, 타이포, 반응형, 접근성 확인.
Check that a change to a web app actually works in the running app before calling it done. Drives the real page and returns a pass/fail verdict with the request that fired, the…
Verify UI changes by rendering and looking — screenshot, browser, or running app — never by reading the markup and imagining it.
Install, instrument and verify a web app end to end without pausing for a human. Use in an autonomous or goal-mode agent, in CI, or in any client that asks for approval on every…
Drive a project's documented user scenarios through a real browser with Playwright MCP, then report what actually broke.
Verify known browser behavior or regressions through an already-configured Playwright installation, capturing machine-readable evidence at the public user-visible seam.
Verify macOS menu bar widget builds correctly and app bundle structure is valid. Trigger after any changes to widget/ directory files (main.swift, build.sh, Info.plist,…
For test co-location: tests in same file as code, run with main, tests as documentation and examples.
Drive a real browser against AI Atelie's running dev server to verify a change works, and capture screenshots + video as PR evidence.
Witness claim classification and method routing. Determines what kind of witness claim is being verified and dispatches to the witness-verifier.
Match verification layers to impact, uncertainty, reversibility, and audience when tests alone cannot prove the requested outcome or acceptance boundary.
Use when a worker has written its report and exit-file. This is the Critic step — re-run tests yourself, trust nothing.
Scan and fix hardcoded paths, project-specific references, and environment-coupled values in agents, skills, hooks, and orchestration files to ensure portability across repos.
Use when verifying any feature in a browser-based interactive runtime (three.js, canvas, WebGL, DOM game) where behavior depends on game state, render output, or user input — and…
Verify signed artifacts and SLSA build provenance with Sigstore cosign and slsa-verifier, enforce keyless OIDC identity, and apply SLSA Build levels to harden the software supply…
Visually verifies Compose UI components by rendering @Composable/@Preview functions to images from the project's JVM runtime; STRONGLY PREFERRED for rapid UI iteration and visual…
Use before claiming any task is complete, fixed, or passing, and before handing finished work back to the user.
Flutter-specific simulator/emulator verification loop with flutter drive and screenshot capture for both platforms.
Verifies a mobile UI change by running it on a simulator/emulator. Use after editing any screen, view, or layout — boot a device, install the build, screenshot, and diff against…
Gather evidence before claiming that work is finished, delivered, correct, or fixed. Use immediately before reporting completion — 完成了吗 / 好了没 / 交付 / 验收 / 检查一下 / 确认下.
The /flow engine's VERIFY stage — trace recent work for correctness, run the verification gate, gather proof-of-completion scaled to the change, attach it to the work item, and…
Look up VeriGlow Agent Map for any website URL to discover its data functions, internal APIs, browser automation recipes, and agent reliability reports.
Expert-level Verilog and SystemVerilog knowledge following IEEE 1800 standards. Generates synthesizable RTL code with proper coding styles and constructs.
Verimi integration. Manage data, records, and automate workflows. Use when the user wants to interact with Verimi data.
Verimor API üzerinden SMS gönder, bakiye sorgula, rapor al, başlıkları listele ve kara liste yönet.
Veriphone integration. Manage data, records, and automate workflows. Use when the user wants to interact with Veriphone data.
Automate Veriphone tasks via Rube MCP (Composio). Always search tools first for current schemas. — from general/automation
Lógica booleana e circuitos digitais com resultados exatos — tabelas verdade, simplificação mínima, mapas de Karnaugh, formas normais SOP/POS, simulação de circuitos com clock e…
Veritone integration. Manage data, records, and automate workflows. Use when the user wants to interact with Veritone data.