Agent skills directory

为任意 Agent Skill 设计、实现、接入或精简 Verifier 与 State；当用户希望给目标 skill 配置验证器/状态机、落实已有设计，或仅规划和审查架构时使用，尤其适合需要避免过度设计、硬编码并符合 Kernel 契约的...

Use when you want to validate changes before committing, or when you need to check all React contribution requirements.

Verify a Mathiz change end-to-end before committing — which builds, tests, and live flows to run for each area of the co...

Verify that a change really works before you claim completion

Curation review pass — Capabilities or Functionalities with confidence='extracted' awaiting Alex's verification.

Verify agent identity using ERC-8004 on-chain registry

Use when you need to PROVE a claim with evidence, run quality/security scans, or validate that work is actually complete...

Run an explicit user-requested criteria-driven verification loop. Use when the user asks to define success criteria, clo...

Run unit tests then integration tests (LocalStack) and surface any failures before committing

Use when a plan's tasks are landed and its branch needs the gate before a pull request, the scripted checks, the branch...

Run the backend verification loop after Kotlin/Spring code changes — Kotlin style + unit tests via `gradlew verify`, plu...

After a change, before commit/merge — independently review the complete candidate against user intent and standards, run...

AI DevKit · Enforce evidence-based completion claims — require fresh command output before reporting success. Use when c...

Drive EZR's actual surfaces to confirm a change works — the program runner, the browser interface, and the tool CLIs. Us...

Pre-commit verification - checks changes won't break the deployed app or corrupt the database

Run all quality gates and produce a comprehensive pass/fail report.

Fresh verification gate before claiming done, fixed, passing, ready, or before commit/PR. Evidence before claims, always...

Run the full ChefFlow verification protocol - spec audit, build integrity, production parity, and Playwright pressure te...

Verify task completion by demonstrating real value: run the new code on real data, show visible results, find gaps betwe...

Redirects to review deep. Use review with depth levels instead.

Use before any completion claim, commit, or PR — requires running verification commands and confirming output before mak...

Proves a change works before it is called done, and reports the evidence on a ladder from "said" to "ran". Use when you...

Adversarial verification of implementation work. Spawns a read-only subagent that runs builds, tests, linters, and probe...

Verify-before-done — exercise the current change end-to-end against its acceptance criteria (the SDD plan's, or the tick...

Use when implementation is finished and about to be called done or merged — the rsc-sdd evidence gate: runs the stack's...

Contract document for the binding test verdict file at .claude/state/last_test_result. Format spec for callers (integrat...

Run the appropriate verification chain for recent changes. Detects what changed and runs build, tests, smoke checks, and...

Run the full verification pipeline — tests, types, and quality checks

Lightweight project verification. Runs typecheck, lint, prettier (auto-fix), and build. Reports pass/fail status and off...

Use after implementation is complete to verify that code matches specifications. Ensures every Requirement is implemente...

Verify code changes work by running them. Proves through execution, not just inspection.

기능 구현을 마친 뒤 직접 검증하고 사용자용 테스트 체크리스트를 줄 때 쓰는 절차. 임시 검증 자원 규칙과 체크리스트 형식 포함.

Spawn the hardware-verifier agent for a named package's most recent PR.

Build, run, and drive this app (FastAPI + SvelteKit) to observe a change at its real surface. Use when verifying a diff/...

Verify a change is done by running lint, the Prettier check, the test suites, and a production build. Use after finishin...

Goal-backward verification that a completed feature actually achieves its goal, run before a PR or when work is declared...

Verify code or product claims after changes using fresh, risk-matched evidence. Use before saying a bug is fixed, tests...

Use when making any completion claim, reviewing findings, or processing agent reports

Run kajet-turbo locally against a temp DB and a fake embedding endpoint, then drive the REST surface (login, notes, jobs...

Run format, lint, test, and build checks on the Rust project. Automatically invoked after completing a task or implement...

Exercise a change end to end in the running application (hit the route, run the command, click through the page) and rep...

AI 응답 검증

Combined verification — recite (description quality via cold-read prediction) + validate (schema compliance) + review (h...

Run full quality gate suite before committing or creating a PR

검증 스킬. 빌드, 린트, 테스트 검증. 커밋/PR 전 필수 실행. AI가 스스로 코드를 검증하는 자체 검증 루프.

Prove a change works before calling it done, by running every check that applies to what changed and reporting the real...

Build, relaunch, and observe the Claudence menu bar app to verify a change end-to-end.

Verify a claim before stating it, and verify a test before trusting it, in OpenAlgo Desktop. Use before asserting that a...

Generate or maintain a project-local verification skill that drives the real app the way a user does, in any language or...

Verify any change, fix, behavior, deploy, or external state with current evidence from its real surface. Use when the us...

Verify a requested change or claim with fail-first evidence, targeted checks, live output, and exit codes. Use for 'çalı...

Comprehensive verification before PRs. Runs all quality gates and produces a structured pass/fail report.

Run every check before committing — full test suite, all four structural gates, the coverage ratchet and the boot smoke...

Run the OpenDataSuite quality gate (cargo fmt, clippy -D warnings, tests, cargo-deny, docs link sanity) and report pass/...

Full pre-PR verification pipeline — build, typecheck, lint, test, secrets, git status

Run all local validation checks for Skoleoverblikket before declaring work done. USE THIS SKILL when the user says 'veri...

Run the full verification pass on a large change — clean-room install, complete test suite, lint, packaging check, CLI s...

Build, launch, and drive a Debug build of Rapture for Mac to verify changes end-to-end against its real surfaces (destin...

Verify that a code change actually does what it's supposed to by running it and observing real behavior — not just by re...

Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fi...

Run and fix the software-factory verification gate (scripts/verify.sh) from the repo root — format, build, config-JSON a...

Verifies a feature branch in an isolated sandbox — extracts the test plan from the PR, generates verification items from...

Run this repository's gates on the work about to be committed — the backtest suite, and the quality score for every stag...

Browser-check what a change could have broken in timepicker-ui (library demo and docs-app, before/after). Use at the end...

Run this after every code change in this Vue project, before committing, before opening a PR, or whenever the user says...

Verify game mechanics match the design document

Run full verification suite (ruff check, ruff format, ty type check, pytest) and report results. Use before committing,...

Build, launch and drive wayfinder-maps to verify a change end-to-end (server + headless browser).

File structure verification - ensuring skill directory exists with all 3 reference files in correct locations.

Fast parallel verification before PR. Use when "verify", "review my changes", "is this ready", "pre-review", "check befo...

Verify a competitive programming or LeetCode solution for correctness, edge cases, and performance. Use when asked to "v...

Verify project behavior anchors — compilation, tests, and interaction checks after autonomous runs. NOT the Claude Code...

Build, launch, and drive the P3DX dashboard to verify changes at the browser surface.

Run full verification on recent code changes — tests, LLD compliance, and security review. Claude MUST run this automati...

Run a full implementation verification pass after code or data changes. Use when the user asks to verify, QA, smoke test...

Use before claiming work is done, fixed, or passing — requires running verification commands and confirming output befor...

Verify ticket completion criteria — use when finishing a ticket, before marking work done, or checking acceptance criter...

Decide whether the diagnosed behaviour is actually a bug or whether the code is doing what it was designed to do. Gate t...

Верификация артефакта по эталону из Pack. Загружает роль VR.R.001 (Верификатор) с context isolation — проверяет результа...

Run verification tests and report numerical accuracy after code changes to model files

Build the app, launch on simulator, and verify feature behavior via mobile-mcp interaction. Use after making changes to...

Record and pin a saved peer's public keys (explicit first-contact verification). Use to verify a contact before messagin...

Prove applied Sentry changes with a live marked event: arrival, readable stack trace, privacy scan of the arrived payloa...

Exercise the real app, API, CLI, or document artifact and collect observable evidence; unit tests alone do not count as...

Run comprehensive verification on current codebase state

Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video + time...

Bounded acceptance verification that runs concrete checks and an explicit LLM judge over evidence.

Verify that a Nano (XNO) payment has settled: confirm a send/receive block, read its amount and pay-to account from the...

관리 그룹(수강료현황/직원관리/수납관리/자료실/역할관리/통계분석/급여관리) 탭의 핵심 기능을 검증합니다. 관리 관련 컴포넌트 수정 후 사용.

Use when after pushing commits to remote repository

Use when about to assert any factual claim about what code or a product does - in an answer, a doc, a commit message, or...

Run full source-of-truth verification: tests, lint, contract drift check, and codegraph scan. Automatically invoked afte...

Reduces hallucinations by requiring verification, sourcing claims, and expressing appropriate uncertainty when informati...

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)...

Audit a claim or implementation, prove what can be proven with concrete evidence, and explain the result in clear audien...

Runs all 9 verification gates and health checks, interprets failures with actionable fix guidance, and re-verifies after...