В каталоге 181 320 навыков в 14 категориях.
Build the checked-out branch, launch that exact app, let the user confirm the fix is really there, then push and land it...
Check and repair rational polynomial identities with ResiMind when an expansion looks wrong, two algebraic answers disag...
Check finished work against the request and report the result honestly with evidence. Use this before saying any task is...
Use before you say that work is done, fixed, or ready for review. Also use it when the user says "make sure it works", "...
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion check...
Run the canonical verification pipeline (spotlessCheck → assembleStableDebug → lint → test), parse the results, and refu...
Compare provider DTOs and WireMock test payloads with live responses from the real public API (currently NBP), and captu...
Run affected app feature checks, inspect evidence, or maintain this project's verifier when source or accepted behavior...
Run the quality gates for an app in this lab repo (typecheck, lint, tests, build) and look at it in a browser. Use befor...
Comprehensive application verification specialist. Runs static analysis (typecheck, lint, prettier), build verification,...
変更後の検証ループ — プロジェクトの lint・typecheck・test・build を実行し、失敗を修正して再実行する。実装完了の報告前、および commit・PR 作成前に必ず使用する。
Run architecture compliance checks for BioETL (quick/full/category modes) before commit or PR.
Prove that the file you are about to send, publish, or hand off IS the thing you mean — before it leaves your hands. Reb...
Verify required artifacts exist, are complete, and match expectations.
Pre-commit verification floor for two specific claim shapes that recur at decision points — vendor-specific quantitative...
Use when an agent is about to claim completion, correctness, safety, publication, deployment, or any consequential exter...
Use for any task that will end in a claim about tests, the build, or whether the work is done: making tests pass, fixing...
Use when about to create a git commit in this project
Use when about to claim work is complete, fixed, or passing, before committing changes - requires running verification c...
Evidence rules for completion claims. Use before ticking an acceptance criterion, ending an implementation run, or writi...
Execute bug fixes from an issue description when locations may be stale, paths may not match repo layout, and bugs may a...
Verify observable product behavior through selected project-owned app references and falsifiable end-to-end evidence whe...
Load this skill before a change meant to alter no behavior (a refactor, rename, dependency upgrade, or port): pin a base...
Post-edit verification of a short's opening and closing 1.5s. Claude sees a 3-frame strip from each end plus the trimmed...
Set up a repo's machine gates (format, lint, type check, security, dependency audit, tests), or audit whether existing g...
Prove a Brigade change works by driving the real `brigade` CLI against a throwaway temp target, then capture receipts as...
Verify the application builds successfully and check for type errors. Use when finished with changes, before committing,...
Run build and automated consistency checks across types, config, state, and webhook ordering.
SeldonFrame merge gate — run unit tests + tsc + check-use-server + migration-journal + regression-grep and return ONE pa...
코드 스플리팅 효과와 번들 크기를 검증합니다. 빌드 최적화 또는 대형 라이브러리 추가 후 사용.
Select and run the gates that actually cover a change. Use after every edit and before every commit.
Verify an implemented change by mapping intended behavior to executable checks, running those checks, and handing off co...
Select and run checks, reproduce bugs, diagnose failing tests or CI gates, add regression tests or assess requested cove...
Prove a change works before calling it done: pick checks from what the diff touched (core, content, brand, ui, pwa, assi...
Mechanical Go verification of a scoped mivia change. Run test, vet, build, race, invariant and contract gates, then repo...
コードや設定を変更したあと、完了を報告する前に、変更が想定どおりに動くことを実際に確かめる skill。実装・修正の作業を終えるとき、または変更が動くかを聞かれたときに使用する。
Use this skill after implementing code to verify correctness before notifying the user.
Prove code works by running it, not just checking it exists. Verification through execution rather than inspection. Use...
Use before reporting a change done when the project declares verification commands, or when the user asks for verificati...
Use when researching a topic from web pages, threads or transcripts and every claim needs an exact quote checked against...
Run (or re-run) Stage 4 only — the Claim Verifier: extract every claim from the draft, verify each against its declared...
Verify marketing claims. Use when: cross-checking statistics, awards, certifications, or performance claims with sources...
Find sources for every numerical claim in the draft, add inline hyperlinks, and add internal links to brand-reference ar...
Run Chain-of-Verification (CoVe) on a draft or a block of text with factual claims. Spawns the `claim-verifier` agent in...
수업 그룹(시간표/출석부/출결관리/수업관리/강의실/강의실배정/숙제관리/시험관리/교재관리) 탭의 핵심 기능을 검증합니다. 수업 관련 컴포넌트 수정 후 사용.
Prove that a command-line tool actually did what it said, instead of trusting its exit code and its output. Snapshots th...
- After tasks are marked done
Verify an implemented code or config change with evidence scaled to risk and blast radius. Portable, language-agnostic....
Post-pick gate that re-reads each picked span's transcript and either keeps it as-is or tightens its [t0,t1] to cover on...
소통 그룹(공지사항/학부모포털/알림센터) 탭의 핵심 기능을 검증합니다. 소통 관련 컴포넌트 수정 후 사용.
Arc-completeness gate. Re-reads each picked span's ASSEMBLED arc (the words inside its cuts) plus a tail lookahead and a...
Verify a completion, progress, or success claim against current direct evidence before it is made or accepted, especiall...
Verify that a coding or configuration task is complete by mapping requested outcomes to fresh evidence, repository check...
Verify a Crossplane configuration package before committing - build it, run its composition tests and read the render, a...
Integrated skill for fact-checking and reference verification. Covers claim identification, source verification, and ref...
Run comprehensive quality verification on workshop or demo content using Red Hat standards and validation agents.
Verify dark earthquake claims against fault databases. Use when checking if a candidate earthquake is truly "dark" (unma...
Checks that a data-rendering screen shows exactly what its source returns. For each screen that renders rows from an API...
Confirm a requested feature change via AERA Debug mode (Debug view, console, logs). Use when validation must happen thro...
Use when accepting a subagent's or worker's change: it reports all tests pass with no raw output, calls a new test or li...
Go/No-Go checklists for risky data deployments. Generates pre/post-deploy verification queries, rollback procedures, and...
Compares a build, screen by screen, against a design handoff (Figma frames or exported PNGs) and renders the owner's fra...
Checks that the components a design board names actually appear at that board's route in the running build. Walks React'...
Verify an architecture diagram against the actual codebase. Checks component existence, connection accuracy, and read/wr...
Compare test results and behavior between the current branch and the base branch. Proves changes work by diffing test ou...
ドキュメント（docs/）の内容がコードの実装と一致しているかを検証します。「ドキュメントを検証」「ドキュメントとコードの整合性をチェック」「docsを確認」と言われたときに使用します。
Verify documentation line numbers match current code state
Use for multi-step work (sweeps, migrations, runs of similar edits), for ordering commits and PRs, and for ordering the...
Verify if an email address is valid and deliverable
Snapshot test email templates using Verify to catch regressions. Validates rendered HTML output matches approved baselin...
ErrorBoundary + fallback UI + 에러 복구 패턴을 검증합니다. 컴포넌트 에러 처리 수정 후 사용.
Drive FinancialDevelopment the way a user does: FastAPI Quant Console dashboard (HTTP) plus pytest unit suite. Use when...
Verify code-review or security-review findings for false positives using deep codebase tracing, framework-aware analysis...
Firebase mutation 훅의 invalidateQueries/에러처리/writeBatch 패턴을 검증합니다. mutation 훅 수정 후 사용.
Measure which firstmate behaviors are proven, and say which are not, by running real firstmate sessions and driving the...
Use only when the user explicitly requests verification that a security fix remediates a reported vulnerability. Do not...
Mandatory incident fix verification with observables. Invoke after: applying production fixes, before declaring incident...
Checks that a designed screen-to-screen journey — an interaction diagram or a named list of steps — actually runs that w...
Check that a form actually rejects bad input: the error message renders, the submit button stays disabled, and no reques...
Runs project compile, test, and lint commands between implementation and quality review. Gates simplify-and-harden behin...
Use on every generative step. Runs 3 to 5 verification rounds with the full suite (tests plus the matching verifier agen...
Run every acceptance criterion of a goal file as an external check, record the command, its exit code and an output exce...
Goal-native live verification. Drives a TRD's implementation to "all assertions pass" under /goal — one assertion of pro...
Сверка журнала гипотез (hypotheses-log.md) по запросу вне ритма week-close. Фильтрует записи со статусом «на сверке» и н...
Forensic audit of an implementation against its authoritative specification. Use whenever a specification document and a...
Trace authoritative spec requirements to existing code evidence; not general diff or design review.
프로젝트의 모든 verify 스킬을 순차 실행하여 통합 검증 보고서를 생성합니다. 기능 구현 후, PR 전, 코드 리뷰 시 사용.
프로젝트의 모든 verify 스킬을 순차 실행하여 통합 검증 보고서를 생성합니다. /verify-implementation으로 실행.
Check a change the way a user sees it, in a browser, against an instance this app starts safely, and keep the evidence (...
Verify inbound shipment facts against PO, ASN, BOL, packing list, labels, counts, and received goods.
This rule ensures that the AI always verifies information before presenting it, avoiding assumptions and speculation.
Design the executable feedback loop for an intent — fastest check, highest-confidence check, manual fallback, observable...
Runs the IronLedger runtime verification harness to enforce financial balance invariants, database migration integrity,...
Nezávisle ověří, že PR splňuje akceptační kritéria svého issue — spustí ověřovací příkazy, porovná změnu s precedentem c...
Verify a completed issue by comparing implementation against acceptance criteria, running tests, and critiquing the work...
Verify a web journey in a real browser with seeded state and captured evidence.
Verify that every interactive control on a page can take keyboard focus and that its primary action fires from the keybo...
Verify claims about known issues in libraries or tools. Use when about to state something is a "known issue", "known bug...
Language-specific verification for Python, TypeScript/JavaScript, and Go. Checks type safety, language idioms, and best...
Prove a language switch translates what the user sees, keeps what they had already typed, and is still in force after a...