테스트·보안 스킬

Design or audit GEODE's dependency-aware grilling flow and slash integration without speculative branch execution or parser-heavy interviews.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audit agent runtimes and their tests for lifecycle inference, capability overload, context pollution, correlated verification, prompt-only control, false success, dead compatibility paths, test-only seams, and complexity without contribution. Use for whole-repository agent audits, slop or dead-code triage, test contribution reviews, large refactors, tool/context simplification, and cleanup requests that need proof before deleting code or tests.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Codebase audit + refactoring workflow. Dead code detection, God Object splitting, duplicate function removal, design flaw identification, frontier comparison verification. Triggered by "audit" ("감사"), "dead code" ("데드코드"), "refactor" ("리팩토링"), "god object", "duplication" ("중복"), "design flaw" ("설계 결함") keywords.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Docs 사이트 (`site/` Next.js) 의 본문/JSX/markdown 링크 audit. broken 내부 링크 탐지, build-time copy 인지, 옵트인 HTTP probe. 신규 페이지 추가 / slug 이전 / chapter 삭제 후 회귀 방지. Triggered by "broken link", "404", "docs link", "hyperlink", "링크 점검", "링크 깨짐", "audit links", "link checker" 키워드.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Scope, preregister, execute, audit, normalize, and publish GEODE evaluations with research-question, reproduction, attempt-lineage, trajectory, verifier-receipt, and immutable artifact contracts. Use for benchmark runs or comparisons, eval-artifact and cache-accounting audits, GPT or subscription result normalization, research question or hypothesis framing, retry diagnosis, trajectory publication, DPO or reward-data readiness reviews, and requests involving MCPMark, tau2, BFCL, Agent-World, HAL, Terminal-Bench, or Toolathlon.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Trigger when: (1) the user mentions "manim", "scene", "video", "EN/KO render", "GEODE_HERO_LANG", "1080p60", or (2) editing files under `scripts/visualizations/` ending in `.py`, or (3) the user asks to render, re-render, or extend any of the four validated scenes (`geode_hero.py`, `autoresearch_filewalk.py`, `autoresearch_compare.py`, `critical_floor.py`). GEODE Manim Scene authoring standard. Locks the patterns the four validated scenes already share — Anthropic-style palette, Helvetica Neue + Pretendard font pairing with weight=NORMAL, EN/KO multilingual lang via `GEODE_HERO_LANG` env, `_dashed_arrow_with_head` stage-coupled tinting, `verify_hero_layout.py` ratchet — so the next scene does not re-discover the kerning / padding / transition regressions catalogued in [[viz-frame-audit]].

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Align, run, audit, and publish GEODE benchmark comparisons against Agent-World arXiv 2604.18292v1 across MCP-Mark, BFCL V4, and tau2-bench. Use for Agent-World or AgentWorld comparison requests, cross-suite agent benchmark design, Tau2 comparator/profile diagnosis, paired thin-runtime-versus-GEODE experiments, mean-accuracy@8 replication, or benchmark comparability and artifact reviews.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Verification checklist to prevent fake success. Detects test deletion/disabling, coverage regression, lint bypass, secret exposure. Triggered by "deception", "fake" ("가짜"), "fake success", "verification" ("검증"), "checklist" ("체크리스트"), "deletion detection" ("삭제 탐지"), "regression" keywords.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Trigger when: (1) the user mentions "noise", "slop", "frame audit", "video review", "letter spacing", "padding intrusion", "frame extract", "naive arrow", or Korean equivalents (노이즈, slop, 프레임 검수, 글자 깨짐), or (2) after rendering a new or modified Manim scene, or (3) the user asks to review an mp4 in `media/videos/` or `~/Downloads/`. Post-render audit workflow for Manim 1080p60 videos. Extracts keyframes via ffmpeg, inspects them through Claude Code's Read tool, and classifies any defects into four standing categories (naive arrow / padding intrusion / glyph kerning drift / frame-order error). Catalogues 12+ verified incidents across the four GEODE scenes so each is caught the first time, not rediscovered. The companion authoring skill is [[manim-scene-craft]].

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Publish and verify a released GEODE version across GitHub Release and PyPI/uv. Use for uv/uvx distribution, stable promotions, release repair runs, and public installation-channel audits.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Ground GEODE design and evaluation work in Stanford CS329A Parts 2 and 5. Use for test-time compute, planning, multi-step reasoning, deep research, LATS, independent subplans, best-of-N, repair depth, measurement replication, verifier authority, and GEODE/Eco²/SIL/Crucible comparisons.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audit and improve Generative Engine Optimization as a measurable discovery-to-citation pipeline. Use for /geo, AI-search visibility, citation readiness, and GEO benchmark work.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Stress-test a plan, decision, or idea as a dependency-aware design tree. Use for grill-me requests, assumption audits, and decision clarification before implementation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

6-lens diagnostic slop audit — unused imports, dead private fns, duplicate signatures, abandoned TODOs, lint bypass markers, stale refs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Test-Driven Development workflow for Software Metrics Machine. Covers test frameworks (Vitest 4.x for CLI/REST/core/utils, Jest 30.x for webapp), test patterns (describe/it, builder pattern, mocks via vi.fn), test commands, coverage requirements, and the Red-Green-Refactor cycle. USE FOR: write tests, run tests, test this, add tests, testing, coverage, TDD, test-driven development, vitest, jest, test pattern, test convention. DO NOT USE FOR: linting (use lint skill), building (use build commands directly), debugging production issues.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Acceptance testing workflow for the Software Metrics Machine CLI e2e suite. Use when writing, extending, debugging, or reviewing bashunit acceptance tests under apps/cli/e2e, including command help checks, cached fixture flows, GitHub MSW-backed flows, local git repository fixtures, SMM_STORE_DATA_AT workspaces, and pnpm run test:cli:acceptance. USE FOR: CLI acceptance tests, e2e tests, bashunit, apps/cli/e2e, command smoke tests, persisted CLI output tests. DO NOT USE FOR: unit tests or Vitest tests (use tdd skill), linting (use lint skill), webapp browser tests.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Linting and code quality workflow for Software Metrics Machine. Covers ESLint 9.x flat config, Prettier formatting, lint-staged (auto-fix on commit), per-workspace configs, TypeScript strict mode, and all lint commands. USE FOR: lint, eslint, prettier, format, code style, linting, lint fix, auto-fix, check style, code quality, lint-staged, typecheck, type-check, tsc noEmit. DO NOT USE FOR: writing tests (use tdd skill), building (use build commands), commit hooks setup.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Notion の仕様ページをレビューし、セキュリティ・考慮漏れ・既存実装との整合性などの問題点をコメントとして報告するスキル。「仕様をレビューして」「スペックをチェックして」「review-spec」などの指示で呼び出される。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Discover and run tests that provide meaningful evidence for a code change. Use after implementation, before handoff or commit, or when the user asks to validate behavior.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Applies local reliability, viewport, tab-safety, stale-ref, widget, and browser-boundary lessons to every agent-browser automation. Use alongside the upstream agent-browser skill whenever navigating, clicking, filling, testing, extracting, taking screenshots, or debugging any website with agent-browser.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Manages Pi packages across their lifecycle: discovers, audits, installs, upgrades, removes, enables, disables, filters, and configures extensions, skills, prompts, and themes from npm, Git, or local sources. Use before any Pi package install or upgrade, when reviewing available updates, changing package activation or configuration, or maintaining the package inventory.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Revisa los cambios de UI en cuanto a accesibilidad — contraste de color, navegación por teclado, gestión del foco, uso de ARIA y texto alternativo. Úsalo cuando la persona pida una revisión de a11y/accesibilidad, verificar el cumplimiento de WCAG, el soporte de teclado, la compatibilidad con lectores de pantalla o el manejo del foco (p. ej. "¿es accesible este modal?", "audita la a11y del formulario").

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audita una vista o componente frente al design system en lo que un script no puede comprobar — estados de interacción, los cuatro estados de datos, primitivas nativas frente a componentes reinventados y jerarquía visual. Úsalo cuando la persona pida revisar el cumplimiento del design system o si un componente sigue las guías (p. ej. "¿esta tarjeta sigue nuestro sistema?", "audita la vista de ajustes").

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.