goodand

Export deterministic component-level OCR evidence for one transparent or semi-transparent image by splitting alpha-connected components, writing a component table, and running OCR on each component. Use when bounded component evidence must be exported before any downstream refinement or caption rerun.

Extract bounded OCR evidence from local image files with macos-ocr-mcp, using macOCR only as a fallback reference when MCP coverage is insufficient. Use when downstream refinement or review needs visible-text evidence, not final semantic decisions.

Wrap object-isolation correction as a repo-specific workflow. Use when a local image already exists, the current isolation result is imperfect, and the next step is to choose between ImageSorcery-first, imagegen-first, or a hybrid correction path with a bounded correction packet and worker run.

Promote a bounded parser raw sidecar artifact into the canonical Table -> Row -> Cell schema. Use when a parser MCP returned markdown plus nested JSON sidecars and the project must normalize that output before any downstream wrapper, worksheet, or RAG consumer reads it.

Triage a bounded batch of PPT-extracted images to find the small subset that is mechanically sufficient for alpha-only component splitting. Use when conservative preprocessing is required and only review-gated deterministic candidates should advance beyond the full-image baseline.

Operate an existing markdown review surface in VS Code with fabriqa for same-page image editing and Foam for backlinks and graph navigation, without redefining machine-truth semantics.

Dispatch one-image-per-worker jobs for the presentation image pipeline. Use when you need to register image jobs, fan out isolated Codex subagents, and keep MCP state as the source of truth.

Audit completed image jobs and export frozen comparison bundles from evidence-backed records. Use when you need approval candidates, retry candidates, comparison summaries, or auto-eval outputs without mutating upstream artifacts.

Safely execute a delegated repository task by proving the git environment, protecting dirty worktrees, running required gates, choosing commit/push or patch export, and halting instead of publishing when verification fails.

Use when building or debugging format converters, parsers, or export pipelines (e.g. HTML→PPTX, DOM→IR, doc→doc): three cross-checking techniques — probe-first classification, dual-source extraction, declaration-level validation — because no single representation of the data can be trusted.

Build converter/parser fixture matrices by probing third-party trees before handlers, adding regression fixtures before feature fixtures, declaring expected behavior and primary gates, isolating outputs, and making renderer checks opt-in.

Create, critique, and validate Mermaid architecture diagrams

Record decisions reached through interview as a non-authoritative repository document that preserves consensus across sessions and across agents. Use whenever interview outcomes need to outlive the conversation in a form that future readers — both human users and other agents — can act on without re-deriving the reasoning.

Run a structured interview where one decision is taken per turn, automatic inferences from prior consensus are surfaced before manual questions, and depth on each decision is preferred over interview round-trips. Use whenever a user needs to make a sequence of related decisions whose record will outlive the conversation.

Process an external evaluation report into prioritized work groups with clear dependencies, separating procedural fixes from substantive interview questions and keeping each group small enough for a single self-contained delegation. Use whenever an external agent or reviewer has produced a list of findings that the project needs to act on without re-litigating each finding.

Diagnose and recover when the same delegated instruction halts repeatedly, by treating environment assumptions as falsifiable and revising the instruction rather than the receiving agent. Use whenever two or more attempts at the same task have failed in a way that suggests the writing agent's model of the executing environment is wrong, not that the executing agent is misbehaving.

Codex JSONL, Gemini JSON, Claude transcript 출력을 파싱하여 구조화 요약을 생성할 때 사용한다. parse-only 작업에만 직접 사용. full workflow(review → parse → save)가 필요하면 cross-agent-bridge를 먼저 사용하라.

cross-agent-bridge family의 raw Codex CLI executor. Codex CLI를 headless로 실행하고 prompt/file/session/sandbox를 제어하는 전용 specialist. bridge.py 리뷰나 full workflow는 cross-agent-bridge를 사용하라.

Claude Code, Codex CLI, Gemini CLI/SDK를 하나의 CLI로 오케스트레이션할 때 사용한다. 에이전트 간 리뷰 요청(review/codex-review), 출력 파싱(parse), 환경 진단(doctor), 초기 설정(setup)이 필요할 때 트리거한다. 단일 스킬 설치로 상호 피드백 워크플로우를 재사용할 수 있다.

cross-agent-bridge family의 raw Gemini CLI executor. Gemini CLI를 headless로 실행하고 prompt/file/stdout을 중계하는 전용 specialist. SDK 리뷰는 gemini-reviewer, full workflow는 cross-agent-bridge를 사용하라.

Gemini SDK/CLI로 코드나 문서 리뷰를 요청할 때 사용한다. Gemini review-only 작업에 직접 사용. full workflow(setup → review → parse → save)나 Codex 리뷰가 필요하면 cross-agent-bridge를 먼저 사용하라.

현재 프로젝트에 claude-gemini-communicator 3-Agent 협업 시스템을 설치하거나 제거한다. Hook 3개 등록 + Skills 5개 심링크. 중복 설치 방지, 안전한 제거 지원.

Diagnose and repair RAG artifact metadata contract failures before patching downstream evaluators. Use when retrieval/eval artifacts have missing or inconsistent item metadata such as `canonical_doc_key`, `child_id`, `chunk_index`, `source_space`, or `parent_id`, or when downstream symptoms appear such as `alignment_row_count=0`, `CC_adj_lexical=0`, `SR_fragmentation_proxy=0`, empty `reranked_contexts_items` fields, or report-facing key drift.

Use this skill when reconstructing Claude or Codex session history from `.claude/projects/*.jsonl`, sibling `memory/` files, referenced handoff markdowns, or `.specstory/history/`. Use it to identify the latest unfinished task, connect session-internal and post-session documents, distinguish upstream objective from downstream TODOs, or recover provenance for timeline-based debugging.

RAG 실험을 실행하고 결과를 수집한다. preflight 검증 → 실험 실행(checkpoint resume) → metrics 추출 → 결과 저장 → MASTER 갱신까지 하나의 워크플로우로 처리. YAML config 기반.

RAG 실험을 사전 검증(preflight)부터 실행, checkpoint resume, chain 오케스트레이션, multi-metric 수집(IC/CC/SR/DocHit/MRR), 보고서 생성까지 자동화한다. 경로/형식/인코딩 같은 boundary 문제를 실행 전에 잡고 싶거나, 실험 후 측정 5단계를 한 번에 묶고 싶을 때 사용한다. YAML config 기반.

RAG 실험 결과를 측정·비교·분석한다. 실험 결과 JSON을 입력받아 모드별 메트릭 산출, cross-mode 비교, hop_type/hit_category별 분해, 종합 보고서를 생성한다. eval-runner(실행 오케스트레이션)와 보완 관계. "성능 비교해줘", "메트릭 뽑아줘", "hop별 분석", "벤치마크 리포트" 등의 요청에 트리거된다.

AI/ML 애니메이션 플레이어 scene 구현·승격·연동.

Babel 다중파일 JSX 프로젝트 scope 관리.

파일 편집 전 반드시 읽고 검증하는 절차.

Transformer 해부도 Z/P 데이터 편집·검증.

Use this skill to generate well-branded ML/DL educational animations and interfaces for 축(Chuk), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, structural mode system, visual-strategy (Markdown) router, and UI kit components. Built on the DaleStudy/daleui open-source foundation with Korean typography support.

Use this skill when creating animation storyboards, graph diagrams, scene-object plans, or visual explanation flows for Text Similarity, RAG, KNN, NNS/ANN, TF-IDF, Jaccard, cosine similarity, lexical/semantic comparison, and related ML concepts. It routes the task to focused reference policies for UX, design system, five-unit explanation, visual formats, graph policy, and scene-object planning.

DS 토큰 컴플라이언스 검사 및 교체 절차.

Use this skill to generate well-branded interfaces and assets for Axis (축) — an AI Hangul font / design system generator — either for production or throwaway prototypes/mocks/decks. Contains brand guidelines, color tokens, typography, fonts, logo assets, and a flagship UI kit for the Axis Studio product.