Генерира офертен документ — попълва шаблона на поръчката с фирмени данни и ценообразуване. Използва се след ценообразуване с eop-price.
자기소개서 초안 작성 전 단계에서 사용할 에피소드를 체계적으로 발굴하고 정리합니다. 경험 소재를 인수분해하여 직무별로 분류하며, 프로젝트 폴더를 지정하면 파일 기반 자동 추출도 가능합니다.
Use when: a concrete defect, incident, review finding, PR review comment, test failure, or bug report suggests a class of equivalent defects across sibling fields, mirror use…
Reviews error handling strategy and exception design. Use when the user asks to review error handling, when a module throws too many exceptions, or when callers must handle errors…
Performs a comprehensive error-handling review across the codebase, checking coverage, propagation, and recovery.
Enruta incidencias de revisión contractual al aprobador correcto según la matriz de escalado
Use when planning a feature and need to understand token cost, time estimate, or complexity before committing to implementation.
Evaluate a company's +$1B exit potential using Titus's 7-filter investing framework. Use when asked to analyze, grade, or score a company's unicorn potential, or to compare…
하네스가 선언한 규칙이 실제로 차단되는지 외부 서브에이전트로 독립 검증합니다. 선언-실행 단절, 회피 경로, 포인터 무효점을 적발하고 보고만 수행하며 직접 보강하지 않습니다.
Load the latest model checkpoint, run evaluation on the test set, and generate a metrics report with confusion matrix.
Distill an ex-partner into an AI Skill. Import WeChat history, photos, social media posts, generate Relationship Memory + Persona, with continuous evolution.
Examensprognose auf Basis vergangener JPA-Klausuren, Statistiken des BMJV und bekannter Schwerpunktmuster.
An example user-invoked skill that demonstrates frontmatter options and the skills//SKILL.md layout
Deploy the application to a target environment. Use when deploying code, releasing, or pushing to staging/production. Requires explicit user invocation.
Traces how errors and exceptions flow through critical code paths to find swallowed errors and broken propagation. Use when analyzing exception handling on important paths.
ONLY when user explicitly types /exe-plan. Never auto-trigger on execute, run, or implement.
Run the execution + quality polish + delivery stages of review-loop against one of three entry modes: resume an approved session (`--session`), execute a user-supplied plan…
Execute an implementation plan by working through each task file in order. Use when an implementation plan folder exists at docs//implementation_plan/.
Background-dispatch variant of execute-phase. Spawns one `claude --bg --agent maxv-executor` session per plan (with auto-worktree) instead of running waves of in-process Agent…
Execute a multi-phase plan one phase at a time. Reads the plan, identifies all phases, then executes only the requested phase (or next pending phase).
Use this skill when executing all plans in a phase with wave-based parallelization, running phase execution, or completing phase work.
Generate implementation report — with smart process improvement when divergences are found
Force the Completed Staff Work method to structure engineering communication — present analyzed options plus your recommendation for approval to merge or ship a risky change.
Force the SCQA (Situation, Complication, Question, Answer) opening to structure engineering communication — RFCs, design docs, and proposals for a reviewer who needs context…
Plan expansion revenue for a healthy customer — identify signals, frame as enablement, and design an expansion approach.
This skill should be used when the user wants expert reviews on a document, plan, or deliverable. Trigger on "expert-review", "전문가 리뷰", "리뷰 부탁", "expert review", "페르소나 리뷰", "전문가…
Explore a Weaviate collection's data, including property metrics and sample objects
Profile and explore a dataset to understand its shape, quality, and patterns. Use when encountering a new table or file, checking null rates and column distributions, spotting…
Systematically explore a codebase area and find/fix obvious issues with fresh eyes.
Full inventory and audit of AWS Glue Data Catalog assets across S3 Tables, Redshift-federated, and remote Iceberg catalogs.
Export an HTML artifact to PDF via headless Chromium (puppeteer Page.pdf). For multi-slide decks one page per
Export an HTML deck to PPTX via per-slide screenshots. Requires Node + pptxgenjs + puppeteer (run /doctor first).
Write an expository paper: precise definitions, diagrams, examples, and known theorems with proofs in your own words. Arrange pedagogically so no idea is used before it is proved.
Invoke parallel document-specialist agents for external web searches and documentation lookup — from Yeachan-Heo/oh-my-claudecode
Integrates patterns from external sources (URLs or local files) into local skills, agents, and plugins.
This skill should be used when the user asks to "extract audio", "get the mp3", "strip audio from video", "rip audio", "save audio from video", "convert to audio", "get the…
Custom-label named-entity recognition (gliner2-base-v1). Use when the user wants to extract entities with their own labels — people, organizations, locations, products, dates, or…
Schema-driven structured JSON extraction (gliner2-base-v1). Use when the user wants to pull specific named fields out of free text into a JSON object — contact info, invoice…
Extract intra-paper justification structure and author it through pks source propose-justification.
Extract PII entities from text (gliner-multi-pii-v1). Use when the user wants to find personally identifiable information — names, emails, phones, addresses, financial identifiers…
Walk a company's existing artifacts (Slack export, Notion export, GDocs, markdown vault, or any folder of documents) and emit draft hookify rules, draft skills, and a draft…
Extract TikZ diagrams from Beamer source, compile to PDF, convert to SVG with 0-based indexing. Use when updating TikZ diagrams for Quarto slides.
Migrate a Jakarta Faces project from one version to another (e.g. JSF 2.3 to Faces 4.1)
Review Jakarta Faces code for common mistakes, anti-patterns, and rule violations
Verify factual accuracy of a document against the codebase and git history. Use when asked to verify, fact-check, or audit claims in a report or document.
Use when: fact-checking factual claims, verifying citations/source support, checking draft/report accuracy, reviewing evidence quality, assigning…
Create a skill with automatic quality validation. Uses Manager Pattern: Task creates → Forked Skill audits → Retry if needed.
Intake e organizzazione fascicolo lavoro: timeline, allegati, ruolo cliente, prossimi atti. Integra testatti licenziamento. Nessuna consulenza legale.
Workspace mandato: struttura cartelle, naming, privilege note, indice allegati. Cross-materia (civile, lavoro, privacy). Nessuna consulenza legale.
Matter workspace privacy: fascicoli DSAR, DPA, violazioni, DPIA. Struttura cartelle, matter.md, collegamento CLAUDE.md. Nessuna consulenza legale.
Trivial inline design task. No subagents, no planning documents, no pipeline stages. Just do the thing described.
Comprehensive product feasibility study with effort and cost estimation. Analyzes technical, economic, market, operational, and schedule feasibility using the TELOS framework.
Manages OrchestKit learning system including feedback status, usage pattern tracking, and privacy/analytics consent.
Drop in the user-feedback subsystem (DB migration + API handlers + UI submit widget + view-my-feedback page + CHANGELOG citation wiring) per project stack
从飞书聊天记录构建个人数字分身 skill — 拉取你发出的消息，分析沟通风格、领域知识和判断模式，生成一份可供他人调用的纯静态个人 skill。触发：'把我做成skill'、'build skill of myself'、'制作我的数字分身'、'生成个人skill'。
Fetch internal company documentation, framework examples, or platform guidelines into the current AI context.
Retrieve saved plan folders from `.ai/planning`, let the user choose one, then load its planning documents and summarise implementation status.
Fetch an RFC from Notion given a URL. Use when user wants to view, review, or work with an existing RFC document. Accepts Notion page URLs or page IDs.
Figma URL 또는 node ID가 주어지면 디자인을 분석하고 구현 계획서를 작성한다. 참조할 기존 코드 없이 처음부터 구현할 때 사용. 참조 코드가 있으면 figma-reference-plan을 사용.
Compare running app screens against Figma designs — captures screenshots from both sources and produces a structured gap report