Review an agent or implementation plan for repo-truth alignment, overreach, missing validation, and sensitive-operation risk.
Render HTML-based graphics, carousels, thumbnails, and PDFs from brand tokens and content specs.
Implement uncompleted phase tasks. Verifies completion by reading actual code (not just checkbox state), respects Decisions & Notes, checks dependencies, and updates the Scope…
Use when implementing a deliverables package against a target. Not for checking or reviewing — use check-deliverables instead.
Execute JXA scripts scoped to a macOS application. Use when running JXA expressions or script files against an app via osascript. Validates Application() scope via AST.
카카오톡 다음 채팅방 목록. "카톡 다음 방", "더 보기", "kakao rooms next", "KakaoTalk more rooms" 시 사용.
카카오톡 이전 채팅방 목록. "카톡 이전 방", "앞으로", "kakao rooms prev", "KakaoTalk previous rooms" 시 사용.
Spec a Kibana dashboard — panels, KQL filters, on-call layout. No auto NDJSON export to prod.
Explains any target (a ticket, a file, a concept, or whatever is under discussion) the way you would explain it to a smart teenager, in a few plain sentences.
Show active live agents. Use when the user asks "list live agents", "who's live", or "show live".
Show active Psyche processes. Use when the user asks "list psyches", "show psyches", or wants to check Psyche status.
Show active owl listeners and clean stale perches. Use when the user asks "who's listening", "list agents", or "show active listeners".
Generate a Camunda Form (.form JSON) for user tasks. Use when creating forms for human task interaction.
Generate a job worker for a Camunda process. Detects language from project config (package.json or pom.xml).
Wdrożenie wersji na środowisko testowe z kontrolą stanu repozytorium. Stosuj, gdy człowiek wywoła /polecenie-wdrozenia; model nie uruchamia go sam.
Quick update to today's journal without full review. Use when user wants to quickly log something they did, add a journal entry, or note an activity.
Screaming Frog MCP crawl + issue classification. Crawls up to 500 URLs, extracts broken links, redirect chains, missing H1s, canonical errors, and missing meta descriptions.
Automatic domain diagnosis for Core Update recovery. Calls Sistrix + DataForSEO MCP, quantifies VI drop, identifies keyword losses, scans backlink profile, correlates with known…
Full recovery workflow orchestrator. Chains recovery-diagnose, recovery-crawl, recovery-plan, and recovery-monitor in sequence.
Weekly recovery tracking. Fetches current VI + keyword positions, computes 0-100 recovery score, appends to NDJSON history, outputs delta report.
Generates a prioritized recovery action plan from diagnosis + crawl data. Determines recovery phase (R1-R5), builds Do-Not-Touch list for stable keywords, prioritizes actions by…
Detect and mask PII in-line in the text, replacing it with label placeholders like [PERSON] and [EMAIL].
Assess the merits of each change recommended by each PR reviewer and recommend what actions to take in response
Test quality and coverage review — coverage metrics, gap analysis, flaky test identification, test quality audit, registry completeness. Use for periodic test health assessments.
Synchronize requirement docs, summaries, README, and changelog after behavior changes.
List root questions in the active rumil workspace. Shows short ID, date, and headline for each. Use this as a lightweight overview before diving into a specific question with…
Visualize all Claude Code session fork/branch relationships as a tree, showing session names, IDs, dates, and parent-child hierarchy
SKEIN task 闭环编排器。$1 路由阶段；$1=plan 或含 --plan 时路由到 skein-plan skill；$1=redo 时路由到 skein-redo skill；执行过程唯一真值源在 references/flow-loop.md。
从 wiki 条目生成 Marp 格式幻灯片。Use when the user wants to create a presentation from wiki content.
Compresses a long chat thread into a 5-bullet summary preserving decisions, action items, and unresolved questions.
DEPRECATED — use `/taw` instead. This shim forwards to `/taw` with the FIX branch. Kept for backward compatibility with earlier taw-kit versions.
Compare 2+ options with a dedicated advocate for each, counter-advocates who challenge every position, and a referee who ranks what survives.
Update the drifted_from_default front matter field for localized content. Accepts an optional comma-separated locale list (e.g.
Add or remove words from the speech recognition vocabulary hints. Use when the user wants to add a word to the dictionary or fix a speech recognition misrecognition.
Скопировать простой текст (без markdown) в буфер обмена (через custom tool clipboard).
Design a Zabbix template — items, LLD, triggers, graphs, macros. Markdown spec only.
Design Zabbix triggers — expression, recovery, severity, dependency, action hints. Sample docs only.
-Automatically convert documentation websites, GitHub repositories, and PDFs into Claude AI skills in minutes. — from qwzx4893-stack/WISE-Agent
Creates a GitHub issue based on a provided specification or context. To be used to create issues for features, bug corrections, or enhancements.
Claude Code ecosystem expertise. Modules: CLI tool (setup, slash commands, MCP servers, hooks, plugins, CI/CD), extensibility (agents, skills, output styles creation), CLAUDE.md…
EO MicroSaaS OS Guide v2 — master orchestrator for the 6-phase MicroSaaS journey. Creates workspace, detects progress, guides students phase-by-phase, handles language pr — from…
Phase 0: Read sector template (creative/fintech/ecommerce/devtool), generate OKLCH palette with chroma > 0.05, pick approved typography pair (never Inter/Roboto/Arial), d — from…
Оркестратор сквозного процесса разбора миссии. Управляет цепочкой шагов, проверяет результат каждого, принимает решение о продолжении или возврате.
Arquitecto de Soluciones Principal y Consultor Tecnológico de Andru.ia. Diagnostica y traza la hoja de ruta óptima para proyectos de IA en español.
Un skill simple pour commencer avec OpenClaw. Use when: vous voulez apprendre comment créer un skill, vous avez besoin d'un exemple minimal, vous testez le système de skills.
Enforces complete Taskwarrior integration protocol for ALL coding tasks. Activates automatically when user mentions "taskwarrior", "task warrior", "tw", or discusses task — from…
Use when you need to generate a checklist document with Java system prompts, following the embedded template exactly and producing INVENTORY-SKILLS-JAVA.md in the project — from…
Use when you need to generate a checklist document with embedded agents inventory, following the embedded template exactly and producing INVENTORY-AGENTS-JAVA.md in the p — from…
Use when you need to install the embedded robot agents into either .cursor/agents or .claude/agents, selecting the destination interactively and copying the embedded agen — from…
Austrian Impressum (legal notice) requirements for all company types. Covers ECG, UGB, GewO, MedienG, and Offenlegungspflicht for public media.
SEO configuration and best practices for TYPO3 v13/v14, including EXT:seo setup, sitemaps, meta tags, and structured data.
Monitor use when deploying monitoring stacks including Prometheus, Grafana, and Datadog. Trigger with phrases like "deploy monitoring stack", "setup prometheus", "configu — from…
Explains difficult concepts using master teaching methodologies (Feynman, Socratic, Cognitive Load, Dual Coding).
Guide for creating and enhancing skills. Use when users want to create a new skill, update/improve an existing skill, or audit skill quality.
Explains difficult concepts using master teaching methodologies (Feynman, Socratic, Cognitive Load, Dual Coding).
Codified expertise for production scheduling, job sequencing, line balancing, changeover optimisation, and bottleneck resolution in discrete and batch manufacturing.
NFL data via ESPN public endpoints — scores, standings, rosters, schedules, game summaries, play-by-play, win probability, injuries, transactions, futures, depth charts,…
Work autonomously without waiting for hand-holding — complete tasks end-to-end without asking for permission at every step.
🚨 LEITURA OBRIGATÓRIA ANTES DE QUALQUER CÓDIGO. Contém regras de ouro de processo, comandos SQL, deploy e correções críticas de UI (inputs pretos). Manda na arquitetura.
[01] META. Сканирует доступные skills, создает план выполнения и идет шаг за шагом с подтверждением каждого этапа.