The LLM-facing contract for the deterministic claude-wiki-pages Bun engine — how ANY agent should call it.
Skill que detecta e instala o binário nativo first-plan-engine (Rust) na primeira invocação. Use quando algum command (cochange, hash, futuramente ast/index/search) for invocado e…
Writes production-ready code — reads patterns first, runs tests after, no gold-plating
Analyzes technical systems and problems through engineering lens using first principles, systems thinking, design methodologies, and optimization frameworks.
longClaw 运行时体检与诊断。用于检查 skill 不触发、hook 不生效、DEV LOG 异常、state.db 记账异常、memory 检索退化、配置迁移不完整等问题。Use when the user says 体检、自检、诊断、doctor、status、排查 longClaw、skill 不触发、hook 有问题、sidecar…
Generates Nano Banana Pro prompts for 4-panel engineer humor comics. Use when user mentions "漫画作成", "エンジニア漫画", "4コマ", or "あるある".
Improve broken prompts and context plans by choosing the smallest prompt-engineering technique that fits.
Transform extracted engineer expertise into an actionable skill with progressive disclosure, allowing agents to find and apply relevant patterns for specific tasks.
Engineer-minded execution orchestrator: takes a planned JIRA ticket and implements it with strict quality discipline — TDD, lint, typecheck, test, behavioral verify, PR.
Automate Enginemailer tasks via Rube MCP (Composio). Always search tools first for current schemas. — from general/automation
Prüft und gestaltet die englische Verfahrenssprache: Parteivereinbarung, Schriftsätze, Anlagen, mündliche Verhandlung, Protokoll, Urteil, Übersetzungen und BGH-Fortsetzung.
Draftet oder prüft englischsprachige Verträge mit deutschem Recht als anwendbarem Recht. Verhindert ungewollten Import von Common-Law-Konzepten, klärt governing language,…
A friendly AI English teacher that runs daily lessons via Telegram voice messages. Teaches grammar, vocabulary, and conversation with a casual buddy vibe.
Help users improve technical writing in English. Invoke when user needs to write or improve technical documents, comments, or documentation in English.
Detects and removes AI-generated writing patterns from English text. Rewrites content to sound natural, authentic, and genuinely human.
Английский репетитор с исправлением ошибок после каждого сообщения. Общается только на английском, задает уточняющие вопросы и соблюдает строгий лимит ответа (не более 50 слов).
English writing rules for generated content and code. Trigger: When generating, editing, or reviewing content, code, documentation, or prompts.
Sistema de memoria persistente para agentes IA. Usa mem_save después de bugfixes, decisiones, descubrimientos, cambios de config.
Compress and prune Engram memory after long sessions or when the store feels cluttered
Inspect a memory for conflicts and evidence, aggregate memory counts by category, or force-summarize a memory
Generate project-specific skills from Claude Code session history. Use when: (1) starting work on a new-to-you codebase, (2) onboarding to a project, (3) capturing learned…
Bulk-load files, directories, or exported chat histories into Engram; export memories to markdown
Recall past work from Claude Code history before starting new tasks. Use when: (1) starting work on a codebase, (2) asked about previous decisions, (3) need context about why code…
Summarize coding sessions into structured learnings using LLM extraction. Use when: (1) distilling lessons from recent work, (2) creating reusable knowledge, (3) building a…
Sistema de memoria persistente para agentes IA. Usa mem_save después de bugfixes, decisiones, descubrimientos, cambios de config.
Enhance frontend to pixel-perfect standards with mobile responsiveness and industry-leading design quality
Use when improving agent prompts, frontmatter, and tool restrictions.
Improve an existing R-based pictogram glyph for the visualization layer. Covers visual audit of the current glyph, diagnosis of specific issues (proportions, readability, glow…
Use when reviewing hooks for safety, timeouts, and correct frontmatter.
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better…
Use when improving general prompts for structure, examples, and constraints.
Use when reviewing SKILL.md files for structure and trigger quality.
_solutions/ MDX 파일의 문제 설명 및 풀이 품질을 개선합니다.
Transform simple prompts into comprehensive, context-aware prompts. Use for prompt enhancement, requirements analysis, and implementation strategy.
Enigma integration. Manage Deals, Persons, Organizations, Leads, Projects, Activities and more. Use when the user wants to interact with Enigma data.
Automate Enigma tasks via Rube MCP (Composio). Always search tools first for current schemas. — from general/automation
Enormail integration. Manage Mailboxs, Campaigns. Use when the user wants to interact with Enormail data.
Enrich person and company pages from external sources (Crustdata, Happenstance, Exa). Validation rules enforced.
Run enrichment pipeline on chunk directories
Find and add authoritative source links for all facts, citations, and references in markdown documents
Look up a company's full profile. Provide a company name, domain, ticker symbol, or ZoomInfo company ID.
Look up a person's full professional profile. Provide a name and company, email address, phone number, or ZoomInfo person ID.
Take an OCR archive that already exists in Paperless-ngx and push smarter titles, tags, and document metadata back into it.
Use when the user wants to fix or fill in missing Zotero abstracts, when they say "fix abstracts", "fill missing abstracts", "/zotero-context:enrich-zotero-abstracts", or when…
Visualize enrichment results using enrichplot package functions. Use when creating publication-quality figures from clusterProfiler results.
Enrow integration. Manage Organizations, Pipelines, Users, Goals, Filters. Use when the user wants to interact with Enrow data.
Guía para delegar tareas a los subagentes correctos según la dificultad del requerimiento.
Track Claude updates and new features directly from your development environment. (Codex skill for /ensemble:claude-changelog)
Lightweight workflow for bug fixes and small issues (Codex skill for /ensemble:fix-issue)
Optimize CLAUDE.md for token efficiency, standards discovery, and progressive context loading (Codex skill for /ensemble:fold-prompt)
Scan Linear for agent-ready issues in the Ensemble project, pick the highest priority one, implement it following TDD, verify with frontend and backend tests/lint, and create a…
Complete TRD implementation using git-town workflow with ensemble-orchestrator delegation and TDD methodology (Codex skill for /ensemble:implement-trd)
Generate real-time productivity metrics and team analytics dashboard (Codex skill for /ensemble:manager-dashboard)
Interactive wizard to pin Claude model tier mappings for this project (Codex skill for /ensemble:map-model)
One-shot migration from legacy ~/.config/ensemble/model-selection.json to project-level .claude/ensemble-model-config.json (Codex skill for /ensemble:migrate-model-config)
Run a comprehensive QA patrol on the Ensemble Tauri desktop app. Use when asked to check Tauri project health, run tests, lint code, or audit for issues.
Automated release workflow orchestration with quality gates, smoke test integration, (Codex skill for /ensemble:release)
Generate web performance metrics dashboard with Core Web Vitals (Codex skill for /ensemble:web-metrics-dashboard)
Automatic persistent memory for Claude Code sessions. Activates on preference statements ("I prefer", "I always", "I like"), corrections ("no, don't", "actually"), identity…
Augmented cognition layer that makes users smarter by connecting conversations to their persistent knowledge tree.