LLM & Agents

Orchestrator agent for coordinating multiple AI agents in a persistent system

Verifies content matches user search intent to maximize sales, leads, digital sales, and mailing list growth through 34 verification modules and 16-part scoring system

Keep project documentation (CLAUDE.md, .env.example) in sync with actual configuration changes. Use after major configuration changes, environment setup modifications, or when user requests "update documentation" or "sync docs with current setup".

Integrates Gemini AI for content generation. Use when adding AI features, generating project descriptions, implementing rate limiting, or working with geminiService.ts. Includes prompting guidelines and error handling.

This skill installs a complete Claude Code skill tracking system using hooks to automatically log skill usage, execution duration, token usage, and user prompts for later analysis. Use this skill when setting up activity tracking in a Claude Code project to identify patterns, monitor costs, and discover opportunities for new skills.

Vector database selection, indexing strategies, and semantic search optimization.

Convert verified algorithmic research into structured, machine-readable frameworks describing how social media platforms rank, reward, and penalize content. Provides factual, updatable platform rules for strategy agents (social-media, content, brand) to reference when developing or evaluating strategic decisions. Use this skill when needing to extract algorithmic mechanics from research, create posting playbooks, or validate content strategies against current platform rules.

Prepare complete PR content ready for creation via reedom-gh:pr-maker agent.

Coordinates the 43-day Malaga Embassy sprint, managing €1,500 capital with constitutional cascade compliance (20/10/15/40/15). Tracks 3 revenue streams (Agent-as-a-Service, Intel Services, Proposal Consultation) targeting €855-1,910/month. Calculates health scores (0-100), provides spending guidance (not blocking), and activates emergency protocols when runway falls below 14 days. Use when discussing Malaga operations, embassy budget, revenue activation, or Captain BROlinni's deployment.

World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.

Use when user asks where to put configuration, skills, or learnings, or discusses sharing config across projects. Provides decision criteria for the three-tier architecture (global ~/.claude, plugin, project-local .claude) to prevent duplication and ensure reusability. Invoke before creating new skills or configuration to determine the correct tier and location.

指导用户为 Claude Code 创建系统级 Agent Skills，支持多个业务子 Skill 的模块化设计。当用户想要创建、编写或设计系统级 Skill，或提到"生成 skills-list / 更新技能清单 / generate_skills_list"时使用。脚本 `scripts/generate_skills_list.py` 仅存放于本 skill-writer 目录，其他系统级 Skill 不需要复制；需要更新清单时由 skill-writer 脚本对目标 Skill 目录执行。

ブログ記事に必要な情報を深くリサーチするエージェント。技術的なトピック、最新の情報、ベストプラクティス、関連する事例などを包括的に調査し、信頼性の高い情報を提供します。ブログ記事の執筆時に、詳細な情報や最新の情報が必要な場合に使用してください。

Wolf's 10 core principles for agent behavior and system design

사용자의 개발 프로필 정보를 관리합니다. 사용자의 기술 스택, 선호도, 경험 수준에 대한 질문이 필요할 때 자동으로 활성화되며, ~/.agents/WHOAMI.md 파일에서 정보를 읽습니다. 파일이 없으면 대화형으로 프로필을 생성합니다.

Helper methods for PM agents to read, write, and update workflow-state.json files consistently during workflow execution. Use when managing workflow state persistence, tracking wave progress, handling HITL stops, or resuming workflows.

This skill uses the Renku CLI to generate video compositions given an inquiry prompt. It can generate all the media files required for the composition and stitches them into a final video.

Use when editing or improving methods sections with incomplete protocols, missing reagent details, insufficient statistical information, or poor reproducibility - ensures CNS-level rigor with complete reagent specification, statistical transparency, and ethical compliance

End-of-session summary that logs work completed to Obsidian. Run this at the end of any Claude Code session to capture what you accomplished. Creates or appends to the daily session log.

Semantic versioning helpers and release scripts. Use when managing versions, bumping version numbers, creating releases, generating changelogs, or when user mentions versioning, semantic versioning, release management, version bumps, or semver.