agent-workflow
Expert system for designing and architecting AI agent workflows based on proven Meta methodologies. Use when users need to build AI agents, create agent workflows, solve problems using agentic systems, integrate multiple tools into agent architectures, or need guidance on agent design patterns. Helps translate business problems into structured agent solutions with clear scope, tool integration, and multi-layer architecture planning.
council
Run multi-LLM council for adversarial debate and cross-validation. Orchestrates Claude, GPT-4, and Gemini for production-grade implementation, code review, architecture design, research, and security analysis.
graphite-stack-updater
Update Graphite PR stacks by addressing review comments and syncing PRs. Use when user says "update my graphite stack", "address the review comments on my stack", "sync my PR stack after these changes", "submit my entire stack to Graphite", or "I need to update all the PRs in my stack".
plan-executor
Execute implementation plans step-by-step. Use when user says "execute the plan", "implement the plan we created", "start building based on the plan", "go ahead and implement it", "proceed with the implementation", or references a plan file and wants to begin coding.
pr-creator
Create or update pull requests with conventional commits. Use when user says "create a PR for these changes", "submit this for review", "open a pull request", "push these changes and create a PR", "I'm ready to submit this work", or "create PR and link to issue #123".
ba
Task tracker for LLM sessions. Use "$ba ready" to see available work, "$ba claim <id>" to take ownership, "$ba finish <id>" when done.
updating-pr-title-and-description
Pull Request作成・更新時に使用。タイトルと説明文を自動生成・更新する。
semantic-committing
コミット時、「commit」「git add」「変更を分割」の言及時に使用。git diffを分析し、変更を論理的な意味単位に分割してコミットする。git-sequential-stageでhunk単位のステージングを行う。
pltr-cli
Helps you work with Palantir Foundry using the pltr CLI. Use this when you need to query datasets, manage orchestration builds, work with ontologies, run SQL queries, manage folders/spaces/projects, copy datasets, or perform admin operations in Foundry. Triggers: Foundry, pltr, dataset, SQL query, ontology, build, schedule, RID.
flow-coach
Interactive claude-flow orchestration coach that guides users through swarm topology selection, agent deployment, memory configuration, and SPARC workflows. Use when learning claude-flow, choosing between swarm vs hive-mind, selecting agents, or optimizing multi-agent coordination. NEVER auto-executes - always displays recommendations and asks first.
expert-routing
领域专家路由。当知识库无法回答用户问题时，根据问题领域查找并通知对应专家。仅在 IM 模式下可用。触发条件：6阶段检索无结果时。
using-cloud-cli
Cloud CLI patterns for GCP and AWS. Use when running bq queries, gcloud commands, aws commands, or making decisions about cloud services. Covers BigQuery cost optimization and operational best practices.
using-git-worktrees
Creates isolated git worktrees for parallel development. Use when starting feature work needing isolation or working on multiple branches simultaneously. Not for simple branch switching or basic git operations.
using-modern-cli
>-
skill-composer-studio
CHAIN multiple existing skills into custom multi-step workflows. Programmable skill combinations with automatic handoffs. Create composite skills from building blocks with conditional logic.
expert-panel
Assemble 2-3 complementary experts to collaboratively analyze anything. Experts work together to explore topics from multiple expert angles.
skill-orchestrator
This skill orchestrates programming tasks by analyzing available Claude Code skills and creating execution plans. It should be used when working on any coding task that could benefit from multiple specialized skills. The skill supports two execution modes selected by user - manual (Claude executes with explicit skill references) or delegated (tasks sent to sub-agents with skills).
book-sft-pipeline
End-to-end system for creating supervised fine-tuning datasets from books and training style-transfer models. Covers text extraction, intelligent segmentation, synthetic instruction generation, Tinker-compatible output, LoRA training, and validation.
Page 20 of 31 · 543 results