executing-plans
Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches
dispatching-parallel-agents
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
creating-workflows
Use this skill when creating automated multi-phase workflows for development tasks using claude-flow orchestration. Implements patterns for implementation kickoff, verification, retry loops, and failure recovery.
mise-task-managing
Use this skill when working with mise to manage your project. All projects should rely on mise for package management, encapsulating common tasks, and consolidating devops operations.
software-change-management-using-git
Use this skill when any task is complete, before beginning any non-trivial task, or whenever working with git or tasked with commiting code.
claude-code-optimizer
Claude Code productivity patterns including EPCC workflow, context management, and extended thinking triggers. Use when starting sessions or managing context.
mcpgraph
Build no-code MCP servers with tools that compose and orchestrate other MCP tools, with data transformation and conditional logic.
create-meta-prompts
Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).
llm-council
Multi-LLM collaborative brainstorming and planning. Use when user explicitly requests consultation with multiple AI models (ChatGPT, Gemini, other LLMs) before presenting an implementation plan, or asks to "consult the council", "ask other models", or "get perspectives from other AIs". Queries external LLM APIs, synthesizes their perspectives, and presents an adapted implementation plan.
temporal
Operate Temporal workflows in this repo: start/list/inspect workflows, fetch history, debug nondeterminism, reset/cancel/terminate, and check task queues via Temporal CLI.
github
Work with GitHub in this repo: PR creation, CI checks, and gh CLI operations.
pr-process
Prepare commits and pull requests for this repo following the PR template and Conventional Commits.
github-issue
Create GitHub issues in this repo using the Codex issue template and the gh CLI. Use when the user asks to file/open/create a GitHub issue, track work, or request a Codex implementation run via .github/ISSUE_TEMPLATE/codex-task.md.
Convex Agents Workflows
Orchestrates multi-step agent operations with durable execution, automatic retries, and recovery from failures. Use this for complex workflows that need to survive server restarts or coordinate multiple agents.
Convex Agents Human Agents
Integrates human agents into automated workflows for human-in-the-loop interactions. Use this when humans need to respond alongside AI agents, handle escalations, or provide context that AI cannot determine.
xlsx-editor
Specialized guidance for editing EXISTING Excel files with emphasis on preserving formulas, formatting, and structure across multiple tabs. Use this skill when modifying, updating, or adding data to existing .xlsx files where maintaining integrity is critical—particularly for multi-tab workbooks, complex formulas, formatted tables, and data that must maintain sort order and relationships across sheets.
skill-dependency-mapper
Analyzes skill ecosystem to visualize dependencies, identify workflow bottlenecks, and recommend optimal skill stacks. Use when asked about skill combinations, workflow optimization, bottleneck identification, or which skills work together. Triggers include phrases like "which skills work together", "skill dependencies", "workflow bottlenecks", "optimal skill stack", or "recommend skills for".
token-budget-advisor
Proactive token budget assessment and task chunking strategy. Use this skill when queries involve multiple large file uploads, requests for comprehensive multi-document analysis, complex multi-step workflows with heavy research (10+ tool calls), phrases like "complete analysis", "full audit", "thorough review", "deep dive", or tasks combining extensive research with large output artifacts. This skill helps assess token consumption risk early and recommend chunking strategies before beginning work.
Page 15 of 31 · 543 results