Agents
AI agents and automation
command-creator
by softaworks
This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices.
helloagents
by hellowind777
AI-native sub-agent orchestration framework for multi-CLI environments
parallel-dispatch
by jmagly
Result schema: schemas/dispatch-result.schema.json
tot-exploration
by jmagly
@.aiwg/research/findings/REF-020-tree-of-thoughts.md - Research foundation
Auto-Provenance
by jmagly
@.claude/rules/qualified-references.md - Qualified reference rules
citation-guard
by jmagly
@.aiwg/research/docs/grade-assessment-guide.md - GRADE methodology
codemap
by jellydn
Orchestrate parallel codebase analysis to produce 7 structured documents about the codebase in .planning/codebase/
refine
by tkersey
Refine an existing Codex skill via $ms with minimal diffs, then validate with quick_validate. Trigger when asked to improve a skill's trigger description/frontmatter, workflow text, metadata, scripts/references/assets, or agents/openai.yaml; also for requests to iterate, refactor, rename, or fix a skill using usage/session-mining evidence (for example from $seq).
self-improvement
by peterskoett
"Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks."
ms
by tkersey
Create, update, or refactor Codex skills in this repo, including SKILL.md, frontmatter trigger text, agents/openai.yaml, and scripts/references/assets. Use when asked to create or improve a skill, tighten trigger descriptions from usage evidence (for example via $seq), regenerate/verify agents/openai.yaml, or adjust skill metadata/workflows.
async-jobs
by yonatangross
Async job processing patterns for background tasks, Celery workflows, task scheduling, retry strategies, and distributed task execution. Use when implementing background job processing, task queues, or scheduled task systems.
langgraph
by yonatangross
LangGraph workflow patterns for state management, routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming, subgraphs, and functional API. Use when building LangGraph pipelines, multi-agent systems, or AI workflows.
git-workflow
by yonatangross
Complete git workflow patterns including GitHub Flow branching, atomic commits with interactive staging, merge and rebase strategies, and recovery operations using reflog. Essential patterns for clean history. Use when managing branches, defining branching strategy, or recovering git history.
assess
by yonatangross
"Assesses and rates quality 0-10 with pros/cons analysis. Use when evaluating code, designs, or approaches."
review
by ballred
Smart review router. Detects context (morning, Sunday, end of month) and launches the appropriate review workflow. Use anytime for the right review at the right time.
agent-orchestration
by yonatangross
Agent orchestration patterns for agentic loops, multi-agent coordination, alternative frameworks, and multi-scenario workflows. Use when building autonomous agent loops, coordinating multiple agents, evaluating CrewAI/AutoGen/Swarm, or orchestrating complex multi-step scenarios.
audit-agent-consolidation
by melodic-software
Analyze agents for consolidation opportunities. Groups agents by configuration, tracks references, and manages refactoring.
hook-management
by melodic-software
Central authority for Claude Code hooks management in this repository. Automates enforcement of critical repository rules through hooks. Use when adding hooks, managing hooks, configuring hooks, troubleshooting hooks, or understanding hook behavior. Delegates to docs-management skill for official hooks documentation. Provides organization-specific patterns, configuration management, and workflow guidance.
agent-sdk-development
by melodic-software
Central authority for Claude Agent SDK (TypeScript and Python SDKs). Covers SDK installation, authentication (Anthropic key, Bedrock, Vertex), sessions and resumption, forking sessions, streaming vs single mode, custom tools, permissions (allowedTools, disallowedTools, permissionMode), MCP integration, system prompts (CLAUDE.md, appendSystemPrompt, outputStyle), cost tracking, todo tracking, structured outputs, hosting patterns, plugins, and SDK branding guidelines. Assists with building custom agents, configuring SDK options, and troubleshooting SDK issues. Delegates 100% to docs-management skill for official documentation.
clone-research
by wcygan
Comprehensive product research for building an MVP clone. Spawns 4 parallel research agents to produce 9 standardized documents: Product Thesis, Feature Priority Matrix, MVP Scope Contract, Core User Journeys, Domain Model, System Architecture, Revenue & Pricing Model, API Surface Spec, and Design System Brief. Use when planning a clone, building a competitor alternative, scoping an MVP, or analyzing a product to replicate. Keywords: clone, MVP, product research, teardown, feature matrix, domain model, reverse engineer, competitor clone
Product Discovery
by wcygan
Example queries and expected outputs
deep-dive
by wcygan
Deep dive into a codebase to understand specific topics, patterns, or implementations. Spawns parallel agents with distinct investigation strategies (breadth-first mapping, depth-first tracing, optional history/boundary analysis) then synthesizes findings into a layered summary. Use for understanding how something works, exploring unfamiliar code, or building a mental model of a large system. Keywords: deep dive, explore, understand, how does, architecture, codebase exploration, trace, investigate, mental model
business-review
by wcygan
Launch a multi-function business review team to evaluate product ideas, features, or applications from stakeholder perspectives. Agents represent product management, marketing, engineering, finance, data science, data engineering, sales, and synthesis roles. Use when evaluating a new feature, assessing product viability, planning launches, or need cross-functional input on business decisions. Keywords: business review, product evaluation, feature assessment, stakeholder analysis, cross-functional review, product viability, go-to-market, unit economics, technical feasibility
plan-mode
by wcygan
Research, analyze, and create a detailed implementation plan without making any code changes. Read-only planning mode with sub-agent exploration. Use when planning implementation, designing approach, creating technical plans, or analyzing before building. Keywords: plan, design, approach, implementation plan, analyze, research, strategy, read-only planning