Topic: mcp
13,395 skills in this topic.
-
debugging-dags
Comprehensive DAG failure diagnosis and root cause analysis. Use for complex debugging requests requiring deep investigation like "diagnose and fix the pipeline", "full root cause analysis", "why is this failing and how to prevent it". For simple debugging ("why did dag fail", "show logs"), the airflow entrypoint skill handles it directly. This skill provides structured investigation and prevention recommendations.
astronomer/agents 295
-
managing-astro-local-env
Manage local Airflow environment with Astro CLI. Use when the user wants to start, stop, or restart Airflow, view logs, troubleshoot containers, or fix environment issues. For project setup, see setting-up-astro-project.
astronomer/agents 295
-
setting-up-astro-project
Initialize and configure Astro/Airflow projects. Use when the user wants to create a new project, set up dependencies, configure connections/variables, or understand project structure. For running the local environment, see managing-astro-local-env.
astronomer/agents 295
-
deploying-airflow
Deploy Airflow DAGs and projects. Use when the user wants to deploy code, push DAGs, set up CI/CD, deploy to production, or asks about deployment strategies for Airflow.
astronomer/agents 295
-
testing-dags
Complex DAG testing workflows with debugging and fixing cycles. Use for multi-step testing requests like "test this dag and fix it if it fails", "test and debug", "run the pipeline and troubleshoot issues". For simple test requests ("test dag", "run dag"), the airflow entrypoint skill handles it directly. This skill is for iterative test-debug-fix cycles.
astronomer/agents 295
-
refactor
Code refactoring workflow - analyze → plan → implement → review → validate
parcadei/Continuous-Claude-v3 3,690
-
ast-grep-find
AST-based code search and refactoring via ast-grep MCP
parcadei/Continuous-Claude-v3 3,690
-
tldr-code
Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.
parcadei/Continuous-Claude-v3 3,690
-
qlty-during-development
QLTY During Development
parcadei/Continuous-Claude-v3 3,690
-
repo-research-analyst
Analyze repository structure, patterns, conventions, and documentation for understanding a new codebase
parcadei/Continuous-Claude-v3 3,690
-
trace-claude-code
Automatically trace Claude Code conversations to Braintrust for observability.
Captures sessions, conversation turns, and tool calls as hierarchical traces.
parcadei/Continuous-Claude-v3 3,690
-
llm-tuning-patterns
LLM Tuning Patterns
parcadei/Continuous-Claude-v3 3,690
-
agent-context-isolation
Agent Context Isolation
parcadei/Continuous-Claude-v3 3,690
-
create-handoff
Create handoff document for transferring work to another session
parcadei/Continuous-Claude-v3 3,690
-
github-search
Search GitHub code, repositories, issues, and PRs via MCP
parcadei/Continuous-Claude-v3 3,690
-
mcp-chaining
Research-to-implement pipeline chaining 5 MCP tools with graceful degradation
parcadei/Continuous-Claude-v3 3,690
-
graceful-degradation
Graceful Degradation with Helpful Messages
parcadei/Continuous-Claude-v3 3,690
-
hooks
Hook Development Rules
parcadei/Continuous-Claude-v3 3,690
-
remember
Store a learning, pattern, or decision in the memory system for future recall
parcadei/Continuous-Claude-v3 3,690
-
loogle-search
Search Mathlib for lemmas by type signature pattern
parcadei/Continuous-Claude-v3 3,690
-
research-external
External research workflow for docs, web, APIs - NOT codebase exploration
parcadei/Continuous-Claude-v3 3,690
-
observe-before-editing
Observe Before Editing
parcadei/Continuous-Claude-v3 3,690
-
tldr-deep
Full 5-layer analysis of a specific function. Use when debugging or deeply understanding code.
parcadei/Continuous-Claude-v3 3,690
-
tldr-overview
Get a token-efficient overview of any project using the TLDR stack
parcadei/Continuous-Claude-v3 3,690