Agent Skills Hub

mcpgraph

Build no-code MCP servers that orchestrate tools as directed graphs using YAML for data transformation, conditional routing, and automated workflows.

performing-systematic-debugging-for-stubborn-problems

Executes a rigorous, multi-phase Fagan Inspection to systematically resolve persistent, stubborn bugs and complex code interactions.

market-debrief-cn

A deep analysis tool for A-share markets generating interactive, FT-style HTML daily reports using multi-agent parallel architecture, AkShare data, and Tavily news.

Project-Management-Interactive-copilot-test

A universal skill for automating GitHub Project V2 Kanban boards, supporting status transitions, sprint management, and interactive workflows via CLI.

workflow-producer

A stage-driven AI writing agent for structured, repeatable, and reversible long-form content production with human-in-the-loop workflows.

autoresearch

Autonomous multi-team codebase improvement agent with specialized modes: narrow (goal-directed), broad (hypothesis-divergent), and sweep (quality-focused).

bazinga-db-core

Manage database orchestration sessions, state snapshots, and system-level operations for the BAZINGA-DB core engine.

service-mesh-observability

Implement production-grade observability for Istio and Linkerd service meshes, including distributed tracing, metric dashboards, and golden signal monitoring.

context-degradation

Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.

sui

Debugs deterministic Sui simtest failures using automated logging and the scientific method.

flaky-detect

Identify, categorize, and troubleshoot flaky tests by analyzing CI history, execution patterns, and code structure to improve test suite reliability.

performance-analysis

Systematic performance engineering: baseline measurement, profiling, bottleneck diagnosis, and evidence-based optimization guidance for high-performance applications.