Agent Skills Hub

query-writing

Writes, executes, and refines SQL queries, from basic selects to complex multi-table joins, aggregations, and subqueries for data retrieval and reporting.

context-degradation

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

deep-research

A systematic, multi-angle web research agent. Use for deep investigation, complex queries, and as a mandatory pre-research step before content generation to ensure evidence-backed, high-quality results.

tpmjs-tool-creator

Development guide for creating and publishing TPMJS tools using the blocks CLI, AI SDK v6, and npm registry patterns.

context-management

Proactive context window management for AI agents via intelligent token monitoring, snapshot creation, and selective state rehydration to maintain continuity during long sessions.

kungfu

Search, retrieve, and manage your KUNGFU.SH bookmarks programmatically to streamline your research and knowledge management workflows.

dajare

Generate high-quality Japanese puns (dajare) based on keywords, topics, or situations. Includes rhyme analysis and contextual humor generation.

parallel-agents

Orchestrate complex workflows by coordinating multiple specialized AI agents for multi-perspective code analysis, feature implementation, and system-wide reviews.

synthesizer

Synthesizes multi-agent research findings into coherent, citation-backed reports, resolving contradictions and identifying consensus.

spec-to-code-compliance

Verifies blockchain smart contract code against technical specifications, whitepapers, and design documents to ensure exact implementation compliance.

lgtm

Launch lgtm TUI to review markdown files, code plans, or documentation with line-by-line commenting, syntax highlighting, and collaborative feedback workflows.

paper-writing

Full-stack automated paper writing pipeline from research narrative to polished LaTeX/PDF.