Multi-chain blockchain protocol and on-chain indexing research plugin. Ships three chain-specific skills: blockchain-research:ethereum-researcher (EVM, EIPs, go-ethereum, reth, revm, prysm), blockchain-research:solana-researcher (SVM, SIMDs, PoH, agave, SPL, Anchor), blockchain-research:tempo-researcher (TIP-20, TIP-403, MPP, Simplex BFT, Payment Lanes, Fee AMM, tidx). All skills share a chain-agnostic procedure base (quick / full mode branching, on-demand submodule install, 24-hour update cache, manifest-driven setup). Each skill produces reports via the plugin-level shared MD / HTML templates with Mermaid and inline SVG. Use the relevant chain skill whenever the user is investigating that chain, even without the word 'research'.
3 skills
AI coding agent instruction file init and retrofit. Builds a single routing chain so every AI tool reads the same source: tool symlink -> AGENTS.md -> .agents/README.md (overview plus top-level directory routing table) -> each top-level <dir>/README.md -> detail files. Sets up AGENTS.md, idempotent symlinks across major AI tools (Claude Code, Cursor, Copilot, Windsurf, Cline, Roo Code, Gemini CLI, Codex, Zed, Antigravity, Amp, Aider, Continue), and a .agents/ meta directory (README, schema, conventions, preset.json, hooks/pre-commit-secrets.sh, local). No agents/ content directory and no team or hub mode branching - the chain is single-mode and AI-first. Bundles a meta-validator companion skill that auto-fixes frontmatter / relations / git timestamps, rebuilds .agents/.tag-index, scans for secrets, and enforces tight length recommendations (AGENTS.md 50/80/120, README.md 80/120/200). Use whenever the user wants to initialize a project, bootstrap AGENTS.md, unify instruction files across AI tools, retrofit an existing project, validate routing READMEs, or make a repo AI-navigable - even if they say 'AI rules', 'agent config', or 'check AGENTS.md'.
2 skills
Markdown knowledge base init and retrofit. Creates .kb/ meta directory plus preset top-level directories (team-docs, research, product, custom, career). Every .md file carries required frontmatter (title, created, updated, summary, tags, status, relations). Phase 0.5 verifies tool dependencies (yq or python+PyYAML, gh for career, optional ripgrep/gitleaks/lychee) with OS-aware install on opt-in. Installs a pre-commit secret-scan hook, and for the career preset (roles, resumes, projects, skills, brag, learning, reviews, goals) also a pre-push hook that blocks pushing to a public repository. Bundles a companion kb-validator skill that syncs timestamps from git log, prunes broken relations, rebuilds .tag-index, enforces README per directory, and flags length recommendations. Use whenever the user wants to initialize a repo as a shared knowledge base, set up a personal career portfolio, retrofit existing docs, prepare docs as a submodule, or make markdown AI-navigable - even if they say 'docs init', 'career portfolio', 'set up wiki', or 'validate kb'.
2 skills
Elasticsearch best practices covering mapping, query DSL, index settings, bulk indexing, analyzers, shard sizing, aggregations, pagination, ILM, aliases, and cluster monitoring. Use when designing or changing index mappings, writing or tuning search queries, configuring analyzers, planning shards, building bulk indexing pipelines, or diagnosing Elasticsearch performance issues.
1 skill
Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications. Use when writing, reviewing, or optimizing Go code, designing packages, writing tests, or benchmarking performance.
1 skill
Postgres performance optimization and best practices. Use when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.
1 skill