Conor Bronsdon

avoid-ai-writing. Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude Code, OpenClaw, and Hermes.

substack-mcp. MCP server for Substack — read posts, manage drafts. No publish or delete by design.

claude-context-os. An operating system for your Claude context — version-controlled files, a self-curating memory, and a /start→/end session loop. Works in Claude Code and claude.ai.

claude-code-skills. Production-tested skills for Claude Code — session management, multi-session reconciliation, worktree recovery, and skill scaffolding

gws-mcp-server. Curated MCP server for Google Workspace: Gmail, Calendar, Drive, Sheets, Docs, and Tasks via the official gws CLI. 41 focused tools instead of 400.

wrekenfile-converter. A TypeScript/JavaScript library for converting OpenAPI specifications (v2 and v3) and Postman collections into Wrekenfiles, declarative YAML artifacts that act as the single source of truth for API methods, workflows, headers, and responses.

ai-tools-for-creators. Curated AI skills, MCP servers, and workflow tools for content creators and knowledge workers

aoe2-troop-calculator. An Age of Empires II: troop calculator built to enable easy army composition & cost calculations(without complex excel sheets). Inspired by Hera vs. Lewis, built for AOE2 Definitive Edition.

track-finder. Paste or import a tracklist, get SoundCloud / Spotify / YouTube / Apple Music search links for every track

cot-bench. Open agent evaluation leaderboard with multi-judge scoring

ai-learning-resources. Curated learning path from 'what is AI?' to building with Claude Code and MCP. Quality over quantity.

podcastindex-mcp. MCP server for the Podcast Index API — search podcasts, track appearances, monitor trending shows, check feed health

wrekenfile-demo. Real-world demo of the wrekenfile-converter against the Podcast Index API (OpenAPI 3.0.2 → Wrekenfile v2.0.2)

mojo-xml. General-purpose XML in pure Mojo — an xml.etree.ElementTree-shaped DOM. 14/14 CPython byte-match.

agent-memory-kit. The curation pass for agent memory: a thin, file-based loop that finds rot and contradictions and proposes evidence-cited diffs you review. Markdown in, JSON out, no database.

mojo-diff. Myers text diff + unified_diff in pure Mojo — byte-for-byte match with Python's difflib.

mojo-redis. RESP2 Redis client in pure Mojo — redis-py-shaped API, live-server tested, hardened.

mojo-template. Standalone Jinja-flavored template engine in pure Mojo — mirrors Python's jinja2.

op3-mcp. MCP server for OP3 podcast analytics: downloads, geography, app share. Read-only.

mojo-markdown. CommonMark parser + HTML renderer in pure Mojo — 98.6% spec conformance. Mirrors Python's markdown.

mojo-url. URL parsing, building & query-string encoding in pure Mojo — mirrors Python's urllib.parse.

mojo-unicodedata. Unicode normalization (NFC/NFD/NFKC/NFKD) + casefold in pure Mojo — mirrors Python's unicodedata.

mojo-feed. RSS, Atom, and JSON Feed parsing in pure Mojo — mirrors Python's feedparser. No deps, no FFI.

mojo-html. Liberal HTML parsing + readability article extraction in pure Mojo — mirrors Python's readability.

mojo-tar. tar archive reader/writer in pure Mojo — ustar/GNU/pax, GNU-tar byte-identical. Mirrors Python's tarfile.

mojo-captions. SRT & WebVTT subtitle/transcript parsing in pure Mojo — speakers, voice spans, round-trip, clip windows.

podcast-benchmark. Benchmark any podcast against its peers on public data: cadence, transcripts, feed hygiene. No download estimates.