Dev's honest review of mattpocock's Claude skills: 120+ questions, broken output
shydev69 · x · 2026-09-08
Developer shydev69 gave mattpocock detailed negative feedback on his Claude skills: grill-with-docs asked 120+ questions (many with only one sensible option), took ages, burned through his Astra quota, and still produced broken output. His own diagnosing-bugs and merge-resolve skills, and obra/superpowers' systematic-debugging, all performed better; only wait-what impressed him. His takeaway: spend 30 minutes writing your own skills — you get better results and own the blame when things fail.
More from coding & agent
- Spotify cut Claude Code tokens 90% with a 350-line routing rule, not a model breakthrough — krishnan · 2026-09-08
- A developer proposes an informal agent-native mathlib, tentatively named mathgraph — Sauers_ · 2026-09-08
- Ix builds a persistent symbol graph of your codebase across 26 languages for humans and AI — tom_doerr · 2026-09-08
- Dev builds FreeBuff MCP to route ChatGPT tasks to free agent models — Swimming_Ask3859 · 2026-09-08
- GitHub now classifies agent policy blocks as 'skipped', not failures — Crescitaly · 2026-09-08
- Companion launches iMessage AI agent that reuses your ChatGPT account with MCP support — Scobleizer · 2026-09-08