Autoprompt skill: fewer failures, more tokens
Autoprompt solves 73 of 89 Terminal-Bench 2.1 tasks against a baseline of 60, at roughly 3x the time and 2x the tokens. What that costs on a rented VPS.
#agent-skills
Filtering by topic #agent-skills · clear
The unlazy skill and its Depth Tree method
How the unlazy skill stops an agent declaring done early: the Depth Tree, gates files, the PLAN.md contract, install steps, and what the depth costs you.
Old Coder skill: review evidence, not code
Your agent writes a SPEC you approve and an EVIDENCE report you can rerun yourself. Inside the Old Coder gauntlet: what mutation testing adds over coverage.
Turn a Technical Book Into an Agent Skill
Convert a PDF, EPUB or folder of internal docs into an agent skill your coding agent loads on demand: install, token budget, headless runs, licensing.
How to Write Your Own Agent Skill
Write your own agent skill by distilling one real failure: the SKILL.md anatomy, the description line that decides when it fires, and how to test it.
Claude Code plugins: what they are and cost
What a Claude Code plugin is, where it lives, how to install one, and what it really costs: nothing for the mechanism, tokens for everything it loads.
Agent skills vs MCP servers vs rules files
Three ways to give a coding agent context, and one rule for picking. See what a skill, an MCP server and a rules file each cost in tokens and upkeep.
Share agent skills across repos without drift
Copy a skill into eight repos and the copies drift. Treat skills like dependencies: one shared repo, and a version each project pins and reviews.
The Fable method: skills for any model
The fable-method repo turns Claude Fable 5's habits into agent skills. What each file does, what ports to other models, and how to A/B it on a VPS.
Give your AI agent SearXNG web search
Your SearXNG instance can be the search backend for an AI agent. JSON API setup, the trust boundaries, and the prompt injection surface it opens.