Agent skills that I've built to improve my toolkit
This repository also configures its own agents. See what skills tells them →
Skill Claude Code
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude CodeCodex
Review how well aligned to the repository's purpose and goals the agents are. Use this.
Skill Claude CodeCodex
List, search, download, upload, move, or share files in Dropbox via the dbxcli CLI (dbxcli), using its JSON output and command manifests.
Skill Claude CodeCodex
Look up file hashes, URLs, domains, and IP addresses on VirusTotal via the vt CLI — detection verdicts, reputation, and analysis reports — and submit files or URLs for scanning.
Skill Claude Code
Writes a specification for a code change which clarifies the goal and desired behaviours. Use before making a significant change.
Skill Claude Code
Interview the user to create a technical plan or design based on a specification. Use when creating a technical plan or design to implement the behaviours and goal described in a specification file.
Skill Claude Code
Implement a specification file into code and tests. Use after a plan has been made and the user wants to implement it.
Skill Claude Code
Verify that a specification file has been implemented correctly. Use after a specification has been implemented.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: