Loading...
Loading...
Found 209 Skills
Fully automate building and releasing a coding task.
Start a new agent session in its own `herdr` workspace and tab, send it its starting prompt and confirm it's working. Use when a handover, a new effort or a session's settle runs through `herdr`.
Ask another coding agent in a Herdr pane — on this machine or another one — and get exactly one authorized reply back, with a loop guard, depth limit 1, a fan-out cap and a record of every delegation. Use only when the user mentions Herdr, peers, or another agent, pane or machine, or when a plan you are executing delegates a task through Herdr. Do not use merely because parallel work could help. Requires HERDR_ENV=1 and Herdr's official herdr skill.
Run agentlint CLI after code changes to catch patterns for AI evaluation. Activate when finishing code modifications, before committing, or when the developer asks to lint, scan, or review code with agentlint. Covers agentlint check, agentlint list, agentlint review, agentlint init, inline suppression, and output interpretation.
Make a Spotify Wrapped-style video of the user's year with coding agents (Claude Code, Codex, OpenCode, Pi, Amp, Cursor, Grok Build, and the ones T3 Code runs) from the session history on this machine or several, with stats, their agent persona, and the lessons hidden in how often they corrected the agent, or a short format made to post (dev rage, the agent that would not listen, who signed their commits, the grind, managing a team of agents, the funniest things their agents said back). Use when the user asks for their agent wrapped, coding wrapped, AI wrapped, year in review with agents, a roast of how they use agents, their agents' group chat, or stats about how they use coding agents.