mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Conduct coding agents in herdr from Claude Code: discover, start, prompt, wait in the background, answer dialogs, verify on the machine, review across harnesses, worktrees and saved machines.
Plugin herdr-conductor from marketplace herdr-conductor in yigitkonur/herdr-conductor. Commands read from the repo's manifest — 18 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
conductConduct a goal through herdr agents end to end - upfront questions, a project card, a plan, small briefs in waves, background waits, verification on the machine and a review by an agent that is not the author. Invoked as /herdr-conductor:conduct <goal>.
herdrThis skill should be used when the user mentions herdr, or asks to inspect, start, prompt, wait on, read, answer, review or clean up coding agents (claude, codex, agy and others) in herdr workspaces, tabs, panes or worktrees, locally or on a saved machine; for example "what is running in herdr", "st
setupCheck that herdr and the harnesses are ready for herdr-conductor (a doctor), and create or update the user config and this project's CONDUCTOR.md card. Invoked as /herdr-conductor:setup [doctor|config|project].
watchShow what is running in herdr across this machine and saved machines - one table per server with workspace and tab labels, agent states and completion_seq - and flag agents that are blocked, out of quota or finished; optionally repeat on a schedule. Invoked as /herdr-conductor:watch [local|<machine>
herdr-workerUse this agent to run one bounded task through one coding agent in herdr (claude, codex, agy or another harness) and get back a fixed report with receipts, without filling the main session's context with screens. Typical triggers: a task-scenario step ("have a codex in herdr fix the failing test in
command -v python3 >/dev/null 2>&1 && exec python3 -I "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/guard.py" || true
command -v python3 >/dev/null 2>&1 && exec python3 -I "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session_context.py" || { command -v herdr >/dev/null 2>&1 && echo '{"hookSpecificOutput":{"hookEventName":"Se
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.