workbench
claudecodexPortable workbench for codebase study, opportunities, decisions, bounded experiments, research, audits, and context preservation, connected through modular workflow recipes.
16 skills · 2 commands · 1 agent
Operating roles for the assistant you're already using: an overseer for agent work, a live QA companion, and a review closeout.
Plugin hats from marketplace kennykankush-skillpack in kennykankush/skillpack. Commands read from the repo's manifest — 12 days ago.
autoreviewStructured code review when explicitly requested, preferring OpenAI/Codex before Claude.
birdwatchLive QA companion for product and dev sweeps, the live twin of gauntlet. Use when the user drives an app or flow and wants the agent to watch alongside: tail logs, verify UI against API and DB state, capture experience notes in the user's words, track discrepancies, or act as a scribe while they tes
overseerControl-tower role for agent work. Use when the user asks the assistant to watch or monitor what other coding agents or sessions are doing, check whether an agent's work is valid, relay decisions or questions to an agent on their behalf, keep them briefed across several agents, keep a watch log whil
/hats:autoreviewRun the bundled structured closeout/code-review helper.
/hats:birdwatchLive QA companion. The user drives a flow while it verifies UI against API, DB and logs, keeping evidence-backed findings in the user's words.
/hats:overseerBe the control tower for agent work. Get ready on the project, watch the agents, check their claims, and relay the user's decisions.
Portable workbench for codebase study, opportunities, decisions, bounded experiments, research, audits, and context preservation, connected through modular workflow recipes.
16 skills · 2 commands · 1 agent
Small personal workflows that are useful enough to package but do not belong in Workbench.
3 skills · 3 commands
Opinionated video preproduction workflows for storyboard frames, product-launch motion direction, and AI-video-ready shot batches.
6 skills
Speaks a contextual one-line handover summary (with Ghostty tab number) when Claude or Codex finishes a turn or needs input.
hooks
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
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
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.