sdd
claudecodexSpec-driven workflow for requirements (REQ), change requests (CR), implementation specs, and three-stage reviews; conclusions live in REQ, argumentation in reviews
9 skills
Tmux utilities for sending commands and text across panes
Plugin tmux from marketplace ai-kit in fingergohappy/ai-kit. Commands read from the repo's manifest — today.
agent-crewPut outside CLI agents (codex, pi, zcode, ...) to work in a dedicated `agents` tmux session, one window each — whether that is handing one of them a job, splitting a job across several, having two solve the same problem independently, or having several review one artifact from different angles. Use
agent-tmuxrun app use tmux
lane-leadAct as the lead: you talk with the user, and the actual work goes to Claude Code workers you start as new windows in your own tmux session, one window per job. Covers taking stock before handing anything off (also after a crash or reboot cut running lanes short), launching each worker so it runs una
tmux-dispatchDispatch a task to an agent (Claude Code, Codex, ...) running in another tmux pane by writing the brief to a document under docs/tmux-channel/ and sending that pane only the document's path, stamped with your own pane id so the agent reports back into the same document. Use this whenever the user wa
tmux-replyReport back to the tmux pane that dispatched a task to you by appending a "## Report" section to the channel document the task arrived in, then sending that pane a one-line status — DONE: / BLOCKED: / QUESTION: — together with the document's path. Use this proactively — without being asked again — w
ui-test-leadLead manual UI testing that a tester agent (dsh, Claude Code, codex, ... in another tmux pane, on this machine or another one over ssh) carries out in a real browser against a test environment: every brief carries the user's standing test rules (browser only and never the database, reach pages by cl
Spec-driven workflow for requirements (REQ), change requests (CR), implementation specs, and three-stage reviews; conclusions live in REQ, argumentation in reviews
9 skills
Code review, evaluation, and fix utilities for quality assurance workflows
7 skills
Git worktree and branching utilities for rebasing and atomic commits
5 skills
Agent collaboration flow: task → dispatch → evaluate → report → review → redo
2 skills
Personal learning note generation and management skills
2 skills
AI self-reflection and learning skills for capturing lessons from mistakes
1 skill
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
8 skills · 1 MCP server
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Use Alibaba Open Code Review from local Codex.
2 skills
Claude Code skill for creating and presenting Slidev slidedecks
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.