Local coding-agent orchestrator — DAG of auto-approved, git-worktree-isolated sub-sessions across LLM providers (Claude/Kimi/Grok/DeepSeek/local). AGPL-3.0.
Skill Claude CodeCodex
Delegate a multi-step coding task to sidekick — a local orchestrator that decomposes the task into a DAG of subtasks, fans out auto-approved coding sub-sessions on isolated git worktrees (Claude Code on the claude branch, Kimi/Moonshot on the kimi branch — same envelope either way), runs acceptance checks, and merges…
Skill Claude CodeCodex
Deterministic UI quality audit of a web page or a whole product — WCAG 2.2 A/AA accessibility (axe-core), Core Web Vitals (LCP/CLS), browser health (console errors, failed requests, mixed content) and tap-target size — reported dimensions-first, with confirmed-vs-uncertain findings clustered into root-cause families…
Skill Claude CodeCodex
Time-to-Capability benchmark — run the SAME user goal against different products or releases and compare how hard each makes it: elapsed time, interaction count, credential steps, forced onboarding screens and documentation detours. Use when the user wants a release-to-release UX regression check ('did this goal get…
Skill Claude CodeCodex
Goal-based end-to-end UI testing that PROVES the outcome. Given a URL and a plain-language goal (e.g. 'sign up, create a project, and invite a teammate'), sidekick drives a real browser to do it and then verifies success with a DETERMINISTIC signal on the real page — the execution agent is never allowed to grade its…
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: