ci-mockup-figure
CommandCreate space-efficient paper and proposal figures (HTML mockups, TikZ, or skia-canvas) from tool selection through LaTeX insertion
Show, check, or change the model and effort each agent role runs on (one registry)
$ npx -y skills add yzhao062/anywhere-agents --agent claude-code
description: "Show, check, or change the model and effort each agent role runs on (one registry)" argument-hint: "[show | doctor | verify | set <family> [role] <model> <effort>]"
Read and follow the skill definition. Look for it at `skills/agent-models/SKILL.md` first, then `.claude/skills/agent-models/SKILL.md`, then `.agent-config/repo/skills/agent-models/SKILL.md`.
Command arguments from the slash invocation: `$ARGUMENTS`
With no arguments, run `show` and `doctor` and report the result. `show`, `doctor`, and `verify` map to the resolver commands of the same name. `set` changes the registry and is done only in a source repository, following the skill's "Change a model or an effort" steps; it ends at the user's approval of the commit.
One config for every agent — Claude Code, Codex, and whatever comes next. Start with effective defaults. Add packs, small bundles of rules, skills, or permissions, as you need them. One AGENTS.md drives every agent in every repo on every machine.
Create space-efficient paper and proposal figures (HTML mockups, TikZ, or skia-canvas) from tool selection through LaTeX insertion
Design concise overview, mechanism, or workflow figures as editable PowerPoint objects
Detect the work type (papers, proposals, code, figures, admin) and dispatch to the right domain skill
Run prun: parallel delegation fan-out on Agy workers, or Codex or Grok when you name it (the session coordinates)
Audit a GitHub README and rewrite it with modern patterns for a scannable ten-second skim
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.