kellykampen

36 mods across 1 repository, 2 stars between them.

antigravity-cli

25

kellykampen/agent-skills

Skill Claude CodeCodex

Drive Google's Antigravity CLI (the agy command — a Gemini/Antigravity terminal coding agent, successor to Gemini CLI) from the shell to delegate coding, review, and bulk work to a DIFFERENT model harness than the one you're running in. Use this whenever you want to hand a task to agy, run a cheaper/faster model for…

2 1mo ago B 219 tokens original MIT

social-capture

26

kellykampen/agent-skills

Skill Claude CodeCodex

Capture social media content (YouTube transcripts, X threads) and save to Obsidian. Use this skill when a URL is posted in the Social Telegram topic (530).

2 1mo ago A 39 tokens original MIT

check-model-usage

27

kellykampen/agent-skills

Skill Claude CodeCodex

Checks quota/usage and session + weekly pacing across AI coding harnesses in one command -- Claude Code, Codex CLI/OpenAI (including GPT-5.6 where CodexBar exposes it), Antigravity (agy), GLM/Z.ai, Kimi/Moonshot, plus any CodexBar-visible OpenRouter/xAI providers -- using only the CodexBar CLI (no TUI probes, no…

2 1mo ago A 174 tokens original MIT

code-structure

28

kellykampen/agent-skills

Skill Claude CodeCodex

Use when multiple workflows duplicate the same operational logic, when deciding what belongs in actions vs shared services, or when refactoring repeated operational blocks across domain flows. Use when adding new features that share mechanics with existing ones.

2 1mo ago A 47 tokens original MIT

kellykampen/agent-skills

Skill Claude CodeCodex

Records visual proof while testing UI behavior — screen recording with structured test/assertion annotations — then posts the video and a results summary to the PR and tracker issue. Use whenever a UI change needs verifiable evidence that it works, instead of prose claims.

2 1mo ago A 55 tokens original MIT

issue-breakdown

30

kellykampen/agent-skills

Skill Claude CodeCodex

Break a feature or initiative into a Linear epic (project) plus small, review-ready issues that meet a strict quality bar: every issue is a user story ('as a role, I want an action, so a result') with explicit acceptance criteria, a Fibonacci estimate of 3 points or less (anything larger is split), a parent…

2 1mo ago A 182 tokens original MIT

model-classifier

31

kellykampen/agent-skills

Skill Claude CodeCodex

Classify any task description into the single best underlying AI model to run it on, scored on cost, intelligence, and taste — across a roster of current frontier and budget models (Claude Opus, Sonnet, Haiku, and Fable; GPT/Codex including GPT-5.6 Sol/Terra/Luna; Grok; Gemini Pro and Flash; Kimi; GLM). Returns a…

2 1mo ago A 214 tokens original MIT

kellykampen/agent-skills

Skill Claude CodeCodex

Use this to create a short animated explainer video or a README/social GIF for a skill, feature, product, workflow, or process — one render produces both an MP4 (with a real royalty-free soundtrack sourced live from Pixabay Music) and a matching GIF, in a shared dark editorial-diagram visual system (numbered scenes…

2 1mo ago A 226 tokens original MIT

skill-maker

33

kellykampen/agent-skills

Skill Claude CodeCodex

Toolkit for authoring and iterating on Claude Code skills end to end. Create a new skill, edit or improve an existing skill, run skill evals, benchmark skill performance with baseline comparison and variance analysis, and optimize a skill's description for reliable triggering. Use whenever the user wants to create a…

2 1mo ago A 131 tokens copy · 86% MIT

analyzer

34

kellykampen/agent-skills

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

2 1mo ago A 0 tokens copy · 100% MIT

grader

36

kellykampen/agent-skills

Agent

Evaluate expectations against an execution transcript and outputs.

2 1mo ago A 0 tokens copy · 100% MIT