ryoppippi

Lints Agent Skills against the Agent Skills specification and host authoring conventions. Use when writing, reviewing, or fixing SKILL.md files or their referenced documents.

Formats source files. Use when applying formatter output.

Creates commits. Use when committing changes.

Runs tests. Use when verifying changes.

Deploys the application.

Contains 201 lines. Use when testing the rejected boundary.

Contains exactly 200 lines. Use when testing the accepted boundary.

Has a misspelled frontmatter field. Use when reviewing frontmatter.

Gets a Codex second opinion or delegates bulky work to a Codex subagent. Use before a significant approach is settled, or instead of reading pages and long output here.

Run a code review using Codex or a native subagent. Use when the user wants a code review of uncommitted changes, a specific commit, or changes against a base branch.

Fetches and searches web content with ax, tgrab, grok, codex, and exa. Use for text from a URL, web/tweet/semantic search, or social/video content.

Creates atomic Conventional Commits. Use when committing code changes, splitting hunks into revertable units, or writing commit messages.

Resolves missing CLI tools. Use when a command is unavailable, a shell reports command not found, or a tool must be run without installing it globally.

Write idiomatic, functional Nushell — the default language for shell scripts here. Use when writing or reviewing any new script, .nu files, `shell: nu {0}` CI steps, or when porting bash/POSIX shell to Nushell.

Guides authoring agent-facing instructions following Anthropic's SKILL.md best practices. Use when adding or editing skills under `agents/skills/`, rules in `claude/rules/`, `CLAUDE.md`, or `agents/shared/` fragments — frontmatter, references, and routing…

Audits all local skills in this repo for skill-creator and Anthropic best-practice compliance. Use to review the whole skill collection — checking descriptions, SKILL.md length, cross-skill duplication, and documentation references — not to author a single…

Runs the full PR lifecycle. Use when creating a branch, committing, pushing, opening a PR, requesting AI review, and driving CI and review to completion.

Guides ccusage monorepo development. Use when editing packages, docs, shared configuration, bundled CLI packaging, dependencies, exports, or validation commands.

Guides repo-local skill creation and updates. Use when adding or editing .agents/skills, SKILL.md frontmatter, references, scripts, or skill routing.

Guides ccusage Rust and Vitest tests. Use when adding or fixing cargo tests, CLI snapshots, Claude model pricing, LiteLLM compatibility, Vitest tests, or fixture-backed tests.

Guides ccusage TypeScript and JavaScript work. Use before reading or editing .ts, .tsx, .js, or .jsx files, including package launchers, Vitest tests, Bun scripts, schemas, mocks, and typed fixtures.

Guides t-wada Red-Green-Refactor TDD. Use when implementing features, fixing bugs, or refactoring logic with strict test-first development.

Guides ccusage agent source formats. Use when checking agent log locations, raw record structure, token mappings, model names, precomputed costs, or source-specific CLI behavior.

Creates atomic Conventional Commits. Use when committing code changes, splitting hunks into revertable units, or writing detailed commit messages.

Guides content changes in the ryoppippi.com repository, including blog Markdown, post-local Svelte or Solid islands, Tweet embeds, and curated OSS metadata.

Finds and maintains verified external articles, podcasts, and YouTube appearances for ryoppippi.com. Use when auditing new contributions or refreshing the Blog and Media listings.

Fetch event info from a URL using agent-browser and add/update the talk README.md

Scaffold a new talk directory with README.md and optionally package.json for Slidev