dahlia
- 15 skills
- 0 followers
- 20 hours ago last updated
- ▌ Logtape · dahliaUse this skill when writing any code that uses LogTape for logging in JavaScript or TypeScript. Covers getting loggers, the structured message syntax, configuration, library author rules, context, lazy evaluation, testing, and common mistakes to avoid. Trigger whenever the user is adding logging to a project, debugging log output, or integrating LogTape with a framework.
- ▌ Rspress Custom Theme · dahlia bundleCustomize Rspress themes using CSS variables, Layout slots, component wrapping, or component ejection. Use when a user wants to change the look and feel of an Rspress site, override theme components, add custom navigation/sidebar/footer content, inject global providers, or modify the default Rspress theme in any way. Also use when a user mentions theme/index.tsx, Layout slots, BEM class overrides, or rspress eject.
- ▌ Rspress Best Practices · dahliaRspress best practices for config, CLI workflow, content organization, frontmatter, MDX, themes, i18n, search, static assets, deployment, and debugging. Use when writing, reviewing, or troubleshooting Rspress documentation sites.
- ▌ Rspress Description Generator · dahliaGenerate and maintain description frontmatter for Rspress documentation files (.md/.mdx). Use when a user wants to add SEO descriptions, improve search engine snippets, generate llms.txt metadata, prepare docs for AI summarization, or batch-update frontmatter across an Rspress doc site. Also use when adding new documentation pages to an Rspress project — every new doc file needs a description.
- ▌ I18N · dahliaFill in missing translations in web-next .po files, add i18n-aware UI labels to components, and ensure translation quality — consistent glossary terminology, correct punctuation/typography per language, proper formality levels, and placeholder preservation. Use when translating UI labels, reviewing translations, managing glossaries, or adding new translatable strings to components.
- ▌ Fedify · dahliaUse this skill whenever writing JavaScript or TypeScript code that uses Fedify to build an ActivityPub server, handle federation activities, implement fediverse features, or integrate Fedify with a web framework such as Hono, Express, Next.js, Nuxt, Fastify, Koa, NestJS, Astro, SvelteKit, Fresh, h3, Elysia, or Cloudflare Workers. Covers the `Federation` builder pattern, actor/inbox/outbox/collection dispatchers, inbox listeners, vocabulary objects from `@fedify/vocab`, key pair management, HTTP Signatures, Object Integrity Proofs, the `KvStore` and `MessageQueue` interfaces, database adapter packages, structured logging with LogTape, OpenTelemetry tracing, the `fedify` CLI toolchain, and common mistakes. Also apply when the user mentions ActivityPub, federation, fediverse, WebFinger, NodeInfo, FEPs, or Mastodon interoperability, even if they do not name Fedify explicitly.
- ▌ Commit · dahliaMake a commit in Git with an appropriate commit message for the currently staged changes.
- ▌ Code Review Loop · dahlia bundleFinish a rough-but-working change set by running it through two independent AI reviewers — first an iterative `codex review` loop on OpenAI's frontier model, then a final `claude -p` pass on Claude's frontier model — applying only the fixes that stay inside the original goal, escalating anything that would widen the scope, and committing with the right `Assisted-by` trailers. Use this skill whenever the user asks to "run a code review loop", "review and fix my changes", "polish this before I commit", "마무리 좀 해줘", "코드 리뷰 루프", "리뷰 받고 고쳐줘", "Codex 리뷰", "Claude 리뷰", or otherwise wants a first draft brought up to committable quality by AI review — even when they name only one of the two reviewers.
- ▌ Address Pr Review · dahliaWork through unresolved review comments on a GitHub pull request end-to-end — read each thread, fix the code where the reviewer is right, post a short reply explaining yourself where they aren't, group the fixes into well-scoped commits whose messages link to the comments they address, push, post follow-up replies naming the commit that resolved each thread (with bare commit hashes so GitHub auto-links them), resolve every triaged thread, and re-trigger Codex / Gemini if either bot reviewed the PR. Use this skill whenever the user asks to "address PR review", "handle review comments", "respond to review feedback", "apply review suggestions", "go through the review on PR
- ▌ Codex Code Review Loop · dahliaNarrow, single-reviewer workflow using codex exec --json, with self-review when the executing assistant is Codex. Use only when the user names this skill explicitly or asks for a Codex-only loop with no Claude pass. For general review-and-fix requests, use code-review-loop instead. Requires access to the target repository; external review also requires an authenticated Codex CLI.
- ▌ Fable Code Review Loop · dahliaNarrow, single-reviewer variant that drives the review loop through `claude -p` pinned to Claude Fable 5.1, with no Codex pass. Do not use for general review requests — the two-reviewer finishing workflow in `code-review-loop` supersedes this. Use only when the user names this skill explicitly, or explicitly asks for a Fable-only review loop.
- ▌ Sacho · dahliaHelp a maintainer adopt and operate Sacho, the opinionated changelog manager that keeps user-facing release notes as one small Markdown fragment per change under changes.d/ and compiles them into CHANGES.md at release time. Use this skill whenever a repository has a sacho.toml, a changes.d/ directory, or a CHANGES.md built from fragments; whenever the user wants to add Sacho to a project, write or edit a changelog entry for a change they just made, cut a release, publish release notes, or wire `sacho check` into CI or a pre-commit hook; whenever forward-porting a bugfix release across maintenance branches or resolving a changelog merge conflict; and whenever `sacho check` or the changelog merge driver reports a problem. Also use it any time the user mentions Sacho, changes.d fragments, or asks how to write a changelog entry for users instead of generating one from commit messages.
- ▌ Release · dahliaCreate and publish releases for the Optique project. Use when releasing a patch, minor, or major version. Handles Sacho release notes, the mise bump-version task, tags, and maintenance-branch merges.
- ▌ Optique · dahlia bundleUse this skill when writing any code that builds a command-line interface with Optique in TypeScript or JavaScript. Covers the combinatorial parser model, choosing @optique/core vs @optique/run, value parsers, structured messages, optional()/withDefault()/multiple(), subcommands with command() and or(), shell completion, async parsing, the integration packages, and common mistakes to avoid. Trigger whenever the user is parsing command-line arguments, building a CLI, or adding options or subcommands to a tool.
- ▌ Javascript Testing Expert · dahliaExpert-level JavaScript testing skill focused on writing high-quality tests that find bugs, serve as documentation, and prevent regressions. Advocates for property-based testing with fast-check and protects against indeterministic code in tests. Does not cover black-box e2e testing.