菜单
Searches anime and manga by natural-language query using the ani CLI and AniList, supporting trending, popular, top, search, info, hidden gems, and binge modes. Use when the user wants to find anime or manga, explore trending titles, or get information about a specific series.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | search-anime |
| description | Searches anime and manga by natural-language query using the ani CLI and AniList, supporting trending, popular, top, search, info, hidden gems, and binge modes. Use when the user wants to find anime or manga, explore trending titles, or get information about a specific series. |
Search anime and manga by natural-language query using the ani CLI and AniList.
ani commandinfo shows Crunchyroll, HIDIVE, and other links from AniList--manga/search-anime # default: trending digest (anime + manga)
/search-anime trending # currently trending anime
/search-anime trending --manga # currently trending manga
/search-anime popular # popular this season
/search-anime popular --season winter --year 2024
/search-anime upcoming # season preview: upcoming + current popular
/search-anime top # top-rated of all time
/search-anime all-time # most-watched of all time
/search-anime search <natural query> # smart NL search
/search-anime info <title or AniList id> # full detail card with streaming links
/search-anime digest # full weekly briefing
/search-anime gems # hidden gems: high score, lower popularity
/search-anime gems --manga # hidden gem manga
/search-anime binge # completed series worth binging (24+ eps)
natural search examples
/search-anime search action anime from 2023 with score above 85
/search-anime search something like attack on titan
/search-anime search dark psychological thriller finished
/search-anime search slice of life romance with high ratings
/search-anime search isekai comedy
/search-anime search mecha sci-fi from the 90s
Before any command, verify ani is installed:
which ani
If not found, stop and tell the user:
aniis not installed. Install it from https://github.com/pavelsimo/ani —go install github.com/pavelsimo/ani@latestor grab a release binary.
Parse the first argument:
| Argument | Mode |
|---|---|
(none) or digest | digest |
trending | trending |
popular | popular |
upcoming | preview |
top | top |
all-time | all-time |
search <query> | search |
info <name-or-id> | info |
gems | gems |
binge | binge |
--manga flag anywhere → append --type manga to all ani calls for that invocation. --lang english → append --lang english to all calls. Derive the current season from today's month: Jan–Mar = winter, Apr–Jun = spring, Jul–Sep = summer, Oct–Dec = fall.
After detecting the mode, read reference/output-modes.md for the exact ani commands, JSON parsing rules, output templates, and error handling for that mode. Read reference/reference-tables.md when mapping natural-language genres, formats, or score displays.
--json — never parse the human-readable table outputid in digest and preview modes — never show the same title twicetimeUntilAiring is in seconds; always display as "Xd Yh"mediaRecommendation can be null if the entry was deleted; skip silentlyexternalLinks only comes from ani info, not from list commands; surface a tip in list modes to run /search-anime info <title> for streaming linksGenerates changelog entries from git history following Keep a Changelog conventions and cuts versioned releases. Use when the user wants to update CHANGELOG.md with recent commits or promote [Unreleased] to a versioned release.
Creates a conventional git commit with gitmoji prefix and lowercase imperative message. Use when the user is ready to commit staged changes or wants help composing a clean, atomic commit message.
Scaffolds production-ready CLI projects from language templates, supporting Go with Cobra, Makefile, golangci-lint, goreleaser, and GitHub Pages docs; and Python with Typer, uv, ruff+mypy, PyPI OIDC trusted publishing, and GitHub Pages docs. Use when the user wants to bootstrap a new command-line tool project from scratch.
Analyzes a codebase and generates LLM-optimized documentation covering project overview, architecture, build system, testing, development patterns, deployment, and a file catalog. Use when the user wants to document a codebase or refresh existing project documentation.
Transforms documents into polished self-contained HTML by reading Markdown/text directly, converting other supported inputs with uvx markitdown, selecting from 20 purpose-built templates, and generating the output.
Turns a rough description into a structured GitHub issue with gitmoji title, problem statement, acceptance criteria, optional interview mode, and posting via gh CLI.