菜单
Access Pixiv for searching illustrations, manga, and viewing rankings. Supports searching by keyword and viewing daily/weekly/monthly rankings.
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
Process raw events into distilled long-term memories using batch processing.
Create a brand-new reusable skill from a single completed task. Read the per-task SKILL_SOURCE markdown the handler wrote, distil the workflow into a generalised SKILL.md, save it at skills/<name>/SKILL.md. Use this when CraftBot has spawned a 'Create Skill' workflow task and you need to author the new skill end-to-end without user interaction.
Refine an existing CraftBot skill using evidence from one completed task that used it. Read the per-task SKILL_SOURCE markdown the handler wrote, diff it against the existing SKILL.md, apply surgical edits to skills/<target>/SKILL.md. Use this when CraftBot has spawned an 'Improve Skill' workflow task and you need to refine the skill's accuracy or token efficiency without redesigning it.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Conduct a conversational interview to explore user's job and life goals
Daily planning skill that reviews recent interactions, scans external environment, identifies tasks for today, and updates the Goals, Plan, and Status section in PROACTIVE.md.
| name | pixiv |
| description | Access Pixiv for searching illustrations, manga, and viewing rankings. Supports searching by keyword and viewing daily/weekly/monthly rankings. |
This skill allows searching and browsing Pixiv illustrations.
Before using, you must have a valid Pixiv Refresh Token.
The token is stored in config.json inside the skill directory.
To configure:
node skills/pixiv/scripts/pixiv-cli.js login <REFRESH_TOKEN>To search for illustrations by keyword:
node skills/pixiv/scripts/pixiv-cli.js search "KEYWORD" [PAGE]
Example:
node skills/pixiv/scripts/pixiv-cli.js search "miku" 1
Returns a JSON array of illustration details (title, url, tags, user, etc.).
To view rankings:
node skills/pixiv/scripts/pixiv-cli.js ranking [MODE] [PAGE]
Modes: day, week, month, day_male, day_female, week_original, week_rookie, day_ai.
Default is day.
Example:
node skills/pixiv/scripts/pixiv-cli.js ranking day
To view a user's profile details:
node skills/pixiv/scripts/pixiv-cli.js user <USER_ID>
Example:
node skills/pixiv/scripts/pixiv-cli.js user 11
To view the profile of the currently logged-in account (based on Refresh Token):
node skills/pixiv/scripts/pixiv-cli.js me
To list users that the logged-in account follows:
node skills/pixiv/scripts/pixiv-cli.js following [PAGE]
To view latest illustrations from followed users:
node skills/pixiv/scripts/pixiv-cli.js feed [RESTRICT] [PAGE]
RESTRICT can be all, public, or private. Default is all.
To download an illustration (single image, manga/multiple, or ugoira zip):
node scripts/pixiv-cli.js download <ILLUST_ID>
Files are saved to downloads/<ILLUST_ID>/.
Returns JSON containing the list of downloaded files.
To publish a new illustration directly to Pixiv using the AppAPI v2 (pure code, no browser needed):
node scripts/pixiv-cli.js post <FILEPATH> "<TITLE>" "[TAGS_COMMA_SEPARATED]" [VISIBILITY]
VISIBILITY: public (default), login_only, mypixiv, or private.illust_ai_type: 2) is applied by default.Example:
node scripts/pixiv-cli.js post "./output.png" "My New Art" "Original, Girl, AI" private
If the user asks how to get a token:
gppt (Get Pixiv Token).refresh_token in Local Storage or Cookies (though OAuth refresh token is cleaner).