MiniMax-AI/mcode-stack / stacks/jiachen/skills/making-content
making-content
UnverifiedContent production in three modes: rewrite, Xiaohongshu (小红书) image post, short video. Rewrite (default): turns an AI-sounding Chinese or mixed Chinese-English draft (post, newsletter, engineering blog, commentary) into the author's restrained style: few emoji, short paragraphs, hedged claims, neutral wording, English terms split by spaces. Triggers: 按我的风格改, 去 AI 味, 润色, 改改这篇, or a vague 帮我改改 when the context is a structured draft. Also for a Xiaohongshu image post from scratch (title, cover, cards, body, hooks); read references/xhs-post.md first. Also turns a document, research, notes or an article into a 60-180 s vertical video (抖音, 小红书, 视频号, B站: real sources, voice-over, captions, cover). Triggers: 做成视频, 做个短视频, 剪个 90 秒版本, 配音, 换成我的声音, or complaints of 字太密, AI 味太重, 容易走神; read references/video-pipeline.md first.
| File | Kind | Size |
|---|---|---|
| .gitignore | other | 167 B |
| SKILL.md | skill md | 25.6 KB |
| evals/evals.json | config | 4.5 KB |
| references/layouts.md | markdown | 8.5 KB |
| references/text-density-lint.md | markdown | 4.2 KB |
| references/video-pipeline.md | markdown | 12.5 KB |
| references/voice-and-music.md | markdown | 5.5 KB |
| references/xhs-post.md | markdown | 9.0 KB |
| requirements.txt | manifest | 233 B |
| scripts/capture.py | script | 6.4 KB |
| scripts/compositor.html | other | 27.8 KB |
| scripts/fetch_assets.py | script | 4.0 KB |
| scripts/lint.py | script | 8.6 KB |
| scripts/render.py | script | 4.6 KB |
| scripts/timeline.py | script | 8.7 KB |
| scripts/tts.py | script | 5.5 KB |
| templates/cover.html | other | 2.9 KB |
| templates/script.example.json | config | 5.0 KB |
| templates/sources.example.json | config | 58 B |
scripts/fetch_assets.py
View on GitHub#!/usr/bin/env python3
"""Fetch the non-capture assets a project needs, into the project dir.
python3 fetch_assets.py fonts # fonts/fonts.css + woff2 (Inter, Source Serif 4, JetBrains Mono)
python3 fetch_assets.py logo oven-sh --repo oven-sh/bun # logos/oven-sh.png from the repo owner's GitHub avatar
python3 fetch_assets.py logo ferris --url https://rustacean.net/assets/rustacean-flat-happy.png
python3 fetch_assets.py music "Digital Lemonade" # music/Digital_Lemonade.mp3 + prints the CC-BY credit line
Chinese glyphs come from the system (Noto Sans CJK SC / PingFang SC); only Latin faces are downloaded.
"""
import argparse, hashlib, os, re, sys, urllib.parse
import requests
FONT_FAMILIES = ['Inter:wght@400;600;800', 'Source+Serif+4:wght@400;600', 'JetBrains+Mono:wght@400;700'] # the --sans/--serif/--mono faces compositor.html names
BROWSER_UA = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 Chrome/120 Safari/537.36' # Google Fonts serves woff2 only to modern UAs
AVATAR_SIZE = 256 # px; stickers render at <= 132 px, so 2x is enough
def get(url, **kw):
r = requests.get(url, timeout=30, headers={'User-Agent': BROWSER_UA}, **kw)
r.raise_for_status(); return r
def fonts():
os.makedirs('fonts', exist_ok=True); blocks = []
for fam in FONT_FAMILIES:
css = get(f'https://fonts.googleapis.com/css2?family={fam}&display=swap').text
for sub, block in re.findall(r'/\* ([\w-]+) \*/\s*(@font-face \{.*?\})', css, re.S):
if sub not in ('latin', 'latin-ext'):
continue
url = re.search(r'url\((.*?)\)', block).group(1); name = hashlib.md5(url.encode()).hexdigest()[:10] + '.woff2'
if not os.path.exists(f'fonts/{name}'):
open(f'fonts/{name}', 'wb').write(get(url).content)
blocks.append(block.replace(url, name))
open('fonts/fonts.css', 'w').write('\n'.join(blocks)); print(f'fonts/fonts.css ({len(blocks)} faces)')
def logo(name, repo=None, url=None):
os.makedirs('logos', exist_ok=True)
if repo: # github.com/<org>.png and avatars/<login> are often blocked or return a placeholder; the repo page has the real /u/<id> URL
from playwright.sync_api import sync_playwright
with sync_playwright() as p:
b = p.chromium.launch(); pg = b.new_page(); pg.goto(f'https://github.com/{repo}', wait_until='domcontentloaded', timeout=45000)
src = pg.evaluate(r"() => { const i = [...document.querySelectorAll('img')].find(i => /avatars\.githubusercontent\.com\/u\//.test(i.src)); return i && i.src; }")
b.close()
if not src:
sys.exit(f'no owner avatar found on github.com/{repo}')
url = src.split('?')[0] + f'?s={AVATAR_SIZE}&v=4'
if not url:
sys.exit('give --repo owner/repo or --url')
data = get(url).content
if len(data) < 500:
sys.exit(f'{url} returned {len(data)} bytes — probably an error page')
open(f'logos/{name}.png', 'wb').write(data); print(f'logos/{name}.png <- {url}')
def music(track):
os.makedirs('music', exist_ok=True); fn = 'music/' + track.replace(' ', '_') + '.mp3'
url = 'https://incompetech.com/music/royalty-free/mp3-royaltyfree/' + urllib.parse.quote(track) + '.mp3'
open(fn, 'wb').write(get(url).content)
print(fn); print(f'credit (put it in the post description): Music: "{track}" Kevin MacLeod (incompetech.com), CC BY 4.0')
if __name__ == '__main__':
ap = argparse.ArgumentParser(); sp = ap.add_subparsers(dest='cmd', required=True)
sp.add_parser('fonts')
lg = sp.add_parser('logo'); lg.add_argument('name'); lg.add_argument('--repo'); lg.add_argument('--url')
mu = sp.add_parser('music'); mu.add_argument('track')
a = ap.parse_args()
try:
fonts() if a.cmd == 'fonts' else logo(a.name, a.repo, a.url) if a.cmd == 'logo' else music(a.track)
except requests.RequestException as e:
sys.exit(f'download failed: {e} (a sandbox allowlist may block the host; fetch it elsewhere and drop it in place)')
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 195k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 117k | Updated | Claude CodeCodex | Unverified | Install |
| paperclip-pagepaperclipai/paperclipPublish static HTML pages and asset folders to the Paperclip S3/CloudFront page host. Use when asked to deploy, host, or share a persistent page, viewer, prototype, report, or static site without here.now. | Stars: 114k | Updated | Claude CodeCodex | Verified | Install |