title-card-image
This Claude Code skill generates static PNG title or ending cards with centered text using Python's Pillow library. Use it to create simple cover images with a headline and optional subtitle on a solid background, with built-in support for Chinese, Japanese, and Korean characters through intelligent font fallback. The output is deterministic and requires no network calls, making it ideal for video production pipelines that need quick, consistent text-based graphics.
git clone --depth 1 https://github.com/opensquilla/opensquilla /tmp/title-card-image && cp -r /tmp/title-card-image/src/opensquilla/skills/bundled/title-card-image ~/.claude/skills/title-card-imageSKILL.md
# title-card-image
Renders a centered-text PNG suitable for a cover / ending card before
animating into a clip with `video-still-animator`.
## Inputs (`with:`)
| key | required | default | notes |
|---|---|---|---|
| `text` | yes | — | Headline text. Auto-wraps at ~10 chars per line for CJK. |
| `output` | yes | — | Output `.png` path. |
| `subtitle` | no | `""` | Smaller line beneath the headline. |
| `background` | no | `#101018` | Hex color `#RRGGBB`. |
| `text_color` | no | `#ffffff` | Headline color. |
| `font_size` | no | `96` | Headline font size in pixels. |
| `subtitle_size` | no | `36` | Subtitle font size in pixels. |
| `width` | no | `720` | Output width in pixels. Match the merge pipeline. |
| `height` | no | `1280` | Output height. 720x1280 = 9:16. |
## Output
Prints the absolute path of the written PNG on stdout. The PNG is RGB
(no alpha), JPEG-quality-equivalent file ~30-80 KB depending on text
length.
## Font fallback
Tries `--font` if explicit, else walks a CJK-aware list of platform
defaults (Microsoft YaHei / SimHei on Windows, PingFang on macOS, Noto
CJK / WenQuanYi on Linux). If nothing loads, falls back to Pillow's
bundled bitmap font — CJK characters render as squares ("tofu") in that
worst-case but the program never crashes.
## Limits
- No alpha / transparency.
- No rich text styling (italic / drop-shadow / gradient). For richer
cards, generate a real image via `nano-banana-pro` instead.
- Headline wrap is character-count-based for CJK and whitespace-based
for ASCII; mixed strings break at the CJK character count.Submit audio or video for multilingual dubbing, poll status, and download dubbed audio. Use when the user asks for dubbing, 多语言配音, 视频翻译配音, 译制片, or wants a source clip dubbed into another language.
Generate a structured short-video shooting script from a topic. Emits a strict, machine-parseable shot list (3 shots by default) with image prompt + video prompt + voiceover + on-screen text per shot. Trigger when the user asks for a video script, 分镜, 短视频文案, AI视频, 短剧脚本, or wants visual prompts ready for image/video generation.
Use when the user asks to schedule recurring tasks, one-off reminders, timers, or cron-style jobs through the OpenSquilla cron tool.
Multi-round research with explicit methodology, evidence tracking, and citation-tagged synthesis. Trigger on 'deep dive', 'research report', 'literature review', 'investigate X across sources', 'multi-round investigation'. Distinct from the `summarize` skill, which is a single-pass condensation; this skill maintains a state file across iterations, tracks coverage, and produces a long-form report with per-claim citations. Three execution stages: plan (scope into sub-questions), iterate (record evidence per round), compile (synthesize report). The skill itself does not fetch the web — it tells the host agent which fetches to perform via OpenSquilla's existing web tools, and records what comes back.
Read, edit, or create Microsoft Word `.docx` files. Trigger this skill whenever the user mentions a Word document, .docx file, contract, report, brief, memo, or asks to extract text, modify an existing doc, generate one from a brief, or audit tracked changes. Three execution paths: text-and-structure extraction, in-place edit-by-run (preserves styles), and create-from-scratch with python-docx. Falls back to OOXML unzip-and-patch for layout work python-docx cannot reach.
Capture the current git diff (staged, working-tree, or staged file list) as text. Direct shell call for workflows that need repository diffs without an LLM agent loop.
GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.
Query the per-turn DecisionEntry log for skill co-occurrence patterns, meta-skill usage stats, and the router fixture corpus. Returns a JSON summary suitable for downstream LLM consumption. Used by meta-skill-creator's harvest step but also useful standalone for 'which skills did I use most this week?'