Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.
Install the "blog-cover-poster" agent skill from https://github.com/digoal/blog/tree/master/skills/blog-cover-poster into .claude/skills/blog-cover-poster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blog-cover-poster", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add digoal/blog --skill blog-cover-poster -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "blog-cover-poster" agent skill from https://github.com/digoal/blog/tree/master/skills/blog-cover-poster into .agents/skills/blog-cover-poster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blog-cover-poster", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add digoal/blog --skill blog-cover-poster -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "blog-cover-poster" agent skill from https://github.com/digoal/blog/tree/master/skills/blog-cover-poster into .cursor/skills/blog-cover-poster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blog-cover-poster", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add digoal/blog --skill blog-cover-poster -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "blog-cover-poster" agent skill from https://github.com/digoal/blog/tree/master/skills/blog-cover-poster into .gemini/skills/blog-cover-poster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blog-cover-poster", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
GitHub CLI
$ gh skill install digoal/blog blog-cover-poster
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add digoal/blog --skill blog-cover-poster -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "blog-cover-poster" agent skill from https://github.com/digoal/blog/tree/master/skills/blog-cover-poster into .github/skills/blog-cover-poster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blog-cover-poster", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add digoal/blog --skill blog-cover-poster -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "blog-cover-poster" agent skill from https://github.com/digoal/blog/tree/master/skills/blog-cover-poster into .opencode/skills/blog-cover-poster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blog-cover-poster", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
blog-cover-poster
GitHub stars
8.6k
Token cost
~1.4k tokens
SKILL.md length
683 words
Files
6 (incl. scripts, assets)
Skills in repo
98
Repo updated
First seen
Licence
GPL-2.0
At a glance
Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.
Works in 6 steps: Read the source. Take the file/text the… → Plan the deck (do this before writing… → Set up a scratch working dir — author… → …
The user wants cover art
SKILL.md covers Overview, Workflow, Authoring pages and Verification checklist (per…, plus 1 more section
Runs Python scripts from its folder; calls python3
What it does
Blog Cover Poster is an agent skill from digoal/blog. Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points. Renders HTML/CSS to exact-size PNGs via headless Chrome. Use whenever the user wants cover art, 讲解图/配图, carousel slides, 封面图, poster series, or "content images" from an article/文章/素材/文件, especially for blog, 公众号, 小红书, or social posts. Default output is 1080×1920 PNG named 1.png (cover), 2.png, 3.png … written to the current working directory…
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and assets (for example `agents/openai.yaml` and `scripts/render.py`).
It sits in Writing & Content, covering Slides and decks, Blog and article writing and Social media posts. The repository describes itself as: AI,Opensource,Database,Business,Finance,Minds. git clone --depth 1 https://github.com/digoal/blog. The licence is GPL-2.0.
When your agent uses it
The user wants cover art
Carousel slides
Content images from an article/文章/素材/文件
Especially for blog
Example prompts
“content images”
“/blog-cover-poster”
Requirements
Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
1Read the source. Take the file/text the user provides. Extract the title/hook and the core points. Verify facts against the source only…
2Plan the deck (do this before writing any HTML)
3Set up a scratch working dir — author intermediate HTML/CSS here, not in the source directory and not littering the project dir
4Render PNGs into the current project directory ($PWD — where the user invoked the skill), never the source file's directory
5Inspect every PNG with the Read tool. Check the checklist below. Fix the HTML in $WORK and re-render until clean.
6Clean up the scratch dir (rm -rf "$WORK"). Only the N.png files remain in the project dir — that is the deliverable. The source directory…
What it can do on your machine
Read from SKILL.md and the folder at commit ad6fcb7. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Blog Cover Poster loads about 1.4k tokens when it runs. Until then it costs about 150 tokens; SKILL.md has 683 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~150
When it runs· the whole SKILL.md, loaded when a task matches
~1.4k
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
Download SKILL.mdSave it as .claude/skills/blog-cover-poster/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
blog-cover-poster
description
Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points. Renders HTML/CSS to exact-size PNGs via headless Chrome. Use whenever the user wants cover art, 讲解图/配图, carousel slides, 封面图, poster series, or "content images" from an article/文章/素材/文件, especially for blog, 公众号, 小红书, or social posts. Default output is 1080×1920 PNG named 1.png (cover), 2.png, 3.png … written to the current working directory (the project the user is in) — never the source file's directory.
Blog Cover Poster
Overview
Generate a cover image (1.png) plus N coherent content slides (2.png, 3.png, …) from source material. Each image is an exact 1080×1920 PNG. The pipeline authors one HTML file per page using bundled CSS/templates, then renders them to PNG with headless Chrome — this gives precise control over Chinese/English typography, color semantics, and emphasis.
Workflow
Read the source. Take the file/text the user provides. Extract the title/hook and the core points. Verify facts against the source only — do not invent stats, names, or claims that aren't in the material.
Plan the deck (do this before writing any HTML):
Pick a theme: theme-dark (tech / AI / finance / dev topics) or theme-light (knowledge / tutorial / lifestyle / business explainer). Default to the topic fit; honor an explicit user request.
Decide page count automatically from the number of distinct core points: cover + one slide per point. Typical total is 4–8 images. Merge thin points; split overloaded ones. One idea per content slide.
Sketch a one-line outline: 1 cover → 2 <point> → 3 <point> …. If the user gave a fixed count, follow it.
Set up a scratch working dir — author intermediate HTML/CSS here, not in the source directory and not littering the project dir:bash
Author pages as $WORK/page-1.html (cover), $WORK/page-2.html, … using the templates as a starting point (see Authoring pages). The relative <link href="poster.css"> resolves because the CSS sits beside them.
Render PNGs into the current project directory ($PWD — where the user invoked the skill), never the source file's directory:bash
This writes 1.png, 2.png, … (exact 1080×1920) into $PWD. page-1.html always becomes the cover 1.png. If the user names a different output dir, use that instead — but default to $PWD.
Inspect every PNG with the Read tool. Check the checklist below. Fix the HTML in $WORK and re-render until clean.
Clean up the scratch dir (rm -rf "$WORK"). Only the N.png files remain in the project dir — that is the deliverable. The source directory is never touched.
Authoring pages
Start from the templates and edit — don't write markup from scratch:
Keep the same theme-* class on <body> across all pages.
Content-slide layouts
The content template ships three layout blocks — keep one per page, delete the rest:
Points (ul.points): 2–4 scannable items, best default for "reasons / steps / features".
Paragraph (.body): 2–3 short sentences for a concept that needs prose.
Big stat (.stat): one large number for a data point that deserves a full slide.
Show full SKILL.md (276 more words)Show less
Emphasis rules (semantic coloring & sizing)
Emphasis must track meaning and importance, not decoration:
.hl / .hl2 — filled color chip. At most ONE per page, on the single most important term. .hl2 (warm) for contrast/warning/payoff; .hl (cool) otherwise.
.ul — underline. Softer emphasis, for 1–2 secondary terms.
.accent — colored text, for the lead word of each list item.
.muted — de-emphasized text (subtitles, footers, labels).
Type hierarchy is pre-tuned in the CSS: cover title 132px, content heading 84px, body 50–52px. Bigger = more important. If text overflows the 1920px height, cut words or split into another slide — do not shrink below the template sizes.
Copywriting for posters
Cover title: a punchy hook, ≤ ~14 CJK chars per line, ≤ 2 lines.
Content headings: short, one idea. Content body: fragments over full paragraphs — these are read in seconds.
Number the deck in the content .index (e.g. 01 / 05) so the series reads as coherent.
Verification checklist (per image)
Size is exactly 1080×1920 (render.py enforces & prints this).
No text is clipped at edges or overflows the bottom.
Exactly one filled highlight chip per page, on the right term.
Emphasis reflects the actual key point, not random words.
Theme is consistent across all pages; contrast is readable.
Content slides read as a coherent, ordered series (indices match count).
Every claim traces to the source material.
Notes
<SKILL_DIR> is this skill's folder. render.py needs Python 3 with Pillow and a Chrome/Chromium install (it auto-detects common locations).
To regenerate a single slide, edit its page-N.html and re-run render.py — it overwrites all N.png deterministically from the current HTML set.
For custom fonts, brand colors, or logos: adjust assets/poster.css tokens (--d-accent, --l-accent, etc.) or add an <img> in the template.
Blog Cover Poster next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded…
This skill should be used when the user asks to "prepare conference presentation", "create presentation slides", "design poster", "make academic poster", "write promotion content", "create Twitter…
A skill your agent uses when the user asks to "turn this idea into posts for every platform", "write the X thread / LinkedIn post / 小红书 note", or "spec the carousel slides"; turns one idea into N…
Build a performance chart for nubjs.com — the SVG bar figures in blog posts, docs pages and social posts (a runtime augmentation against plain node, an install or dispatch comparison, a cross-tool…
三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…
Find latent bugs in a local PostgreSQL source tree (RELxxSTABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core…
Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation…
从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读，并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…
Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…
Convert a Markdown article into a natural first-person podcast script for 1 to 4 speakers and save it as a .txt file under the current project's markdown directory.
Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points. Blog Cover Poster is an agent skill from digoal/blog. Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.
When should I use Blog Cover Poster?
Blog Cover Poster fits situations like: the user wants cover art; carousel slides; content images from an article/文章/素材/文件; especially for blog.
How do I install Blog Cover Poster in Claude Code?
Run `npx skills add digoal/blog --skill blog-cover-poster -a claude-code`. Or copy the skill folder (skills/blog-cover-poster in digoal/blog) into .claude/skills/blog-cover-poster in your project. Claude Code loads it when a task matches its description.
How do I install Blog Cover Poster in Codex?
Run `npx skills add digoal/blog --skill blog-cover-poster -a codex`. Or copy the skill folder (skills/blog-cover-poster in digoal/blog) into .agents/skills/blog-cover-poster in your project. Codex loads it when a task matches its description.
Can I use Blog Cover Poster in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add digoal/blog --skill blog-cover-poster -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/blog-cover-poster, .gemini/skills/blog-cover-poster, .github/skills/blog-cover-poster and .opencode/skills/blog-cover-poster in your project.
What does Blog Cover Poster need to run?
Going by SKILL.md and its folder, Blog Cover Poster needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Blog Cover Poster access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Blog Cover Poster safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Blog Cover Poster use?
Blog Cover Poster is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Blog Cover Poster use?
About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Blog Cover Poster?
Skills that share tags, products or a category with Blog Cover Poster: Report (microsoft/data-formulator, 18k stars), Post Acceptance (Galaxy-Dawn/claude-scholar, 5.7k stars), Repurpose Linkedin (AgriciDaniel/claude-repurpose, 157 stars) and Social Creative Builder (aaron-he-zhu/aaron-marketing-skills, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Blog Cover Poster?
digoal (a GitHub user) maintains it in digoal/blog, which has 8,588 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on October 9, 2026.
Source: digoal/blog on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
