Agent skill

GitHub Repo Cards

by ob-labs in ob-labs/agentseek

Fetching GitHub repo or trending info via gh CLI and rendering beautiful SVG/PNG card images.

Apache-2.0Auto-check passed

Install GitHub Repo Cards

skills CLI
$ npx skills add ob-labs/agentseek --skill github-repo-cards -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ob-labs/agentseek github-repo-cards --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ob-labs/agentseek.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/github-repo-cards .claude/skills/github-repo-cards && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
github-repo-cards
GitHub stars
192
Token cost
~517 tokens
SKILL.md length
222 words
Files
3 (incl. scripts)
Skills in repo
4
Repo updated
First seen
Licence
Apache-2.0

At a glance

Fetching GitHub repo or trending info via gh CLI and rendering beautiful SVG/PNG card images.

  • Works in 2 steps: Repo Card — given /, produce a card… → Trending Card — fetch today's trending…
  • Asked to visualize repo stats
  • SKILL.md covers Capabilities, Workflows, Output and Requirements
  • Runs Python scripts from its folder; calls uv and gh

What it does

GitHub Repo Cards is an agent skill from ob-labs/agentseek. Fetching GitHub repo or trending info via gh CLI and rendering beautiful SVG/PNG card images. Use when asked to visualize repo stats, trending repos, or generate GitHub-style cards.

Its SKILL.md is about 520 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/gh_repo_card.py` and `scripts/gh_trending_card.py`).

It works with GitHub and Python. The repository describes itself as: AgentSeek is an application development lifecycle toolkit for AI ecosystem apps, built by OceanBase OSS Team. The licence is Apache-2.0.

When your agent uses it

  • Asked to visualize repo stats
  • Generate GitHub-style cards

Example prompts

  • “/github-repo-cards”

Requirements

  • Python 3

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Repo Card — given /, produce a card showing
  2. Trending Card — fetch today's trending repos and render a list card with

What it can do on your machine

Read from SKILL.md and the folder at commit 8abad49. 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 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • uv
    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv and gh, which can reach the network depending on how they are called.

    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

GitHub Repo Cards loads about 517 tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 222 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~517

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.

SKILL.md

The full file from ob-labs/agentseek at commit 8abad49, republished under its Apache-2.0 licence (© ob-labs). 222 words, ~517 tokens.

Download SKILL.mdSave it as .claude/skills/github-repo-cards/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
github-repo-cards
description
Fetching GitHub repo or trending info via gh CLI and rendering beautiful SVG/PNG card images. Use when asked to visualize repo stats, trending repos, or generate GitHub-style cards.

GitHub Repo Cards

Generate beautiful GitHub-style SVG card images for repositories or trending projects, then convert them to PNG.

Capabilities

  1. Repo Card — given <org>/<repo>, produce a card showing:

    • Basic info (name, description, language, license)
    • Star & commit activity sparkline
    • Top N contributors (avatars + commit counts)
    • A customisable "analysis" text block
  2. Trending Card — fetch today's trending repos and render a list card with:

    • Repo name, description, language badge
    • Star / fork counts
    • Recent commit activity sparkline (mini bar chart)

Workflows

Generate a Repo Card
uv run scripts/gh_repo_card.py <org>/<repo> [--top-n 5] [--analysis "Your analysis text here"] [--output card.svg]

The script path is relative to this skill directory: skills/github-repo-cards/scripts/gh_repo_card.py

This will:

  1. Call gh to fetch repo metadata, stargazer counts, commit activity, and top contributors.
  2. Render an SVG card with all the information.
  3. Convert the SVG to PNG via rsvg-convert (falls back to ImageMagick convert).
uv run scripts/gh_trending_card.py [--language python] [--since daily] [--limit 10] [--output trending.svg]

The script path is relative to this skill directory: scripts/gh_trending_card.py

This will:

  1. Scrape GitHub trending page (or use gh api search with recent star sorting).
  2. Render a multi-row SVG list card.
  3. Convert to PNG.

Output

SVG and PNG files are written to the current working directory (or the path given by --output). The PNG file shares the same base name.

Requirements

  • gh CLI authenticated (gh auth status)
  • rsvg-convert (librsvg) or ImageMagick convert for SVG→PNG
  • Python ≥ 3.12, run via uv run (PEP 723 inline metadata)

© ob-labs, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in skills/github-repo-cards of ob-labs/agentseek.

  • SKILL.md
  • scripts/gh_repo_card.py
  • scripts/gh_trending_card.py

Open the folder on GitHubat commit 8abad49

Compare with similar skills

GitHub Repo Cards 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.

GitHub Repo Cards compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
GitHub Repo Cards this skillob-labs/agentseek192—~517Automated safety check: PassApache-2.0
GitHub Deep Researchbytedance/deer-flow83k5 repos~1.3kAutomated safety check: PassMIT
Update V8 Versionopeninterpreter/openinterpreter69k2 repos~845Automated safety check: PassApache-2.0
Last30daysmvanhorn/last30days-skill64k—~7.8kAutomated safety check: NotesMIT
Summarise Ecosystem Resultsastral-sh/ruff50k1 repos~2.2kAutomated safety check: PassMIT
Merge Dependabot PRsonyx-dot-app/onyx32k1 repos~2.2kAutomated safety check: PassMIT

Similar skills

  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    83k GitHub starsUsed in 5 repos~1.3k tokens
    Research & ScienceAuto-check passed
  • Update V8 Version

    openinterpreter/openinterpreter

    Bumps the pinned v8 and rusty_v8 versions in Codex, validates the release-candidate path with the v8-canary check, and traces failures to upstream build changes.

    69k GitHub starsUsed in 2 repos~845 tokens
    DevOps & CloudAuto-check passed
  • Last30days

    mvanhorn/last30days-skill

    Research what people actually say about any topic in the last 30 days.

    64k GitHub stars~7.8k tokensUpdated today
    Research & ScienceAuto-check: notes
  • Official

    A skill your agent uses when a user says "summarise ecosystem results", "summarize this ty ecosystem report", "what changed in this ecosystem run?", or asks to summarise or summarize ty ecosystem…

    50k GitHub starsUsed in 1 repo~2.2k tokens
    DevelopmentAuto-check passed
  • Merge Dependabot PRs

    onyx-dot-app/onyx

    Triages and lands a batch of open Dependabot PRs in the Onyx repo, where main is gated exclusively by GitHub's merge queue: approves and enqueues green PRs, closes superseded duplicates, fixes…

    32k GitHub starsUsed in 1 repo~2.2k tokens
    DevelopmentAuto-check passed
  • Official

    Create a CUDA Python pull request from an approved personal or organization-owned fork, including the GitHub CLI GraphQL fallback for renamed organization-owned forks.

    3.4k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check passed

More from ob-labs/agentseek

  • Agentseek Lifecycle

    ob-labs/agentseek

    A skill your agent uses when helping with AgentSeek-managed projects or AgentSeek-compatible templates: create projects, diagnose lifecycle issues, run doctor/dev/info/task commands, edit lifecycle…

    192 GitHub stars~559 tokensUpdated 17 days ago
    Auto-check passed
  • Documentation Writer

    ob-labs/agentseek

    Diátaxis Documentation Expert. An agent skill from ob-labs/agentseek.

    192 GitHub stars~1.9k tokensUpdated 17 days ago
    Auto-check passed
  • Langchain Dev Guide

    ob-labs/agentseek

    LangChain / LangGraph engineering pitfalls and verified fixes.

    192 GitHub stars~1.8k tokensUpdated 17 days ago
    Auto-check passed

Works with

Questions about GitHub Repo Cards

What does GitHub Repo Cards do?

Fetching GitHub repo or trending info via gh CLI and rendering beautiful SVG/PNG card images. GitHub Repo Cards is an agent skill from ob-labs/agentseek. Fetching GitHub repo or trending info via gh CLI and rendering beautiful SVG/PNG card images.

When should I use GitHub Repo Cards?

GitHub Repo Cards fits situations like: asked to visualize repo stats; generate GitHub-style cards.

How do I install GitHub Repo Cards in Claude Code?

Run `npx skills add ob-labs/agentseek --skill github-repo-cards -a claude-code`. Or copy the skill folder (skills/github-repo-cards in ob-labs/agentseek) into .claude/skills/github-repo-cards in your project. Claude Code loads it when a task matches its description.

How do I install GitHub Repo Cards in Codex?

Run `npx skills add ob-labs/agentseek --skill github-repo-cards -a codex`. Or copy the skill folder (skills/github-repo-cards in ob-labs/agentseek) into .agents/skills/github-repo-cards in your project. Codex loads it when a task matches its description.

Can I use GitHub Repo Cards 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 ob-labs/agentseek --skill github-repo-cards -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/github-repo-cards, .gemini/skills/github-repo-cards, .github/skills/github-repo-cards and .opencode/skills/github-repo-cards in your project.

What does GitHub Repo Cards need to run?

Going by SKILL.md and its folder, GitHub Repo Cards needs Python for the scripts in its folder and the command-line tools its instructions call (uv and gh). Our summary lists: Python 3.

Does GitHub Repo Cards access the network?

SKILL.md contains no URLs. Its commands use uv and gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is GitHub Repo Cards 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 GitHub Repo Cards use?

GitHub Repo Cards is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does GitHub Repo Cards use?

About 517 tokens (SKILL.md is roughly 2.1k 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 GitHub Repo Cards?

Skills that share tags, products or a category with GitHub Repo Cards: GitHub Deep Research (bytedance/deer-flow, 83k stars), Update V8 Version (openinterpreter/openinterpreter, 69k stars), Last30days (mvanhorn/last30days-skill, 64k stars) and Summarise Ecosystem Results (astral-sh/ruff, 50k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains GitHub Repo Cards?

ob-labs (a GitHub organization) maintains it in ob-labs/agentseek, which has 192 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 21, 2026.

Source: ob-labs/agentseek on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.