Shieldcn Badges

shadcn-styled README badges, charts, and headers from the hosted shieldcn.dev service

Tested · Works

Test report

Verdict
Tested · Works
Score
8.8/10
Tested
Jul 21, 2026
Environment
Claude Code 2.x (agent harness)

This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (SKILL.md unreadable at packages/web/app/.well-known/agent-skills/shieldcn-badges/SKILL.md). The test below is what we measured on Jul 21, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Fetched skills/shieldcn-badges/SKILL.md raw; frontmatter has name+description and parses. Body references shieldcn.dev endpoints (not local files); I curled 5 of them (npm/next, npm/dm/next, github stars/license/ci for vercel/next.js) and all returned HTTP 200 image/svg+xml with real resolved data (next v16.2.12, 201.3m/month downloads, MIT license, CI passing) plus correct link targets in the .json responses. No security smells: no curl|sh, base64 blobs, secret exfil, or injection text. Install tested in a temp HOME (export HOME=$(mktemp -d)); SKILL.md landed at ~/.claude/skills/shieldcn-badges/SKILL.md cleanly. OUTPUT test: task = badge row for vercel/next.js. Baseline used flat img.shields.io badges with no links and no centering; skill artifact used shieldcn.dev variant=secondary SVGs, each wrapped in an <a> with the correct auto-resolved destination (license -> actual LICENSE file, CI -> actual actions run), centered via <p align=center> with human alt text. Concrete observed difference: shadcn rounded-surface SVG vs flat Shields.io, and accurate link targets pulled from the service rather than hand-guessed.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 7/10
  • Docs & honesty 5/5

What Shieldcn Badges does

A URL reference that teaches the agent to build README badges, badge groups, download charts, header banners, and contributor/sponsor images using the hosted shieldcn.dev service, which renders shadcn/ui-styled SVG/PNG badges from live npm, GitHub, PyPI, and other provider data. Triggers when a user asks to add or replace README badges (npm version, GitHub stars, CI status, license), add a README header/banner or download chart, or make a project README look better. The service resolves real values and correct link targets; no local scripts or API keys are required.

How to install Shieldcn Badges

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Shieldcn Badges

  • /shieldcn-badges shadcn-styled README badges, charts, and headers from the hosted shieldcn.dev service

It also activates on plain-language prompts like these:

  • Add npm and GitHub stars badges to my README
  • Build a README header banner in shadcn style
  • Create a sponsors grid for my project README

Frequently asked questions

Is the Shieldcn Badges skill free?
Yes. The skill itself is free from jal-co/shieldcn. SkillProof publishes the install command and an independent test verdict at no cost.
Does Shieldcn Badges work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched skills/shieldcn-badges/SKILL.md raw; frontmatter has name+description and parses. Body references shieldcn.dev endpoints (not local files); I curled 5 of them (npm/next, npm/dm/next, github stars/license/ci for vercel/next.js) and all returned HTTP 200 image/svg+xml with real resolved data (next v16.2.12, 201.3m/month downloads, MIT license, CI passing) plus correct link targets in the .json responses. No security smells: no curl|sh, base64 blobs, secret exfil, or injection text. Install tested in a temp HOME (export HOME=$(mktemp -d)); SKILL.md landed at ~/.claude/skills/shieldcn-badges/SKILL.md cleanly. OUTPUT test: task = badge row for vercel/next.js. Baseline used flat img.shields.io badges with no links and no centering; skill artifact used shieldcn.dev variant=secondary SVGs, each wrapped in an <a> with the correct auto-resolved destination (license -> actual LICENSE file, CI -> actual actions run), centered via <p align=center> with human alt text. Concrete observed difference: shadcn rounded-surface SVG vs flat Shields.io, and accurate link targets pulled from the service rather than hand-guessed.
What is the Shieldcn Badges SkillProof Score?
8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Shieldcn Badges?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Shieldcn Badges with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.