AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Magicmd

skill-didilili-magicmd-magicmd · by didilili

Use when the user wants public article URLs from WeChat, Juejin, CSDN, or technical blogs converted into Markdown packages, including batch conversion, local media, metadata, and extraction reports.

No reviews yet
0 installs
24 views
0.0% view→install

Install

$ agentstack add skill-didilili-magicmd-magicmd

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-didilili-magicmd-magicmd)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Magicmd? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

MagicMD

MagicMD converts public article links into Markdown packages. Use it as a thin tool wrapper: call the published CLI, inspect the output, and report what was created.

User-Facing Prompts

When users are not sure what to ask, suggest concise prompts like these:

Use MagicMD to convert this public article into a Markdown package, then summarize the output files and warnings.
Read urls.txt, batch convert all public article links into output/articles with MagicMD, skip existing packages, and report failures from batch-report.md.
Use MagicMD doctor to check whether this workspace can convert WeChat, Juejin, CSDN, and generic article links.
Inspect this MagicMD output directory and tell me which articles need manual review before publishing.

When to Use

Use this skill for:

  • Single public article URL to Markdown conversion.
  • Batch conversion from a URL list.
  • WeChat Official Account, Juejin, CSDN, and generic public article pages.
  • Agent workflows that need article.md, metadata, local images, videos, or extraction reports before publishing elsewhere.

Do not use it to bypass login, paywalls, private pages, CAPTCHA, rate limits, or platform access controls.

Command Choice

Prefer an installed CLI when available:

magicmd doctor
magicmd "" -o output/
magicmd batch urls.txt -o output/

If magicmd is not installed, use the PyPI package through uvx:

uvx --from magicmd magicmd doctor
uvx --from magicmd magicmd "" -o output/
uvx --from magicmd magicmd batch urls.txt -o output/

For repeated batch runs:

magicmd batch urls.txt -o output/ --skip-existing
magicmd batch urls.txt -o output/ --overwrite

Workflow

  1. Run magicmd doctor when the environment is unknown.
  2. Put multiple URLs in a plain text file, one URL per line.
  3. Convert with magicmd "" -o or magicmd batch -o .
  4. Verify each output package contains article.md, metadata.json, and extraction-report.json.
  5. Check local media directories such as images/ or videos/ when media download is enabled.
  6. For batch jobs, inspect batch-report.md and batch-report.json.
  7. If conversion is incomplete, inspect extraction-report.json, debug.html when present, and the source URL.

Reporting Back

Tell the user:

  • Output directory path.
  • Number of successful and failed conversions.
  • Important warnings from extraction-report.json or batch-report.md.
  • Whether media was downloaded locally.
  • Any limits encountered, such as 403, login requirement, video hotlink protection, or missing dynamic resources.
  • Next suggested action: publish, manually review, retry with browser support, or collect failure evidence.

Keep the original URL and output package intact so the user can compare against the source page.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.