← Back to Skills Marketplace
yinwuzhe

charmia-test-0428-01

by yuangui · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
33
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install charmia-test-0428-01
Description
Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).
README (SKILL.md)

Summarize

Fast CLI to summarize URLs, local files, and YouTube links.

Quick start

summarize "https://example.com" --model google/gemini-3-flash-preview
summarize "/path/to/file.pdf" --model google/gemini-3-flash-preview
summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto

Model + keys

Set the API key for your chosen provider:

  • OpenAI: OPENAI_API_KEY
  • Anthropic: ANTHROPIC_API_KEY
  • xAI: XAI_API_KEY
  • Google: GEMINI_API_KEY (aliases: GOOGLE_GENERATIVE_AI_API_KEY, GOOGLE_API_KEY)

Default model is google/gemini-3-flash-preview if none is set.

Useful flags

  • --length short|medium|long|xl|xxl|\x3Cchars>
  • --max-output-tokens \x3Ccount>
  • --extract-only (URLs only)
  • --json (machine readable)
  • --firecrawl auto|off|always (fallback extraction)
  • --youtube auto (Apify fallback if APIFY_API_TOKEN set)

Config

Optional config file: ~/.summarize/config.json

{ "model": "openai/gpt-5.2" }

Optional services:

  • FIRECRAWL_API_KEY for blocked sites
  • APIFY_API_TOKEN for YouTube fallback
Usage Guidance
This skill is an instruction-only wrapper around a CLI named 'summarize'. Before installing or running it: 1) Verify you trust the brew tap (steipete/tap) — prefer official/homebrew/core formulas or inspect the formula/source on GitHub. 2) Be cautious about supplying API keys (OpenAI, Anthropic, xAI, Google GEMINI, FIRECRAWL, APIFY): the installed binary will use any keys present in your environment or in ~/.summarize/config.json. 3) If possible, review the brew formula or run the binary in a sandbox/container before giving it credentials or running it on sensitive machines. 4) Note the small metadata inconsistency (ownerId differs in _meta.json vs registry metadata) — likely benign but worth a quick check of the upstream project page (https://summarize.sh) and the brew formula source to confirm you’re getting the expected software.
Capability Analysis
Type: OpenClaw Skill Name: charmia-test-0428-01 Version: 1.0.1 The skill bundle provides a standard interface for the 'summarize' CLI tool, used for summarizing web content and local files. It utilizes a legitimate Homebrew tap (steipete/tap/summarize) for installation and follows standard practices for managing LLM API keys via environment variables. No malicious instructions, obfuscation, or unauthorized data exfiltration patterns were identified in SKILL.md or _meta.json.
Capability Tags
requires-sensitive-credentials
Capability Assessment
Purpose & Capability
Name/description match the instructions: the skill is an instruction-only wrapper for the 'summarize' CLI. Requiring the 'summarize' binary and providing a brew install for it is appropriate for the stated purpose.
Instruction Scope
SKILL.md instructs the agent to use the summarize CLI and lists environment variables (OPENAI_API_KEY, ANTHROPIC_API_KEY, XAI_API_KEY, GEMINI_API_KEY, FIRECRAWL_API_KEY, APIFY_API_TOKEN) and an optional config file (~/.summarize/config.json). Those are relevant to the CLI but are not declared in requires.env; the instructions do not attempt to read unrelated system files or contact unexpected endpoints, but they do rely on user-provided secrets and local config.
Install Mechanism
The install spec uses a brew formula (steipete/tap/summarize). brew installs are common, but this is a third‑party tap rather than an official/homebrew core formula. This increases risk because the binary will be installed and executed on the host; the skill bundle contains no code to audit.
Credentials
No required env vars are declared in the registry metadata, yet SKILL.md documents multiple provider API keys and optional tokens. These env vars are directly relevant to the CLI’s functionality (models/providers, firecrawl/apify fallbacks), but the discrepancy between declared requirements and runtime expectations is worth noting. If you set keys, the installed binary could use them; ensure you trust the source before supplying credentials.
Persistence & Privilege
The skill does not request always:true and is not requesting to modify other skills or system-wide settings. It mentions an optional per-user config file (~/.summarize/config.json) which is normal for a CLI.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install charmia-test-0428-01
  3. After installation, invoke the skill by name or use /charmia-test-0428-01
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Added new skill "summarize" for quickly summarizing URLs, files, and YouTube links via the summarize CLI. - Supports a variety of file types: web pages, PDFs, images, audio files, and videos. - Default model is Google Gemini 3 Flash Preview; supports other popular API providers. - Configurable via flags and an optional config file for advanced settings. - Includes fallback and extraction options for improved flexibility and reliability.
Metadata
Slug charmia-test-0428-01
Version 1.0.1
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is charmia-test-0428-01?

Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube). It is an AI Agent Skill for Claude Code / OpenClaw, with 33 downloads so far.

How do I install charmia-test-0428-01?

Run "/install charmia-test-0428-01" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is charmia-test-0428-01 free?

Yes, charmia-test-0428-01 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does charmia-test-0428-01 support?

charmia-test-0428-01 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created charmia-test-0428-01?

It is built and maintained by yuangui (@yinwuzhe); the current version is v1.0.1.

💬 Comments