← Back to Skills Marketplace
ivangdavila

Summarizer

by Iván · GitHub ↗ · v1.0.2 · MIT-0
linuxdarwinwin32 ⚠ suspicious
7705
Downloads
5
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install summarizer
Description
Summarizes any source without losing the claim: documents, meetings, papers, threads, transcripts, data, and code changes. Use when asked to summarize, condense, shorten, recap, distill, or write a TLDR, abstract, or executive summary; when a source is too long to read or must hit a word count; when summarizing a call, interview, Slack channel, pull request, contract, earnings report, podcast, or a stack of sources on one topic; when a summary dropped something important, invented a detail, turned a hedge into a fact, or reads like the headings; and when the same material must be re-cut for another audience, length, or channel. Covers compression ratios, chunking, faithfulness and omission audits. Not for recurring external feeds (`digest`), decision documents whose point is the recommendation (`brief`), cross-source insight generation rather than compression (`synthesize`), or pulling text or a transcript out of a file or video first (`extract-pdf-text`, `youtube-video-transcript`).
Usage Guidance
Install only if you want a stateful local summarizer that can remember sources, deadlines, templates, audience preferences, contacts, and project context. For confidential transcripts, contracts, reports, or personal data, prefer disabling storage where possible and reviewing proposed writes to shared contacts or project files.
Capability Assessment
⚠ Credentials
Although paths are limited to declared local Clawic data folders and there is no network transfer, the skill can read and modify shared contacts and project files containing personal or business context.
✓ Install Mechanism
The artifact is Markdown/JSON only, with no executable files, dependency installation, shell commands, remote payload execution, or background service setup observed.
⚠ Instruction Scope
The skill directs automatic reads from persistent memory and dynamically indexed local boxes, and says no permission is needed before writes; this is broader than a simple summarize-and-return workflow.
⚠ Persistence & Privilege
Default storage is index-only rather than none, and the skill records source metadata, corrections, templates, deadlines, audience profiles, contact rows, and project notes without per-action user approval.
ℹ Purpose & Capability
The core summarization instructions are coherent and purpose-aligned, including fidelity checks, length control, genre-specific summaries, and recurring-summary support for previously handled streams.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install summarizer
  3. After installation, invoke the skill by name or use /summarizer
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
Clearer disclosure of what is stored and where
v1.0.1
Full coverage pass: deeper guides, situation-named files, and per-user configuration
v1.0.0
Initial release
Metadata
Slug summarizer
Version 1.0.2
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 3
Frequently Asked Questions

What is Summarizer?

Summarizes any source without losing the claim: documents, meetings, papers, threads, transcripts, data, and code changes. Use when asked to summarize, condense, shorten, recap, distill, or write a TLDR, abstract, or executive summary; when a source is too long to read or must hit a word count; when summarizing a call, interview, Slack channel, pull request, contract, earnings report, podcast, or a stack of sources on one topic; when a summary dropped something important, invented a detail, turned a hedge into a fact, or reads like the headings; and when the same material must be re-cut for another audience, length, or channel. Covers compression ratios, chunking, faithfulness and omission audits. Not for recurring external feeds (`digest`), decision documents whose point is the recommendation (`brief`), cross-source insight generation rather than compression (`synthesize`), or pulling text or a transcript out of a file or video first (`extract-pdf-text`, `youtube-video-transcript`). It is an AI Agent Skill for Claude Code / OpenClaw, with 7705 downloads so far.

How do I install Summarizer?

Run "/install summarizer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Summarizer free?

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

Which platforms does Summarizer support?

Summarizer is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).

Who created Summarizer?

It is built and maintained by Iván (@ivangdavila); the current version is v1.0.2.

💬 Comments