Summarize Documents
Condense a collection of plain-text documents into a concise structured summary.
Install
$ agentstack add skill-elvinmorales-agent-librarian-summarize-docs ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
About
Summarize Documents
Purpose
Produce a concise summary that preserves decisions, action items, and open questions from synthetic documents.
When to use
- Several plain-text documents need one reviewable summary.
- A reader needs decisions and action items separated.
Inputs
- One or more plain-text documents.
- Optional maximum summary length.
Outputs
- Markdown summary with overview, decisions, action items, and open questions.
Tools
- Read-only local text access.
Side effects
- None; the skill returns text without changing source documents.
Dependencies
- UTF-8 text input.
Examples
Given three synthetic project documents, return one summary with deduplicated action items.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ElvinMorales
- Source: ElvinMorales/agent-librarian
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.