Skip to content

Source Intake Scanner

Scans configured project sources and proposes evidence-backed backlog tasks for review

Repository
agno-agi/agno
Stars
43,013
Licence
Apache-2.0
Files
1 file

What it does

This skill teaches an AI agent to read the document sources linked to a company product, look for real actionable issues in them, and propose backlog tasks backed by specific evidence links and content hashes. It requires every task to belong to a project, avoids duplicate proposals, and never copies whole documents into task briefs. The agent only proposes work; it never accepts or completes tasks, and a human authorization check gates any further action.

Great for

  • Teams running Agno's company/product workflow who want routine scans of their sources turned into reviewable backlog items
  • Product or operations leads who want evidence-linked task suggestions rather than free-form summaries
  • Developers building automated intake routines that need deduplication and traceable evidence

Skip it if

  • Individuals looking for a general-purpose document summarizer: the skill depends on Agno's Product, Source, Project and Task tools and is not useful without them
  • Unattended use with broad permissions: the skill itself notes that proposals depend on a server-side human authorization check, so misconfigured authorization could let suggested executors act on work
  • Situations needing the agent to accept or finish work automatically: the skill explicitly forbids this

Try asking

  • “Scan our configured product sources and propose backlog tasks for any new issues you find, with evidence links”
  • “Check the design-docs source for unresolved items and propose tasks under the appropriate project”
  • “Run a quiet intake check on this product; only propose work if the evidence is new”
Step-by-step guide: how to use Source Intake ScannerInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.

    intake.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip intake.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip intake.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Configure Sources and Projects in Agno before running so the agent can reuse existing projects instead of creating new ones
  • Review Backlog proposals manually; the skill keeps them there until a human accepts them
  • Use the pattern and path arguments of the source index to narrow scans and control cost on large sources

What's inside

  • SKILL.md

Redistributed unmodified from agno-agi/agno under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.