agentleFS
Sign inStart free
samulee003samulee003/agentic-ppt-skills/.agents/skills/presentation-source-intake/SKILL.md

presentation-source-intake

Skill0 starsChanged 24 days agoMITView on GitHub

Inventories presentation source folders, classifies materials, identifies authoritative versions, and records conflicts or missing access before deck work starts. Use when the source-intake gate is current for a presentation project or when a router asks for a source inventory.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use when source-intake is the current gate.

    line 8
  2. Distinctive:

    Read repo instructions and nearby handoff docs first.

    line 10
  3. Distinctive:

    Keep the source folder read-only.

    line 11
  4. Distinctive:

    Read existing deck, source, and work artifacts before creating new ones.

    line 12
  5. Very specific:

    When genoffice is available (genoffice --version or /Applications/GenOffice.app/Contents/Resources/cli/genoffice), use it to read Office …

    line 14
  6. Very specific:

    Write SOURCE-INVENTORY.md from templates/SOURCE-INVENTORY.md.

    line 22
  7. Distinctive:

    Prefer exact filenames over vague summaries.

    line 25
  8. Distinctive:

    If discoverable answers exist in the files, find them before asking the user.

    line 26
  9. Distinctive:

    Stop after the inventory is complete enough for product grilling to begin.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Build the source inventory

Use when source-intake is the current gate.

  • Read repo instructions and nearby handoff docs first.
  • Keep the source folder read-only. Create working notes only in the presentation work area.
  • Read existing deck, source, and work artifacts before creating new ones.
  • Inspect file contents with structured tools appropriate to each type: PDF, PPTX, DOCX, spreadsheet, image, script, note, and export.
    • When genoffice is available (genoffice --version or /Applications/GenOffice.app/Contents/Resources/cli/genoffice), use it to read Office and PDF files cleanly without raw unzip/cat: genoffice info <file> --json, genoffice docs read <file.docx> --full --json (or genoffice convert <file.docx> --to md), genoffice sheet read <file.xlsx> --stats --json, genoffice slides read <file.pptx> --full --json, and genoffice pdf read <file.pdf> --range 1-20 --json.
  • Classify every relevant item by role, recency, and reuse value instead of copying folders into the work area.
  • Identify version lineage: draft, revision, export, derivative, duplicate, and latest known source.
  • Mark the most authoritative source for each topic, chart, claim set, and visual asset.
  • Record reusable assets that can move forward without rework.
  • Record stale materials that should not drive current decisions.
  • Record conflicts, missing files, and access blockers explicitly.

Write SOURCE-INVENTORY.md from templates/SOURCE-INVENTORY.md.

  • Fill every section with concrete paths, dates when visible, and short evidence notes.
  • Prefer exact filenames over vague summaries.
  • If discoverable answers exist in the files, find them before asking the user.
  • Stop after the inventory is complete enough for product grilling to begin.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free