agentleFS
Sign inStart free
rm2thaddeusrm2thaddeus/Aitor_Skills/pixel-detective-exports/SKILL.md

pixel-detective-exports

Skill4 starsChanged 10 months agoMITView on GitHub

Export Pixel Detective UMAP projections with HDBSCAN and manage Qdrant collections via the ingestion API. Use when the user asks for latent space exports, UMAP clustering assets, or collection operations (list/create/select/delete/merge).

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the start skill to bring up services:

    line 52

≈ “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

Pixel Detective Exports

Generate standalone exports (no UI) and manage collections for Pixel Detective.

Requirements

  • Ingestion API running on http://localhost:8002
  • Qdrant running (Docker)
  • GPU UMAP service on http://localhost:8003 for HDBSCAN clustering
  • Optional (for visuals): matplotlib
  • Optional (for PDF output): weasyprint (preferred) or playwright

Quickstart

  • UMAP + HDBSCAN JSON/CSV/SVG: python skills/pixel-detective-exports/scripts/export_umap_hdbscan.py --collection <name>
  • Cluster report PDF/HTML (all collections): python skills/pixel-detective-exports/scripts/export_umap_pdf.py --sample-size 500

Exports

UMAP + HDBSCAN export (standalone)

  • Script: python skills/pixel-detective-exports/scripts/export_umap_hdbscan.py
  • Output default: exports/pixel-detective/umap/umap_hdbscan_<collection>.json|csv|svg
  • Example:
    • python skills/pixel-detective-exports/scripts/export_umap_hdbscan.py --collection my_collection --sample-size 2000
    • Color controls: --color-map tab20 --point-size 18 --outlier-size 12 --outlier-color #94a3b8

UMAP PDF report (all collections)

  • Script: python skills/pixel-detective-exports/scripts/export_umap_pdf.py
  • Output default: exports/pixel-detective/umap/umap_cluster_report.pdf
  • Example:
    • python skills/pixel-detective-exports/scripts/export_umap_pdf.py --sample-size 500 --title "Pixel Detective UMAP Clusters"

Collection management

Manage collections via API (Qdrant in Docker)

  • Script: python skills/pixel-detective-exports/scripts/manage_collections.py
  • Examples:
    • List: python skills/pixel-detective-exports/scripts/manage_collections.py --action list
    • Info: python skills/pixel-detective-exports/scripts/manage_collections.py --action info --collection my_collection
    • Create: python skills/pixel-detective-exports/scripts/manage_collections.py --action create --collection my_collection --vector-size 512 --distance Cosine
    • Select: python skills/pixel-detective-exports/scripts/manage_collections.py --action select --collection my_collection
    • Delete: python skills/pixel-detective-exports/scripts/manage_collections.py --action delete --collection my_collection
    • Merge: python skills/pixel-detective-exports/scripts/manage_collections.py --action merge --dest merged_collection --sources a,b,c
    • Qdrant fallback listing: python skills/pixel-detective-exports/scripts/manage_collections.py --action list --qdrant http://localhost:6333

Notes

  • HDBSCAN clustering is performed by the GPU UMAP service; the ingestion service does not offer HDBSCAN.
  • Collection operations go through the ingestion API, which talks to Qdrant in Docker.
  • Use the start skill to bring up services:
    • powershell -ExecutionPolicy Bypass -File skills\\start-pixel-detective\\scripts\\start_pixel_detective.ps1 -Mode backend -UseGpuUmap

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