agentleFS
terravicterravic/pde-agent-plugin/skills/pkde-dashboard/SKILL.md

pkde-dashboard

Skill0 starsChanged 14 days agoApache-2.0View on GitHub

Builds and renders the single-pane interactive PkDE Scientific Dashboard combining the multi-agent lineage graph, validation scorecard, and inter-agent message stream with PkDE's 14 interactive scientific viewers (3Dmol.js structures/docking, Plotly ADMET radar, pLDDT/PAE, gnomAD, GTEx, and Hypex ELO tournaments).

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Use this skill whenever you need to build, update, or serve the unified Multi-Agent + PkDE Interactive Scientific Dashboard …

    line 10

≈ “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

PkDE Unified Mission Control & Interactive Scientific Dashboard (pkde-dashboard)

Use this skill whenever you need to build, update, or serve the unified Multi-Agent + PkDE Interactive Scientific Dashboard (dashboard.html) or start the non-blocking background HTTP/SSE server (0.0.0.0:8765).

What the Dashboard Renders

  1. Pane 1 -- Multi-Agent Operations (Split & Agents Views):
    • Interactive SVG Agent Lineage Forest: Hierarchical layout (NODE_W=180, NODE_H=76) with vertical/horizontal orientation transpose (t), zoom/pan, fit-to-screen (f), bezier state edges, and pulse animations on active agents.
    • Agent & Work-Order Inspector Drawer: Clicking any agent node displays its Work Order metadata (WO-NNN-rM, stage, cycle, attempt counter), Injected Skills pills (from templates/<role>/agent.yaml), Recent Agent Communications, and the 10-Check Mechanical Validation Matrix (deliverables_exist, report_headings, paths_resolve, provenance_valid, analysis_citations, relay_coverage, version_policy, findings_integrity, source_tags_resolve, unrecognized_json).
    • Resource Leases & Inter-Agent Event Stream: Live tracker for .pkde/control/leases/*.json (af3, hypex-supervisor) and filterable .pkde/control/events.ndjson message log.
  2. Pane 2 -- PkDE Scientific Output & Embedded Interactive Viewers (Split & Discovery Views):
    • Overview, Session Prompt Charter, Stage Gates & Mandatory Relays: Active Session Prompt Charter (.pkde/program.yaml), Stage 0-4 Triage Scorecard, Liability Tracker table, and Mandatory Relays audit matrix.
    • Specialist Findings & Dossier Reader (Layer 1): Discipline-grouped Markdown/KaTeX reports with interactive {source: ...} verification badges and **Relay: ...** callouts.
    • Interactive Scientific Viewers Studio (Layer 0 + Analysis):
      • 3Dmol.js 3D Structure (.cif/.pdb colored by AlphaFold pLDDT bands), Pocket Druggability (.pockets.json), 3D Molecule SDF (.3d.sdf), and Docking Poses (.receptor.pdbqt + .poses.pdbqt).
      • Plotly.js 5-Axis ADMET Radar (.predict.json), pLDDT Confidence Line Plot (.afdb.json), 2D PAE Heatmap (.pae.json), gnomAD Constraint Gauges (.gnomad-constraint.json), and GTEx Tissue Expression Bars (.tissue.json).
      • BRICS Fragment & SAR Studio (.brics.json), Docking Pose Score Comparison (.docking_result.json), Contact Map (.contacts.json), Hypothesis ELO Tournament Studio (.tournament.json / .hypex.json), and the 3-File Provenance Inspector (Layer 0 + .meta.json + .analysis.json).
  3. Live Telemetry Console (#telemetry-drawer + 4th Telemetry Full-Screen View):
    • Persistent Collapsible Bottom Console (#telemetry-drawer): Anchored across Split, Agents, and Discovery views with Ticker (38px), Console (205px), and Full View toggles, category filter pills, text search, and hover/scroll auto-pause.
    • 4th Full-Screen Telemetry View (#telemetry-view): Dedicated two-column Mission Telemetry Terminal + Live Active Agents & Recent Discovery Additions status board.
    • One-Click Deep Navigation: Clicking any telemetry one-liner automatically opens the corresponding pane and selects the exact Agent node, Layer 1 Finding, Layer 0 Scientific Studio viewer, or Mandatory Relay table.
    • Non-Blocking Differential DOM Updates: Per-section signatures and requestAnimationFrame coalescing ensure active 3Dmol.js WebGL cameras, Plotly.js charts, Findings reader scroll positions, and SVG pan/zoom states never reset while live telemetry streams in.

Usage

1. Start Non-Blocking Background Server from Prompt (0.0.0.0:8765)

./bin/pkde dashboard start --prompt "<user prompt>" --host 0.0.0.0 --port 8765 --json
./bin/pkde dashboard status --json
./bin/pkde dashboard stop --json

2. Build Self-Contained Standalone Snapshot (dashboard.html)

python3 skills/pkde-dashboard/scripts/render_dashboard.py
# Or directly via the pkde CLI:
./bin/pkde dashboard build --standalone --json

3. Serve Foreground Auto-Refreshing Dashboard (SSE /api/stream)

./bin/pkde dashboard serve --host 0.0.0.0 --port 8765

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.