cxavireh/hotz-skills/visualize

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Build results dashboard, comparison view, or project overview. Triggers on "visualize", "可视化", "show results", "dashboard", "compare experiments", "chart my results", "project overview".

Install

npx vskill@latest install cxavireh/hotz-skills/visualize

SKILL.md

Visualize

Build a Flask + HTML dashboard for experiment results via @viz-frontend.

Instructions

When this skill is invoked with optional <argument>:

Step 1: Determine target
  • If argument is overview → project overview mode (delegates to @slides-maker Mode 3)
  • If argument is compare → comparison mode (cross-experiment)
  • If argument is an exp ID (e.g., exp01a) → that experiment
  • If no argument → read .pipeline-state.json for current_exp
  • If current_exp is null and no argument → ask user which experiment or overview
Step 2: Gather data

For single experiment:

  • Read exp/{exp_id}/results/summary.md for quantitative results
  • Read exp/{exp_id}/README.md for experiment context
  • Check if viewer/app.py already exists (update vs create)

For compare mode:

  • Read exp/summary.md for cross-experiment overview
Step 3: Delegate to @viz-frontend

For single experiment:

Build a results dashboard for experiment {exp_id}.
Results data: {summary.md content}
Experiment context: {README.md content}
Viewer directory: viewer/
If viewer/app.py exists, add/update the view for this experiment. Otherwise create from scratch.

For compare mode:

Build a cross-experiment comparison dashboard.
Summary data: {exp/summary.md content}
Viewer directory: viewer/

For overview mode:

  • Ask user what type: "slides" (default), "onboarding", or "demo-script"
  • Delegate to @slides-maker:

> mode: overview > content_type: {user's choice}

Step 4: Report

Tell user: "Dashboard ready. Run python viewer/app.py and open http://localhost:5001"

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
1
7-day trend score
8

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/cxavireh/hotz-skills/visualize/badge)](https://verified-skill.com/skills/cxavireh/hotz-skills/visualize)

Something wrong with this skill or its page? Tell us.