Skip to content
cccskills
FreePublished on GitHubEnglish overview

understand-dashboard

Launch the Understand Anything web dashboard to explore an existing codebase knowledge graph, a map of its structure and relationships. Open the current project or a specified directory and receive the local access URL.

OriginalShow the original description

Launch the interactive web dashboard to visualize a codebase's knowledge graph

AI rating90/ 100See how to install

Good for

  • Explore an analyzed codebase visually
  • Open the current project's dashboard
  • View graph data from another project directory

Overview

What it does

Display a codebase knowledge graph created by Understand Anything in an interactive web dashboard. A knowledge graph is data that maps the structure of code and the relationships within it. Launch the dashboard for your current working directory or a specified project. You receive a URL containing an access token and the location of the data being displayed.

When it helps

Use it to understand a codebase while exploring its analysis results in a browser. You can also open an analyzed project stored elsewhere. The dashboard runs in the background, so you can continue working after it starts.

Example requests

  • “Show the current project with /understand-dashboard.”
  • “Open the specified project with /understand-dashboard /path/to/project.”

Notes

Run /understand first to create knowledge-graph.json. Data is read from .understand-anything/ when that directory exists; otherwise, it uses .ua/. Launching requires Node and npx. If the distributed viewer cannot be retrieved, pnpm is used to install dependencies and build the necessary packages. The ?token= portion of the URL is required to access the data.

This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.

Objective evaluation

AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.

Clear instructionsIs it clear when to use it and what it does?
AGoodIt explicitly describes displaying the current or specified project’s knowledge graph in a dashboard.
Concrete stepsAre steps, inputs, outputs, and examples spelled out?
AGoodIt provides commands for checking data, retrieving the viewer, building a fallback, and reporting the tokenized URL.
SafetyAre sending data, deleting files, and running commands disclosed?
BPartly lackingIt downloads and executes an external release through npx but does not document confirmation steps before execution.
Easy setupDoes it need few tools or API keys, and are they documented?
AGoodIt specifies prior analysis and knowledge-graph.json as prerequisites, with npx startup and pnpm fallback instructions.

The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 21, 2026. Treat it as a guide and read the original before installing.

Disagree? Request a re-evaluation

Tell us which point is wrong and why. No login needed. We will check it against the SKILL.md, redo the evaluation, and show the result here.

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

Files included (1)

  • SKILL.md7.3 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

/understand-dashboard

Start the Understand Anything dashboard to visualize the knowledge graph for the current project.

Instructions

  1. Determine the project directory and data directory:

    • If $ARGUMENTS contains a path, use that as the project directory
    • Otherwise, use the current working directory
    • Prefer the legacy .understand-anything/ data directory when it exists, otherwise use .ua/

    Use the Bash tool to resolve:

    PROJECT_ARG="$ARGUMENTS"
    if [ -n "$PROJECT_ARG" ]; then
      PROJECT_DIR=$(cd "$PROJECT_ARG" 2>/dev/null && pwd -P)
    else
      PROJECT_DIR=$(pwd -P)
    fi
    
    if [ -z "$PROJECT_DIR" ] || [ ! -d "$PROJECT_DIR" ]; then
      echo "Error: Project directory not found: ${PROJECT_ARG:-$PWD}"
      exit 1
    fi
    
    if [ -d "$PROJECT_DIR/.understand-anything" ]; then
      UA_DIR="$PROJECT_DIR/.understand-anything"
    else
      UA_DIR="$PROJECT_DIR/.ua"
    fi
    
  2. Check that $UA_DIR/knowledge-graph.json exists in the project directory. If not, tell the user:

    No knowledge graph found. Run /understand first to analyze this project.
    

    Use the Bash tool to check:

    if [ ! -f "$UA_DIR/knowledge-graph.json" ]; then
      echo "No knowledge graph found. Run /understand first to analyze this project."
      exit 1
    fi
    
  3. Find the dashboard code. The dashboard is at packages/dashboard/ relative to this plugin's root directory. Check these paths in order and use the first that exists:

    • ${CLAUDE_PLUGIN_ROOT}/packages/dashboard/ (Claude Code runtime root, highest priority)
    • ~/.understand-anything-plugin/packages/dashboard/ (universal symlink, all installs)
    • Two levels up from ~/.agents/skills/understand-dashboard real path (self-relative fallback)
    • Two levels up from ~/.copilot/skills/understand-dashboard real path (Copilot personal skills fallback)
    • Common clone-based install roots:
      • ~/.codex/understand-anything/understand-anything-plugin/packages/dashboard/
      • ~/.opencode/understand-anything/understand-anything-plugin/packages/dashboard/
      • ~/.pi/understand-anything/understand-anything-plugin/packages/dashboard/
      • ~/understand-anything/understand-anything-plugin/packages/dashboard/

    Use the Bash tool to resolve:

    SKILL_REAL=$(realpath ~/.agents/skills/understand-dashboard 2>/dev/null || readlink -f ~/.agents/skills/understand-dashboard 2>/dev/null || echo "")
    SELF_RELATIVE=$([ -n "$SKILL_REAL" ] && cd "$SKILL_REAL/../.." 2>/dev/null && pwd || echo "")
    COPILOT_SKILL_REAL=$(realpath ~/.copilot/skills/understand-dashboard 2>/dev/null || readlink -f ~/.copilot/skills/understand-dashboard 2>/dev/null || echo "")
    COPILOT_SELF_RELATIVE=$([ -n "$COPILOT_SKILL_REAL" ] && cd "$COPILOT_SKILL_REAL/../.." 2>/dev/null && pwd || echo "")
    
    PLUGIN_ROOT=""
    for candidate in \
      "${CLAUDE_PLUGIN_ROOT}" \
      "$HOME/.understand-anything-plugin" \
      "$SELF_RELATIVE" \
      "$COPILOT_SELF_RELATIVE" \
      "$HOME/.codex/understand-anything/understand-anything-plugin" \
      "$HOME/.opencode/understand-anything/understand-anything-plugin" \
      "$HOME/.pi/understand-anything/understand-anything-plugin" \
      "$HOME/understand-anything/understand-anything-plugin"; do
      if [ -n "$candidate" ] && [ -d "$candidate/packages/dashboard" ]; then
        PLUGIN_ROOT="$candidate"; break
      fi
    done
    
    if [ -z "$PLUGIN_ROOT" ]; then
      echo "Error: Cannot find the understand-anything plugin root."
      echo "Checked:"
      echo "  - ${CLAUDE_PLUGIN_ROOT:-<unset CLAUDE_PLUGIN_ROOT>}"
      echo "  - $HOME/.understand-anything-plugin"
      echo "  - ${SELF_RELATIVE:-<unresolved path derived from ~/.agents/skills/understand-dashboard>}"
      echo "  - ${COPILOT_SELF_RELATIVE:-<unresolved path derived from ~/.copilot/skills/understand-dashboard>}"
      echo "  - $HOME/.codex/understand-anything/understand-anything-plugin"
      echo "  - $HOME/.opencode/understand-anything/understand-anything-plugin"
      echo "  - $HOME/.pi/understand-anything/understand-anything-plugin"
      echo "  - $HOME/understand-anything/understand-anything-plugin"
      echo "Make sure you followed the installation instructions for your platform."
      exit 1
    fi
    
    DASHBOARD_DIR="$PLUGIN_ROOT/packages/dashboard"
    
  4. Fast path — try the prebuilt viewer first (no install, no build). Each release ships a self-contained viewer tarball; run it pinned to the installed plugin version:

    : "${PLUGIN_ROOT:?Run step 3 first so PLUGIN_ROOT is set}"
    : "${PROJECT_DIR:?Run step 1 first so PROJECT_DIR is set}"
    PLUGIN_VERSION=$(node -p "require('$PLUGIN_ROOT/package.json').version")
    VIEWER_URL="https://github.com/Egonex-AI/Understand-Anything/releases/download/v${PLUGIN_VERSION}/understand-anything-viewer.tgz"
    npx --yes "$VIEWER_URL" "$PROJECT_DIR"
    

    Run this in the background. It prints the same 🔑 Dashboard URL line as the dev server:

    • If the line appears, skip steps 5-6 and continue at step 7.
    • If the process exits without printing it (no release asset for this version, or no network), fall back to steps 5-6.
  5. Fallback: install dependencies and build if needed:

    : "${PLUGIN_ROOT:?Run step 3 first so PLUGIN_ROOT is set}"
    DASHBOARD_DIR="${DASHBOARD_DIR:-$PLUGIN_ROOT/packages/dashboard}"
    cd "$DASHBOARD_DIR" && (pnpm install --frozen-lockfile 2>/dev/null || pnpm install)
    

    Then ensure the core package is built (the dashboard depends on it):

    : "${PLUGIN_ROOT:?Run step 3 first so PLUGIN_ROOT is set}"
    cd "$PLUGIN_ROOT" && pnpm --filter @understand-anything/core build
    
  6. Fallback: start the Vite dev server pointing at the project's knowledge graph:

    : "${PROJECT_DIR:?Run step 1 first so PROJECT_DIR is set}"
    : "${DASHBOARD_DIR:?Run step 5 first so DASHBOARD_DIR is set}"
    cd "$DASHBOARD_DIR" && GRAPH_DIR="$PROJECT_DIR" npx vite --host 127.0.0.1
    

    Run this in the background so the user can continue working.

  7. Capture the access token URL from the server output. The server (viewer or Vite) prints a line like:

    🔑  Dashboard URL: http://127.0.0.1:<PORT>?token=<TOKEN>
    

    Extract the full URL including the ?token= parameter. The token is required to access the knowledge graph data — without it the dashboard will show an "Access Token Required" gate.

  8. Report to the user, including the full tokenized URL:

    Dashboard started at http://127.0.0.1:<PORT>?token=<TOKEN>
    Viewing: $UA_DIR/knowledge-graph.json
    
    The dashboard is running in the background. Press Ctrl+C in the terminal to stop it.
    

    Important: Always include the ?token= parameter in the URL you share. If you omit it, the user will be blocked by the token gate and have to manually find the token in the terminal output.

Notes

  • The fast path (step 4) downloads a version-pinned, self-contained viewer from the GitHub release — nothing is installed into the plugin directory and no build runs
  • The dashboard auto-opens in the default browser (both the viewer and Vite's --open)
  • If port 5173 is already in use, the next available port is picked (both paths)
  • In the fallback, the GRAPH_DIR environment variable tells the dev server where to find the knowledge graph

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

understand

FreeSummaryAI rating 80

Analyze project code, configuration, and documentation to build a graph for interactive architecture exploration. It maps components and dependencies, supports Japanese descriptions, and can update the analysis based on changes since the previous analyzed commit.

  • Understand the structure of an unfamiliar project
  • Explore dependencies between components
  • Generate architecture descriptions in Japanese
Egonex-AI/Understand-Anything87.7KUpdated Oct 21, 2026

understand-chat

FreeSummaryAI rating 100

Ask questions about a codebase using a knowledge graph, a map of its components and relationships. Get explanations tied to specific files, functions, dependencies, and architectural layers, with warnings when the graph may be outdated.

  • Understanding how a feature works
  • Finding callers and dependencies
  • Locating code related to a concept
Egonex-AI/Understand-Anything87.7KUpdated Oct 21, 2026

understand-diff

FreeSummaryAI rating 90

Analyze Git changes or pull requests against a knowledge graph, a map of code components and relationships. Identify modified files, nearby dependencies, affected architectural layers, and review risks, then save data for a dashboard visualization.

  • Understanding a pull request before review
  • Checking the impact of uncommitted changes
  • Reviewing changes across architectural layers
Egonex-AI/Understand-Anything87.7KUpdated Oct 21, 2026

understand-domain

FreeSummaryAI rating 70

Extract business areas, workflows, and process steps from a codebase and display them as an interactive horizontal flow graph. Use an existing knowledge graph, a map of project components, or run a lightweight scan of project files.

  • Understanding business workflows from code
  • Mapping business areas and process steps
  • Creating a business view from an existing knowledge graph
Egonex-AI/Understand-Anything87.7KUpdated Oct 21, 2026

understand-explain

FreeSummaryAI rating 100

Get a detailed explanation of a file, function, or module using an existing knowledge graph and its source code. It explains architectural roles, dependencies, callers, and data flow for readers who may not know the programming language.

  • Understand the role of a specific file
  • Trace a function’s callers and dependencies
  • Follow inputs, processing, and outputs
Egonex-AI/Understand-Anything87.7KUpdated Oct 21, 2026

understand-figma

FreeSummaryAI rating 80

Analyze a Figma file and turn its pages, screens, components, instances, and design tokens—shared design values—into an interactive graph. Open the dashboard to explore the file's structure and relationships.

  • Review the structure of a Figma file
  • Explore components, variants, and instances
  • Inspect how shared design values are used
Egonex-AI/Understand-Anything87.7KUpdated Oct 21, 2026

See all skills by Egonex-AI

Report a problem with this skill