Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Devtools Visualizer

ASecurity

Use the devtools-mcp browser visualization terminal, a local web UI for every profiling/debugging run. Use when you want to SEE the data a human can explore: interactive (click-to-zoom) flame graphs, the queryable data table per run, raw logs, and the tracker as card boards (projects, status columns, task detail), across Linux/macOS/Windows. Covers starting/stopping the dashboard, what each view shows, and the CRDT sync API it serves for other replicas. The visual companion to devtools-mcp-us...

9 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentsgodebuggingapibackend

Works with

terminalcliapimcp

Security Analysis

A100/100

Scanned 9/27/2026

$npx -y skills add Ugbot/ai-grind --skill devtools-visualizer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Devtools Visualizer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Devtools Visualizer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ugbot-devtools-visualizer/badge)](https://www.skillsdirectory.com/skills/ugbot-devtools-visualizer)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: devtools-visualizer
description: >
  Use the devtools-mcp browser visualization terminal, a local web UI for every
  profiling/debugging run. Use when you want to SEE the data a human can explore:
  interactive (click-to-zoom) flame graphs, the queryable data table per run, raw
  logs, and the tracker as card boards (projects, status columns, task detail),
  across Linux/macOS/Windows. Covers starting/stopping the dashboard, what each
  view shows, and the CRDT sync API it serves for other replicas. The visual
  companion to devtools-mcp-usage and tracker-usage.
---

# The visualization terminal (devtools-mcp `devtools_dashboard`)

The LLM works from bounded summaries + Polars queries; a **human** often wants to
*see* the profile. `devtools_dashboard` serves a local web UI that turns the
browser into a window onto the same runs.

## Start / stop

```
devtools_dashboard(action="start")               # prints a http://127.0.0.1:8765 URL
devtools_dashboard(action="start", open_browser=true)   # also opens it
devtools_dashboard(action="status")
devtools_dashboard(action="stop")
```

It binds to localhost only, so nothing leaves the machine. Use `port=0` to grab
any free port if 8765 is taken. The server reads the **live** workspace, so new
runs appear on refresh; no restart needed.

## What you get

- The `/` dashboard lists every run (run_id, suite:tool, target, time, exit) with
  links to each view. Runs that have stacks show a **flame** link.
- `/run/<id>` has the bounded text summary, the full queryable data table
  (the same DataFrame `devtools_analyze` filters), and links to flame/raw.
- `/flame/<id>` is an interactive flame graph: width = inclusive time,
  depth grows downward, hover for name + %, and **click any frame to zoom** into
  its subtree (it re-roots; use "reset" to go back). Server-rendered SVG, no JS
  framework, works offline.
- `/raw/<id>` has raw tool output and logs, bounded.
- `/tracker` holds the project-management views as proper cards: project
  overview with status chips + progress bars, **`/tracker/<PROJ>`** a board
  (status columns of task cards + the "what needs to happen" plan with ready
  and blocked highlighted), **`/tracker/task/<KEY>`** full task detail
  (criteria checklist, commits, dependencies, children).
- `/api/crdt/*` is the JSON sync API other tracker replicas pull from /
  push to (`tracker_sync` on another machine points here).

## Typical flow

```
devtools_run(suite="etw", tool="cpu", binary="C:/app.exe")     # or jvm/dtrace/perf/cdb
devtools_dashboard(action="start", open_browser=true)
# → open the flame link for that run, click into the hot subtree
```

## Cross-platform parity

Flame graphs render identically from any backend that produces stacks: **perf**
(`perf script`) on Linux, **dtrace** (`ustack`) on macOS, **etw** (folded) and
**cdb** (thread stacks) on Windows, and **jvm** (JFR/async-profiler) anywhere.
Folded stacks are the universal currency.

## Notes

- This is the seam for future agentic and visual tooling. The UI reads the live
  AppContext, so new pages/controls can be added without touching the backends.
- For interpreting what you see, read [[flamegraph-reading]]. For the overall
  tool workflow, [[devtools-mcp-usage]].

Attribution

UgbotUgbot
View sourceSee grades on GitHubMore from Ugbot →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →