Skip to content
TrustedSkillsbeta
Back to all skills

Braintrust Analyze

Checked
parcadei·vlatest·agents·MIT

Analyzes complex situations, identifies key stakeholders, and suggests strategic actions based on diverse data inputs.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add parcadei/continuous-claude-v3 --skill braintrust-analyze -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

parcadei

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned parcadei/continuous-claude-v3 at d07ff4b06b.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
d07ff4b06b
Manifest
.claude/skills/braintrust-analyze/SKILL.md
Scanned
2 files, 156 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The Braintrust Analyze skill analyzes Claude Code sessions to provide insights into your workflow. It examines tracing data to identify patterns, issues, and opportunities for improvement within your AI agent interactions. Specifically, it breaks down tool usage, agent activity (like plan-agent or debug-agent), skill activations, and token consumption.

When to use it

This skill is useful in the following scenarios:

  • After completing a complex task to perform a retrospective analysis.
  • When debugging why a task failed.
  • For weekly reviews of your productivity patterns.
  • To identify opportunities for creating new skills or improving existing ones.
  • To understand token usage trends over time.

Key capabilities

  • Session Analysis: Provides detailed breakdowns of individual Claude Code sessions, including tool usage and agent activity.
  • Loop Detection: Identifies repeated sequences of the same tool calls, potentially indicating inefficient approaches or stuck loops.
  • Usage Statistics: Tracks agent and skill usage over time (last 7 days).
  • Token Trends: Visualizes token consumption trends.
  • Session Replay: Allows you to replay a specific session to view the full sequence of actions taken.

Example prompts

Here are some example commands that can be used with this skill:

  • uv run python -m runtime.harness scripts/braintrust_analyze.py --last-session: Analyze the last completed session and display a summary.
  • uv run python -m runtime.harness scripts/braintrust_analyze.py --detect-loops: Detect any looping patterns in recent sessions.
  • uv run python -m runtime.harness scripts/braintrust_analyze.py --weekly-summary: Generate a weekly summary of your activity.

Tips & gotchas

  • Prerequisites: Requires a BRAINTRUST_API_KEY configured in either your user's .claude/.env file or the project's .env file. Braintrust tracing must also be enabled through the braintrust-claude-plugin.
  • The skill is designed for analyzing Claude Code sessions, not general AI agent interactions.