Skip to content
TrustedSkillsbeta
Back to all skills

Trails

Listed
0xsequence-demos·vlatest·other·MIT

Trails generates creative, evocative prose snippets based on a given prompt, sparking narrative ideas and overcoming writer's block.

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 0xsequence-demos/trails-skills --skill trails -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

0xsequence-demos

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 failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 3 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: api.bankr.bot, api.trails.build, trails-api.sequence.app.

    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.

    Hosts contacted

    api.trails.buildundeclaredapi.bankr.botundeclaredtrails-api.sequence.appundeclared

    What it found (3 of 22)

    • .agents/skills/trails/SKILL.md:314contacts api.trails.build
      const quote = await fetch('https://api.trails.build/quote', {
    • .agents/skills/trails/snippets/node-api.ts:80contacts api.trails.build
      const TRAILS_API_URL = 'https://api.trails.build';
    • plugins/trails/SKILL.md:314contacts api.trails.build
      const quote = await fetch('https://api.trails.build/quote', {

  • 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 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 0xsequence-demos/trails-skills at db19e77ed2.

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

Commit
db19e77ed2
Manifest
plugins/trails/SKILL.md
Scanned
32 files, 10,068 lines
Copies in repo
2 — all of them scanned
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 trails skill allows AI agents to track and visualize a sequence of actions or steps taken during an interaction. It records these "trails," providing a historical record of decisions and operations performed by the agent. This can be invaluable for debugging, auditing, and understanding complex workflows. The trails are presented in a structured format suitable for analysis.

When to use it

  • Debugging Agent Behavior: If an agent is exhibiting unexpected or incorrect behavior, using trails allows you to step through its actions and identify the source of the problem.
  • Auditing Complex Workflows: For tasks involving multiple steps and dependencies (e.g., automated data processing), trails provide a clear audit log for compliance or review.
  • Analyzing Agent Decision-Making: Understand how an agent arrived at a particular conclusion by examining the sequence of actions it took.
  • Replicating Successful Interactions: If an agent successfully completes a task, you can analyze its trail to understand the optimal steps and replicate that process in future interactions.

Key capabilities

  • Records sequences of actions.
  • Provides structured output for trails data.
  • Supports visualization of action history.

Example prompts

  • "Enable trails logging."
  • "Show me the last 5 trails."
  • "Analyze the trail from my previous interaction with the system."

Tips & gotchas

The trails skill may impact agent performance due to the overhead of recording actions. Consider enabling it only when debugging or auditing is necessary, rather than continuously running it in production environments.