← Back to Skills Marketplace
bytesagain-lab

Step

by bytesagain-lab · GitHub ↗ · v2.0.2 · MIT-0
cross-platform ✓ Security Clean
277
Downloads
0
Stars
1
Active Installs
4
Versions
Install in OpenClaw
/install step
Description
Log daily steps, set fitness goals, and chart walking trends. Use when logging counts, tracking progress, charting trends, setting goals.
Usage Guidance
This skill appears to be a simple local CLI that stores step/fitness logs under ~/.local/share/step and operates offline. Before installing, review the full script if you want to confirm there are no hidden network calls or cron/scheduling behavior (the provided snippet shows only local file I/O and standard utilities like grep/du/tail). Expect the tool to create and append log files in that directory; back up or remove that directory if you stop using the skill. Autonomous agent invocation is allowed by default on the platform, but this skill does not request extra privileges or external credentials.
Capability Analysis
Type: OpenClaw Skill Name: step Version: 2.0.2 The 'Step' skill is a local health-tracking utility designed to log and manage fitness data in a local directory (~/.local/share/step). Analysis of scripts/script.sh and SKILL.md reveals no evidence of malicious intent, data exfiltration, or unauthorized network activity. While the script contains minor bugs—specifically a duplicate 'export' case label that renders the actual data export function unreachable and some poorly formatted command examples in the documentation—these are clearly unintentional implementation flaws rather than security risks.
Capability Assessment
Purpose & Capability
Name/description (step logging, goals, charts) matches the included shell script and SKILL.md: the tool logs entries, shows stats, exports data, and stores everything under ~/.local/share/step. No unrelated capabilities (cloud, cloud creds, system-wide config access) are requested.
Instruction Scope
SKILL.md instructs use of the local 'step' CLI and references only the DATA_DIR; the script reads/writes files only inside that directory and runs standard local utilities (du, tail, grep, wc). The instructions do not instruct the agent to read unrelated system files, environment secrets, or send data externally.
Install Mechanism
No install spec is provided (instruction-first skill). The included script is a plain Bash script; there's no download-from-URL or package install step that would write or execute remote code.
Credentials
No environment variables, credentials, or config paths are required. The script uses HOME implicitly to build a local data directory, which is appropriate for a per-user CLI tool.
Persistence & Privilege
Skill is not always-enabled and does not request privileged or system-wide persistence. It writes only to its own data directory (~/.local/share/step) and does not modify other skills or global agent settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install step
  3. After installation, invoke the skill by name or use /step
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.2
update
v2.0.1
v2.5 retry: desc+homepage+source+security
v1.0.1
retry-fix-token
v2.0.0
Domain-specific upgrade
Metadata
Slug step
Version 2.0.2
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 4
Frequently Asked Questions

What is Step?

Log daily steps, set fitness goals, and chart walking trends. Use when logging counts, tracking progress, charting trends, setting goals. It is an AI Agent Skill for Claude Code / OpenClaw, with 277 downloads so far.

How do I install Step?

Run "/install step" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Step free?

Yes, Step is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Step support?

Step is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Step?

It is built and maintained by bytesagain-lab (@bytesagain-lab); the current version is v2.0.2.

💬 Comments