Execute

Runs shell commands directly from Claude conversations and captures the output back into the chat. You'd reach for this when you need Claude to actually execute something on your system rather than just suggest commands, like running build scripts, checking file contents, or automating deployment steps. The obvious caveat is security: you're giving an AI direct terminal access, so this makes sense in controlled environments or when you're comfortable reviewing what gets executed. Think of it as turning Claude from a coding assistant into one that can actually touch your filesystem and run your tools.

skills.sh installs: 376
GitHub stars: 29.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add alirezarezvani/claude-skills --skill execute --agent claude-code

Installs into .claude/skills of the current project.

Files

/c-level-agents:execute — 90-Day Execution Plan

Command: /c-level-agents:execute <decision-path>

Turns an approved decision into a 90-day plan with weekly milestones, named DRIs, and a check-in cadence. Where most decisions die: between "we decided" and "what's next Monday?"

Pipeline Position

/c-level-agents:office-hours  →  /c-level-agents:brief  →  /c-level-agents:boardroom  →  /c-level-agents:decide  →  /c-level-agents:execute  →  /c-level-agents:post-mortem
                                                                       ↑ you are here

Input

An approved decision record (output of /c-level-agents:decide).

Output Plan Format

Saved to ~/.claude/execution/YYYY-MM-DD-<slug>.md:

# Execution Plan: <decision title>
**Decision:** <link to /c-level-agents:decide record>
**Owner (Sponsor):** <founder or exec>
**Start:** YYYY-MM-DD
**Checkpoint:** YYYY-MM-DD (90d)

## Outcome (binding)
[Copied from decision: success + kill criteria]

SKILL.md on GitHub