Skip to content
Agentmart
Submit a tool

run

Single-command pipeline launcher for propose->design->create->polish->rewrite->export with hard gates.

Skill by Anubis44197

IndexedApache-2.0
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/anubis44197-run

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Single-command pipeline launcher for propose->design->create->polish->rewrite->export with hard gates.

Use cases: design, data

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/run

What's inside

Skill name
run
Description
Single-command pipeline launcher for propose->design->create->polish->rewrite->export with hard gates.
License
Apache-2.0
Instructions
30 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Run Skill

## Purpose
Start the full novel pipeline from one command and enforce hard execution gates.

## Command
- `/run`

## Execution Contract
1. Ensure runtime bootstrap is prepared:
   - `powershell -ExecutionPolicy Bypass -File scripts/install.ps1`
2. Execute orchestrator:
   - `powershell -ExecutionPolicy Bypass -File scripts/run_pipeline.ps1 -ProjectRoot . -FromPhase intake -ToPhase export`

## Hard Rules
- Do not skip phases.
- Do not claim completion without runner evidence artifacts.
- Respect approval gates for `create`, `rewrite`, `export`.
- If a phase fails or is blocked, stop and report exact error + evidence path.

## Required Outputs
- `runtime/current-run.json`
- `runtime/runs/RUN-*/run-summary.json`
- `runtime/runs/RUN-*/evidence/*.json`

## Notes
- In manual mode, the IDE/operator must still complete each phase task.
- For unattended execution, configure command mode in `runtime/runner-config.json`.

From Anubis44197/kit_hub, Apache-2.0.

More from Anubis44197/kit_hub

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 10, 2026 (3 months ago)
Last release
Aug 16, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Anubis44197

Cite this page

run skill. Agent Mart. https://agentmart.dev/skills/anubis44197-run (last updated 2026-10-24)