# Ralph Sprint

> Create, repair, validate, or advance a Ralph sprint from a repository specification. Use when the user asks for the first or next sprint, sprint planning, spec breakdown, chunk design, CURRENT_SPRINT selection, or preparation after a completed sprint. Never start the autonomous loop unless separately requested.

- **Type:** Skill
- **Install:** `agentstack add skill-zacharygcook-agent-skills-ralph-sprint`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [zacharygcook](https://agentstack.voostack.com/s/zacharygcook)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [zacharygcook](https://github.com/zacharygcook)
- **Source:** https://github.com/zacharygcook/agent-skills/tree/master/skills/ralph-sprint

## Install

```sh
agentstack add skill-zacharygcook-agent-skills-ralph-sprint
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Ralph Sprint

Prepare exactly one reviewable sprint and stop before execution.

1. Read repository agent instructions, the durable `SPEC.md` or equivalent, `.ralph/config.env`, and
   all existing sprint state.
2. If the current sprint is incomplete or its hooks failed, repair or resume it instead of creating a
   competing sprint.
3. Select the next dependency-ordered slice of the spec. Do not create speculative future sprint
   folders.
4. Create or validate `README.md`, `IMPLEMENTATION_PLAN.md`, `relevant-specs.md`, `chunks.json`,
   `prompt.md`, and `SCRATCHPAD.md` under `.ralph/sprints//`.
5. Keep chunks sequential and bounded. Give each concrete acceptance criteria, accurate artifact
   paths, and repository ownership in multi-repo mode.
6. Set `CURRENT_SPRINT`, run `just validate` when available, and repair every setup defect.
7. Summarize the goal, chunks, validation, risks, and operator review path. Do not run `just run`.

When installed beside `$ralph-loop`, its `references/spec-breakdown.md`, `references/sprint.md`, and
`references/chunks.md` provide the complete shared contract. Preserve those invariants even when the
umbrella skill is unavailable.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [zacharygcook](https://github.com/zacharygcook)
- **Source:** [zacharygcook/agent-skills](https://github.com/zacharygcook/agent-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-zacharygcook-agent-skills-ralph-sprint
- Seller: https://agentstack.voostack.com/s/zacharygcook
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.