ralph SKILL.md skillA
ralph from naimkatiman/continuous-improvement is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add naimkatiman/continuous-improvement/ralph@git:20260517.966ce51Pins git:20260517.966ce51 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- naimkatiman/continuous-improvement
- Path
plugins/continuous-improvement/skills/ralph/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260517.966ce51, committed May 17, 2026
- First version recorded
- Apr 27, 2026
- Size
- 8,670 bytes
- Repository stars
- 9
- License
- MIT
Enforces Law 6 (Iterate Means One Thing) of the 7 Laws of AI Agent Discipline at PRD scale. Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete. Converts PRDs to executable JSON, implements stories iteratively with quality checks, and tracks progress.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Ralph — Autonomous Agent Loop Ralph runs iteratively until all PRD stories are complete. Each iteration: picks highest priority story, implements, runs quality checks, commits if passing, updates progress, repeats. ## When to Use - Large features that exceed a single context window - Multi-story PRDs that need consistent implementation - Tasks requiring repeated verification and commit cycles - Long-running development that benefits from persistence across interruptions ## Do NOT Use When - Task is a one-shot fix completable in a single edit — just edit the file - You haven't written a PRD yet — write the PRD first, then run Ralph against it - The work spans fewer than 3 stories — single-iteration verification is enough - You need to explore or plan before committing to scope — use a planning skill first; Ralph is for execution, not discovery - You want manual control over each iteration — run quality checks yourself, no need for Ralph's loop ## Prerequisites - Git repository - PRD document (markdown format) - `jq` installed (`brew install jq` on macOS) ## Workflow ### 1. Create a PRD Generate a detailed requirements document using the PRD skill: ``` …
Read the whole file at its exact version.
How to install
mdr add naimkatiman/continuous-improvement/ralph@sha256:ab334428065c8e16The line at the top of this page pins the label git:20260517.966ce51, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_iq2qupy6dfoocxwr)
6 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Apr 27, 2026 and May 17, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260517.966ce51 latest | 2026-05-17 | 966ce51 | 8,670 B | A | view · diff |
| git:20260503.b7b2ed1 | 2026-05-03 | b7b2ed1 | 8,639 B | A | view · diff |
| git:20260503.e12848d | 2026-05-03 | e12848d | 6,260 B | A | view · diff |
| git:20260429.4947cb8 | 2026-04-29 | 4947cb8 | 3,817 B | A | view · diff |
| git:20260427.56c3ed4 | 2026-04-27 | 56c3ed4 | 3,725 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8670 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
naimkatiman/continuous-improvement · 9 stars · license MIT · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_iq2qupy6dfoocxwr GET https://markdownregistry.com/api/v1/resolve?ref=naimkatiman/continuous-improvement/ralph GET https://markdownregistry.com/api/v1/blob/ab334428065c8e16677f8122bada88777cd329bc569cabecf6e4158879c0b82a
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from naimkatiman/continuous-improvement
Every file in naimkatiman/continuous-improvement