self-improving-agent-builder SKILL.md skillA
self-improving-agent-builder from rysweet/amplihack-rs is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add rysweet/amplihack-rs/self-improving-agent-builder@v1.1.0Pins v1.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- rysweet/amplihack-rs
- Path
amplifier-bundle/skills/self-improving-agent-builder/SKILL.md- Versions recorded
- 2
- Latest version
- v1.1.0, committed May 16, 2026
- First version recorded
- May 4, 2026
- Size
- 5,852 bytes
- Repository stars
- 11
- License
- none declared
Encodes a continuous improvement loop for goal-seeking agents: EVAL, ANALYZE, RESEARCH (hypothesis + evidence + counter-arguments), IMPROVE, RE-EVAL, DECIDE. Auto-commits improvements (+2% net, no regression >5%) and reverts failures. Works with all 4 SDK implementations. Auto-activates on "improve agent", "self-improving loop", "agent eval loop", "benchmark agents", "run improvement cycle".
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
# Self-Improving Agent Builder
## Purpose
Run a closed-loop improvement cycle on any goal-seeking agent implementation:
```
EVAL -> ANALYZE -> RESEARCH -> IMPROVE -> RE-EVAL -> DECIDE -> (repeat)
```
Each iteration measures L1-L12 progressive test scores, identifies failures
with `error_analyzer.py`, runs a research step with hypothesis/evidence/
counter-arguments, applies targeted fixes, and gates promotion through
regression checks.
## When I Activate
- "improve agent" or "self-improving loop"
- "agent eval loop" or "run improvement cycle"
- "benchmark agents" or "compare SDK implementations"
- "iterate on agent scores" or "fix agent regressions"
## Quick Start
```
User: "Run the self-improving loop on the mini-framework agent for 3 iterations"
Skill: Executes 3 iterations of EVAL->ANALYZE->RESEARCH->IMPROVE->RE-EVAL->DECIDE
Reports per-iteration scores, net improvement, and commits/reverts.
```
## Runner Script
The self-improvement loop is implemented as a Rust CLI:
```bash
# Basic usage
amplihack eval self-improve --sdk mini --iterations 3
# Full options
amplihack eval self-improve \
--sdk mini \
--iterations 5 \
--improvement-threshold 2.0 \
…Read the whole file at its exact version.
How to install
mdr add rysweet/amplihack-rs/self-improving-agent-builder@sha256:1db8b851d753d994The line at the top of this page pins the label v1.1.0, 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_7lh4z3m4ooxzgu4j)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between May 4, 2026 and May 16, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.0 latest | 2026-05-16 | 6626bc8 | 5,852 B | A | view · diff |
| v1.1.0 | 2026-05-04 | b7ad1ff | 5,898 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 (5852 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
rysweet/amplihack-rs · 11 stars · license none declared · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7lh4z3m4ooxzgu4j GET https://markdownregistry.com/api/v1/resolve?ref=rysweet/amplihack-rs/self-improving-agent-builder GET https://markdownregistry.com/api/v1/blob/1db8b851d753d994f4ab25c5ce1581f8177a146640ffa1e943b39a61a09d17c8
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.