Home / bkraad47 / fat_llama_fftw · GitHub

iterate-fat-llama SKILL.md skillA

iterate-fat-llama from bkraad47/fat_llama_fftw is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add bkraad47/fat_llama_fftw/iterate-fat-llama@git:20260909.b85385a

Pins git:20260909.b85385a in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: bkraad47/fat_llama_fftw
Path: .claude/skills/iterate-fat-llama/SKILL.md
Versions recorded: 1
Latest version: git:20260909.b85385a, committed Sep 9, 2026
Size: 9,767 bytes
Repository stars: 14
License: BSD-3-Clause

End-to-end iterate-and-ship loop for fat_llama — refreshes the review-current-state factblock, runs test-fat-llama, and dispatches generate-code to fix what it finds, repeating up to 5 cycles or until audio quality is fully satisfactory; rolls back to whichever cycle scored best if none was fully satisfactory; then regenerates docs, bumps the version, and opens a PR for review. Use when asked to autonomously iterate on fat_llama's code/tests/audio quality and ship the result as a reviewable…

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

Before doing anything else, read `.claude/skills/rules/iterate-fat-llama.md` in full — it defines the cycle cap, score formula, naming conventions, version-bump policy, and remote-action confirmation requirement referenced throughout the steps below, and may be updated over time without this file changing. Also read `.claude/rules/scope-and-safety.md` for the filesystem write scope and safety boundaries every skill/agent follows, and `.claude/rules/project-mission.md` for what fat_llama actually is and how it works.

Also read `README.md` at the repo root in full, right now, before Step 0 — it's fat_llama's own description of its purpose and method (iterative soft thresholding of FFT data to upscale compressed audio across supported formats, tested and built primarily against the MP3→FLAC outcome, CPU/FFTW-only, deliberately without AI/ML-based upscaling). Carry that context — condensed per `.claude/rules/project-mission.md` — into every `generate-code` dispatch in step (d) below and into the docs/changelog/PR steps that follow, so nothing drifts toward an out-of-scope "fix".
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add bkraad47/fat_llama_fftw/iterate-fat-llama@sha256:dce17b6a6c0c662c

The line at the top of this page pins the label git:20260909.b85385a, 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.

Badge

[![mdr](https://markdownregistry.com/badge/art_c6fijiidujs6ljho.svg)](https://markdownregistry.com/a/art_c6fijiidujs6ljho)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 9, 2026.

version	committed	commit	size	audit
git:20260909.b85385a latest	2026-09-09	b85385a	9,767 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (9767 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

GitHub

bkraad47/fat_llama_fftw · 14 stars · license BSD-3-Clause · pushed 2026-09-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_c6fijiidujs6ljho
GET https://markdownregistry.com/api/v1/resolve?ref=bkraad47/fat_llama_fftw/iterate-fat-llama
GET https://markdownregistry.com/api/v1/blob/dce17b6a6c0c662c73964ced3a4ba0fce893fe71f12855040bde00a3ccab6fec

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.