subwave-llm-bench SKILL.md skillA
subwave-llm-bench from perminder-klair/subwave is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add perminder-klair/subwave/subwave-llm-bench@git:20261020.20ff360Pins git:20261020.20ff360 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- perminder-klair/subwave
- Path
.claude/skills/subwave-llm-bench/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261020.20ff360, committed Oct 20, 2026
- First version recorded
- Jul 9, 2026
- Size
- 11,413 bytes
- Repository stars
- 1,665
- License
- MIT
Benchmark and compare LLM models for SUB/WAVE's on-air calls — track picks, segments, listener requests, DJ scripts, banter, and programme beats — in pool, agent and Track Shortlist modes, using controller/scripts/llm-bench (the matrix harness) or the legacy picker-only controller/scripts/picker-test.mjs. Use this skill whenever the user wants to assess, benchmark, compare, or test which LLM model to run the station on — phrases like "which model should I use…
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
# SUB/WAVE LLM model benchmark Two harnesses, one job: measure how well a **provider + model** handles the station's real LLM calls before trusting it on air. - **`llm-bench`** (`controller/scripts/llm-bench/`, `npm run llm-bench`) — the primary harness. A matrix runner over **every on-air call kind**: pool picks (`pickNextTrack`), agent picks (`djAgentPick`), Track Shortlist picks (`djShortlistPick`), pool + agent segments (`generateSegment` / `djAgentSegment`), request matching (`matchRequest` / `djAgentRequest`), the free-text scripts (intro, link, station ID, hourly), banter, and the programme family (plan, beats, exchanges). Scores reliability + deterministic rule checks, prints a per-model comparison table, writes a diffable JSON report. - **`picker-test.mjs`** — the legacy picker-only deep-dive. Still useful for high-iteration picker runs comparable with historical results, and it has a bundled orchestration script (see the legacy section at the end). Both import the **live prompts and schemas from `src/`** (never copies), fake everything external (library, tools, weather/news data), and override …
Read the whole file at its exact version.
How to install
claude plugin marketplace add https://markdownregistry.com/mp/a/art_xmiinjwd3cxfyj3p/d3efe21b8f911969c445b35dfecce6d43bf197edd7bb381fb48a312ec988103a.json
Then /plugin install subwave-llm-bench@markdownregistry-xmiinjwd3cxfyj3p in Claude Code. It installs git:20261020.20ff360, the one graded A here, pinned to the commit it was graded at, and leaves it there.
mdr add perminder-klair/subwave/subwave-llm-bench@sha256:d3efe21b8f911969The line at the top of this page pins the label git:20261020.20ff360, 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_xmiinjwd3cxfyj3p)
2 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in perminder-klair/subwave/subwave-llm-bench since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.
Got a copy of subwave-llm-bench from somewhere else? Ask it: where did my subwave-llm-bench come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.
Versions
The registry has recorded 4 versions of this file, between Jul 9, 2026 and Oct 20, 2026, about one every 34 days.
Watch this file (sign in, one email per new version)
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261020.20ff360 latest | 2026-10-20 | 20ff360 | 11,413 B | A | view · diff |
| git:20261015.d7e9c73 | 2026-10-15 | d7e9c73 | 10,377 B | A | view · diff |
| git:20261013.42e5382 | 2026-10-13 | 42e5382 | 10,194 B | A | view · diff |
| git:20260709.42ca3ac | 2026-07-09 | 42ca3ac | 9,535 B | A | view |
Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.
Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml
It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.
Installed this file, say at .claude/skills/subwave-llm-bench/SKILL.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies
In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies
No sha256sum on your machine? shasum -a 256 prints the same lines.
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 (11413 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
perminder-klair/subwave · 1,665 stars · license MIT · pushed 2026-11-17 · branch develop
API
GET https://markdownregistry.com/api/v1/artifacts/art_xmiinjwd3cxfyj3p GET https://markdownregistry.com/api/v1/resolve?ref=perminder-klair/subwave/subwave-llm-bench GET https://markdownregistry.com/api/v1/blob/d3efe21b8f911969c445b35dfecce6d43bf197edd7bb381fb48a312ec988103a
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.