discover SKILL.md skillA

discover from amd-agi/hyperloom is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add amd-agi/hyperloom/discover@git:20261112.b7ffc4a

Pins git:20261112.b7ffc4a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
amd-agi/hyperloom
Path
src/hyperloom_arbor/.claude/skills/dossier/discover/SKILL.md
Versions recorded
2
Latest version
git:20261112.b7ffc4a, committed Nov 12, 2026
First version recorded
Nov 11, 2026
Size
11,528 bytes
Repository stars
272
License
a license file GitHub does not identify

Write the dossier's reading parts, which need no GPU when the evidence exists: 1 model architecture, 2 framework and system, 3 the served code read method by method, 4 the optimization target and the benchmark's rules, 5 the workload and the CPU work it causes, and 10 earlier optimizations, with the dossier's index. Run by Arbor in the map.discover chapter, or by hand when a dossier is missing or these parts are stale.

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

# Discover: the dossier's reading parts

**In a campaign, Arbor runs this skill in a turn of its own.** Its argument is the path of a brief: read the brief
first. It names the dossier's directory, the files to write, and the campaign's program.
**By hand,** the directory is `docs/dossier/<model>-<workload>-<gpu>/`.

**Before writing:**
- Read [the rules](../shared/rules.md) (relative to this skill's directory): every number with a source and label,
  every part with a status, and the asks.
- Look the dossier up (`dossier:read`, `bash ../shared/find-dossier.sh`). Rewrite no part that still holds.
- Start a missing index from [the template](../shared/template.md).

**Parts that wait on later ones:**
- Part 1's kernel column and part 3's kernel-to-method mapping wait on parts 7 and 8 (`dossier:measure`). Write them
  `partial`, naming what fills them. `dossier:measure` completes them.
- Part 4's `## The benchmark's rules` table comes from the benchmark's rules when the `benchmark` plugin wrote them
  (`benchmarks/<name>/rules.md`, named in the brief). Copy them in with their source.

**End your reply** with one `LEDGER:` line per part written, a FACT naming its file:
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_sxyptkwkdcea2ykw/d8198c7544fe336512df5dcdf8e3a3dbd8ba5ae93fa1c609dc69dffdd81e0dcb.json

Then /plugin install discover@markdownregistry-sxyptkwkdcea2ykw in Claude Code. It installs git:20261112.b7ffc4a, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add amd-agi/hyperloom/discover@sha256:d8198c7544fe3365

The line at the top of this page pins the label git:20261112.b7ffc4a, 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 badge

[![mdr](https://markdownregistry.com/badge/art_sxyptkwkdcea2ykw.svg)](https://markdownregistry.com/a/art_sxyptkwkdcea2ykw)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in amd-agi/hyperloom/discover 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 discover from somewhere else? Ask it: where did my discover 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 2 versions of this file, between Nov 11, 2026 and Nov 12, 2026, more than one a day.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261112.b7ffc4a latest2026-11-12 b7ffc4a 11,528 BA view · diff
git:20261111.eef3c682026-11-11 eef3c68 11,001 BA view
Keep it current by itself, install once

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.

Install on GitHub

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.

Keep it current by itself

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.

Check a whole project

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

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 (11528 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

amd-agi/hyperloom · 272 stars · license a license file GitHub does not identify · pushed 2026-11-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_sxyptkwkdcea2ykw
GET https://markdownregistry.com/api/v1/resolve?ref=amd-agi/hyperloom/discover
GET https://markdownregistry.com/api/v1/blob/d8198c7544fe336512df5dcdf8e3a3dbd8ba5ae93fa1c609dc69dffdd81e0dcb

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 amd-agi/hyperloom

analyze-upstream-pr SKILL.md skill
amd-agi/hyperloom · .claude/skills/analyze-upstream-pr/SKILL.md · Analyze whether an upstream pull request applies to an AMD/ROCm deployment. Invoke with the PR's repository and number…
git:20261020.6cc6611 · audit A · 272 stars
check-prior-art SKILL.md skill
amd-agi/hyperloom · .claude/skills/check-prior-art/SKILL.md · Check whether a planned optimization already exists upstream before building it. Invoke with a one-sentence mechanism…
git:20261020.a160c20 · audit A · 272 stars
review-pr SKILL.md skill
amd-agi/hyperloom · .claude/skills/review-pr/SKILL.md · Review a Hyperloom pull request. Invoke with a PR number whenever asked to review, re-review or sanity-check a PR in…
git:20261111.8986752 · audit A · 272 stars
AGENTS.md AGENTS.md file
amd-agi/hyperloom · AGENTS.md
git:20261111.a2c399d · audit A · 272 stars
CLAUDE.md CLAUDE.md file
amd-agi/hyperloom · CLAUDE.md
git:20260921.6b4b413 · audit B · 272 stars
hyperloom-remote-mn-qwen3-30b SKILL.md skill
amd-agi/hyperloom · docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b/SKILL.md · Run a 4-hour multi-node Hyperloom Qwen3-30B-A3B optimization (Infera PD-disaggregated or RayJob aggregated) with…
git:20261111.a2c399d · audit A · 272 stars
hyperloom-custom-advanced SKILL.md skill
amd-agi/hyperloom · examples/hyperloom-custom-advanced/SKILL.md · Run an advanced configurable Hyperloom optimization session with explicit model, framework, workload, objective, and…
git:20261111.a2c399d · audit B · 272 stars
hyperloom-qwen3-14b-fp8-12h-forge SKILL.md skill
amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h-forge/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session on SGLang, vLLM or ATOM with the per-kernel KernelForge…
git:20261111.a2c399d · audit B · 272 stars
hyperloom-qwen3-14b-fp8-12h SKILL.md skill
amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session on SGLang, vLLM or ATOM. Use when the user wants a…
git:20261111.a2c399d · audit B · 272 stars
hyperloom-qwen3-8b-3h SKILL.md skill
amd-agi/hyperloom · examples/hyperloom-qwen3-8b-3h/SKILL.md · Run a 3-hour Hyperloom Qwen3-8B FRAMEWORK_AGENT (OPTIMIZE) session without the Kernel Agent. Use when the user wants a…
git:20261111.a2c399d · audit B · 272 stars
hyperloom-workload-optimizer SKILL.md skill
amd-agi/hyperloom · examples/skills/hyperloom-workload-optimizer/SKILL.md · Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the…
git:20260924.f2e2a9c · audit A · 272 stars
critic-agent SKILL.md skill
amd-agi/hyperloom · src/hyperloom/agents/critic/SKILL.md · Critic layer for the inference optimizer. Use when Conductor asks for a Critic Review verdict on Orchestration or…
git:20261023.0718479 · audit A · 272 stars

Every file in amd-agi/hyperloom

Other files named discover

discover SKILL.md skill
suboss87/fdeops · skills/discover/SKILL.md · Trace a customer workflow and identify the problem, baseline and evidence gaps. Use for discovery or an unclear…
git:20261005.ed7f271 · audit A · 817 stars
discover SKILL.md skill
anombyte93/prd-taskmaster · skills/discover/SKILL.md · Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in…
git:20261102.3071951 · audit A · 612 stars
discover SKILL.md skill
zaxbyhub/opencode-swarm · .opencode/skills/discover/SKILL.md · Full execution protocol for MODE: DISCOVER -- read-only repository discovery and governance/context mapping.
git:20261012.097422c · audit A · 536 stars
discover SKILL.md skill
zaxbyhub/opencode-swarm · .claude/skills/discover/SKILL.md · Full execution protocol for MODE: DISCOVER -- read-only repository discovery and governance/context mapping.
git:20261012.097422c · audit A · 536 stars
discover SKILL.md skill
qbeka/jev-job-search · .claude/skills/discover/SKILL.md · Refresh the job queue without a browser. Use when the user says /discover, "find jobs", "refresh the queue", or before…
git:20261112.0f99505 · audit A · 374 stars
discover SKILL.md skill
konglong87/superpm · commands/discover/SKILL.md
git:20260924.7250d3a · audit C · 94 stars
discover SKILL.md skill
konglong87/superpm · skills/workflows/discover/SKILL.md · Product discovery workflow — chain market analysis, competitor research, demand validation, and prioritization Use…
git:20260924.a3d6f74 · audit A · 94 stars
discover SKILL.md skill
drafthq/draft · skills/discover/SKILL.md · Primary router for discovery, debugging, investigation, quality, and exploration workflows. Analyzes user intent and…
git:20260614.c276954 · audit A · 40 stars

Browse by kind, by grade A, or by owner.