scenarios-extractor SKILL.md skillA
scenarios-extractor from openxiangshan/xiangshanlab is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add openxiangshan/xiangshanlab/scenarios-extractor@git:20260723.ebce76aPins git:20260723.ebce76a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- openxiangshan/xiangshanlab
- Path
tools/scenarios-extractor/skills/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260723.ebce76a, committed Jul 23, 2026
- Size
- 7,120 bytes
- Repository stars
- 62
- License
- none declared
Generate detailed, code-grounded XiangShan verification scenario descriptions from a microarchitecture optimization mechanism name, feature name, module name, or short prompt such as MDP, branch prediction, prefetch, replay, queue arbitration, cache miss handling, or CSR/control optimization. Use when Codex must combine tools/verification-driver scenario-driver rules with tools/xiangshan-code-analyzer/skills/analyze-xiangshan-kunminghu source analysis to produce concrete scenario descriptions…
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
# Scenarios Extractor ## Overview Use this skill to turn a microarchitecture mechanism into verification-ready scenario descriptions. Start from the user's mechanism name, locate the effective XiangShan implementation through `analyze-xiangshan-kunminghu`, then select applicable scenario-driver rules from `verification-driver` and emit concrete scenarios tied to source evidence. Primary source packs: - Code analysis: `/nfs/home/yuanmiaomiao/XiangShanLab/tools/xiangshan-code-analyzer/skills/analyze-xiangshan-kunminghu` - Verification driver rules: `/nfs/home/yuanmiaomiao/XiangShanLab/tools/verification-driver/skills` - Output template: `references/scenario-output-template.md` - Mechanism workflow: `references/mechanism-workflow.md` ## Workflow 1. Normalize the request into a mechanism target. - Expand acronyms only after checking code/docs. For `MDP`, first search for `MDP`, `mdp`, `Memory Dependence`, `MemDep`, and memory-dependence predictor names in XiangShan source and analysis references. - If the mechanism maps to multiple modules, keep a top-level scenario set and one subsection per effective module. …
Read the whole file at its exact version.
How to install
mdr add openxiangshan/xiangshanlab/scenarios-extractor@sha256:68a4bc7f602ea6b1The line at the top of this page pins the label git:20260723.ebce76a, 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_pw4j2sjn7iauikqq)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 23, 2026.
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 (7120 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
openxiangshan/xiangshanlab · 62 stars · license none declared · pushed 2026-11-06 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_pw4j2sjn7iauikqq GET https://markdownregistry.com/api/v1/resolve?ref=openxiangshan/xiangshanlab/scenarios-extractor GET https://markdownregistry.com/api/v1/blob/68a4bc7f602ea6b141ba3765607d0bdb05b58055a58c95a005d93cfb67a26987
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.