instance-space-analysis SKILL.md skillA
instance-space-analysis from andremun/instancespace is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add andremun/instancespace/instance-space-analysis@git:20260725.2d3a6f8Pins git:20260725.2d3a6f8 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- andremun/instancespace
- Path
.claude/skills/instance-space-analysis/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260725.2d3a6f8, committed Jul 25, 2026
- First version recorded
- Jul 25, 2026
- Size
- 27,726 bytes
- Repository stars
- 46
- License
- a license file GitHub does not identify
Perform, interpret, or advise on Instance Space Analysis (ISA) -- the methodology for objective algorithm benchmarking via a 2D/3D projection of problem instances (Smith-Miles & Munoz, ACM Comput. Surv. 55(12), 2023). Use this skill whenever the user wants to: build an instance space from feature/performance meta-data; interpret PRELIM, SIFTED, PILOT, CLOISTER, PYTHIA, or TRACE/TRACE3 output; design a new ISA application for a problem domain; work with this repository's MATLAB `InstanceSpace`…
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
# Instance Space Analysis (ISA) ISA extends Rice's Algorithm Selection Problem (1976) with a geometric layer: instead of learning a selection mapping directly from features to algorithms, it projects instances into a 2D (or 3D) plane and identifies contiguous regions -- **footprints** -- where each algorithm performs well. The result is not just a predictor; it is a visual, falsifiable account of *why* an algorithm wins where it wins, and whether the benchmark suite used to draw that conclusion was diverse enough to trust. Primary source: Smith-Miles & Munoz, "Instance Space Analysis for Algorithm Testing: Methodology and Software Tools," *ACM Computing Surveys* 55(12), Article 255, 2023 (the tutorial this skill is built from). Supersedes/extends: Munoz, Villanova, Baatar & Smith-Miles, *Machine Learning* 107(1), 2018 (PILOT); Simpson, Munoz, Kandanaarachchi & Campello, "ISA3: a 3-dimensional expansion of instance space analysis," *Machine Learning* 114:240, 2025 (3D projection, TRACE3). This skill is scoped to the `andremun/InstanceSpace` MATLAB toolkit -- the reference implementation and the engine behind MATILDA. Everything in …
Read the whole file at its exact version.
How to install
mdr add andremun/instancespace/instance-space-analysis@sha256:435c9e02bcf74763The line at the top of this page pins the label git:20260725.2d3a6f8, 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_guhb6iwzu5stq6to)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, all committed on Jul 25, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260725.2d3a6f8 latest | 2026-07-25 | 2d3a6f8 | 27,726 B | A | view · diff |
| git:20260725.8c26c25 | 2026-07-25 | 8c26c25 | 26,670 B | A | view · diff |
| git:20260725.2a72546 | 2026-07-25 | 2a72546 | 25,857 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 (27726 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
andremun/instancespace · 46 stars · license a license file GitHub does not identify · pushed 2026-10-18 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_guhb6iwzu5stq6to GET https://markdownregistry.com/api/v1/resolve?ref=andremun/instancespace/instance-space-analysis GET https://markdownregistry.com/api/v1/blob/435c9e02bcf74763a8ce0e3426c825c4f59a15739eacff8cb29c703a1894ac8a
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.