synthesis-local-model-runtime SKILL.md skillA
synthesis-local-model-runtime from synthesisengineering/synthesis-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add synthesisengineering/synthesis-skills/synthesis-local-model-runtime@v2.0.0Pins v2.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- synthesisengineering/synthesis-skills
- Path
skills/synthesis-local-model-runtime/SKILL.md- Versions recorded
- 7
- Latest version
- v2.0.0, committed Oct 6, 2026
- First version recorded
- Aug 23, 2026
- Size
- 6,703 bytes
- Repository stars
- 23
- License
- Apache-2.0
Profile a computer, compare Ollama, LM Studio, llama.cpp and MLX-LM, recommend open-weight models that fit its memory and storage, install and update them with identity receipts, and verify inference. Use for local models, Ollama, which model fits this Mac or PC, model inventory or local benchmarks.
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
# Synthesis Local Model Runtime Select local models from measured capacity and dated artifact evidence. Do not turn a model name, parameter count, vendor origin, or successful launch into a claim that an artifact is safe, private, independent, unmarked, or suitable for every workload. ## Binding rules Rules 1 to 11 are the operating contract in its original order (10 and 11 changed in v5; references/preserved.md keeps the old text); 12 to 18 distill references/selection-and-boundaries.md and references/catalog-maintenance.md. 1. Profile the machine with `scripts/local_model_runtime.py profile`. The profiler emits only selection-relevant fields. It never emits hostnames, serial numbers, hardware UUIDs, provisioning identifiers, or account data. 2. Validate the bundled catalog before using it: `scripts/local_model_runtime.py catalog`. 3. Inspect `runtimes` and choose a managed environment. Ollama is the default; LM Studio is the optional managed alternative. llama.cpp and MLX-LM are reported as direct runtimes with their actual capability boundaries. 4. Load any local policy and create a dry-run plan. Recommendation applies …
Read the whole file at its exact version.
How to install
mdr add synthesisengineering/synthesis-skills/synthesis-local-model-runtime@sha256:1406de30f02c986dThe line at the top of this page pins the label v2.0.0, 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_p34hqfoqujd7pnyv)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Aug 23, 2026 and Oct 6, 2026, about one every 7 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v2.0.0 latest | 2026-10-06 | 0a99aa0 | 6,703 B | A | view · diff |
| v2.0.0 | 2026-10-06 | 6aa3c4e | 6,009 B | A | view · diff |
| v1.1.0 | 2026-08-23 | 9a234a5 | 13,636 B | A | view · diff |
| v1.1.0 | 2026-08-23 | ecf1356 | 13,621 B | A | view · diff |
| v1.0.5 | 2026-08-23 | e74d9e4 | 10,267 B | A | view · diff |
| v1.0.4 | 2026-08-23 | 924f5a2 | 9,074 B | A | view · diff |
| v1.0.3 | 2026-08-23 | 5796109 | 8,823 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 (6703 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
synthesisengineering/synthesis-skills · 23 stars · license Apache-2.0 · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_p34hqfoqujd7pnyv GET https://markdownregistry.com/api/v1/resolve?ref=synthesisengineering/synthesis-skills/synthesis-local-model-runtime GET https://markdownregistry.com/api/v1/blob/1406de30f02c986d4a1ae44923cdef76a72df1a6eb12e6a8c268f5c1c175c8c9
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.