benchmarking SKILL.md skillA
benchmarking from signet-ai/signetai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add signet-ai/signetai/benchmarking@git:20261007.6f9a333Pins git:20261007.6f9a333 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- signet-ai/signetai
- Path
.agents/skills/benchmarking/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261007.066f6f9, committed Oct 7, 2026
- First version recorded
- Oct 7, 2026
- Size
- 5,847 bytes
- Repository stars
- 310
- License
- a license file GitHub does not identify
Benchmark Signet memory with MemoryBench: regression-check Dreaming and recall changes, compare models, diagnose score drops, and record results; NOT for the prompt-submit latency benchmark.
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
# Benchmarking Signet's memory quality is measured with MemoryBench (`memorybench/`) running against an isolated Signet daemon. This skill covers the workflows for running and interpreting those benchmarks. `web/docs/src/content/docs/benchmarking.md` and `memorybench/README.md` own the command, flag, and benchmark documentation; read them rather than relying on this file for flags. ## When to Use - A change touches Dreaming (prompt, tools, operations, evidence delivery), recall (search, ranking, SEC, dampening), ingestion, or the MemoryBench Signet provider, and needs proof that results did not get worse. - Comparing Dreaming models or settings (provider, codemode, concurrency, input budget). - A benchmark score dropped and the cause is unknown. - Running full LongMemEval or BEAM for a number someone will cite. ## Workflows Pick the workflow, then read its reference before running anything: | Goal | Reference | | --- | --- | | Check that a change did not regress results (the default) | [`references/regression-check.md`](references/regression-check.md) | …
Read the whole file at its exact version.
How to install
mdr add signet-ai/signetai/benchmarking@sha256:21e160a69731ffcdThe line at the top of this page pins the label git:20261007.6f9a333, 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_gkotfodrsttmxxci)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Oct 7, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261007.066f6f9 latest | 2026-10-07 | 066f6f9 | 5,847 B | A | view · diff |
| git:20261007.6f9a333 | 2026-10-07 | 6f9a333 | 5,573 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 (5847 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
signet-ai/signetai · 310 stars · license a license file GitHub does not identify · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_gkotfodrsttmxxci GET https://markdownregistry.com/api/v1/resolve?ref=signet-ai/signetai/benchmarking GET https://markdownregistry.com/api/v1/blob/21e160a69731ffcdce0c3f0a7809a445f05c1e80f7e1d4a3732eb25259744d0b
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 signet-ai/signetai
Every file in signet-ai/signetai