sk-create-benchmark SKILL.md skillA
sk-create-benchmark from michelkerkmeester/skilled-agent-harness_spec-driven-loops is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-benchmark@v1.6.0.0Pins v1.6.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- michelkerkmeester/skilled-agent-harness_spec-driven-loops
- Path
.hermes/skills/sk-create-benchmark/SKILL.md- Versions recorded
- 5
- Latest version
- v1.6.0.0, committed Oct 11, 2026
- First version recorded
- Sep 18, 2026
- Size
- 25,551 bytes
- Repository stars
- 39
- License
- MIT
Author MCP-promotion and behavior artifacts.
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
<!-- generated by sync-skills-hermes.cjs; do not edit --> > Canonical source: `.skilled/skills/sk-doc/sk-create-benchmark/`. This is a generated markdown-only copy so Hermes can load the > skill without scanning the canonical directory; read `references/`, `assets/` and `scripts/` > from the canonical path above. <!-- Keywords: create-benchmark, benchmark-report.md, source.md, mcp_server benchmarks, benchmark promotion, skill-local benchmark, MCP bake-off, benchmark folder, behavior benchmark, behavior-benchmark.md, behavior_benchmark, scenario contract, behavior-benchmark framework, claude-baseline, benchmark/README.md, run-label folder --> # create-benchmark `create-benchmark` is the `sk-doc` benchmark-authoring packet. It covers: - **MCP promotion** — promote curated evidence from a shipped spec packet into a consuming skill's `mcp-server/benchmarks/benchmark-<YYYY-MM-DD>/`, including winner, fixture, caveats, replay commands, and source pointer (§3-8). - **Behavior** — author a `<mode>/behavior-benchmark/` index, scenario contracts, and Claude baseline under the shared measurement framework (§9). The skill-local surface is the look-here-first entry point, not the archive. …
Read the whole file at its exact version.
How to install
mdr add michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-benchmark@sha256:313d9f024fb7ae5bThe line at the top of this page pins the label v1.6.0.0, 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_tfd3vfm5pbc7nb5t)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 18, 2026 and Oct 11, 2026, about one every 6 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.6.0.0 latest | 2026-10-11 | c3e7463 | 25,551 B | A | view · diff |
| v1.6.0.0 | 2026-10-11 | d93100d | 25,572 B | A | view · diff |
| v1.5.0.0 | 2026-09-27 | cacbf58 | 34,074 B | A | view · diff |
| v1.5.0.0 | 2026-09-18 | 03ec2cc | 33,340 B | A | view · diff |
| v1.5.0.0 | 2026-09-18 | ce72d86 | 42,033 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 (25551 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
michelkerkmeester/skilled-agent-harness_spec-driven-loops · 39 stars · license MIT · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_tfd3vfm5pbc7nb5t GET https://markdownregistry.com/api/v1/resolve?ref=michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-benchmark GET https://markdownregistry.com/api/v1/blob/313d9f024fb7ae5bb81201db1ca2eb80264640dcb7dc7a89b5247057ddfd5313
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 michelkerkmeester/skilled-agent-harness_spec-driven-loops
Every file in michelkerkmeester/skilled-agent-harness_spec-driven-loops