open-benchmark-methodology SKILL.md skillA
open-benchmark-methodology from vibeic/vibe-ic is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add vibeic/vibe-ic/open-benchmark-methodology@git:20261102.b666e3dPins git:20261102.b666e3d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- vibeic/vibe-ic
- Path
vibe-ic-marketplace/plugins/vibe-ic/skills/open-benchmark-methodology/SKILL.md- Versions recorded
- 14
- Latest version
- git:20261102.b666e3d, committed Nov 2, 2026
- First version recorded
- Sep 2, 2026
- Size
- 37,032 bytes
- Repository stars
- 32
- License
- Apache-2.0
Mandatory for VerilogEval, VerilogEval-v2, VerilogEval-Human, CVDP, RTLLM, PyHDL-Eval, RTL-Repo, MetRex, ResBench, ChipAgentsBench, benchmark, pass@1, benchmark floor/defect, run/rerun/score benchmark, or interpreting benchmark results. Enforces one general product entry, clean-room blind evaluation, Program First plus independent AI review/backup, official host scoring, evidence-backed triage, and capture of general enhancements.
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
# Open-Benchmark Methodology
The benchmark measures the Vibe-IC product path, not a benchmark-tuned agent.
Every runnable RTL evaluation uses the same solve core as an ordinary IC-design
request. Dataset differences are allowed only at the input/output boundary.
## Rule 0 — one product entry
For the open RTL suites in `benchmark/BENCHMARK_REGISTRY.json`, the only
authoring path is:
```text
benchmark_dispatch.py <bench> --solve
-> benchmark_io_adapter.stage (input translation only)
-> task_nature_route (input-only advisory proposal)
-> needs_ai_routing.jsonl (AI judges task nature before runner)
-> benchmark_dispatch.py <bench> --resume (hash-bound AI route validation)
-> vibe_ic_one_shot_runner --flow 109 --flow109-manifest ...
--entry-step <stable-ID> --exit-step <stable-ID>
--execution-mode default (normal product runner)
-> Program candidate or declared AI backup
-> independent hash-bound AI review
-> benchmark_dispatch.py <bench> --resume
-> accepted candidate
-> benchmark_dispatch.py <bench> --score
-> official host scorer
```
…Read the whole file at its exact version.
How to install
mdr add vibeic/vibe-ic/open-benchmark-methodology@sha256:fbb265bd71921efcThe line at the top of this page pins the label git:20261102.b666e3d, 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_imyepob6k7i6447q)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 14 versions of this file, between Sep 2, 2026 and Nov 2, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261102.b666e3d latest | 2026-11-02 | b666e3d | 37,032 B | A | view · diff |
| git:20261102.650ca91 | 2026-11-02 | 650ca91 | 36,427 B | A | view · diff |
| git:20261101.a208f65 | 2026-11-01 | a208f65 | 34,671 B | A | view · diff |
| git:20261031.7d23644 | 2026-10-31 | 7d23644 | 33,990 B | A | view · diff |
| git:20261030.a2a11ae | 2026-10-30 | a2a11ae | 31,322 B | A | view · diff |
| git:20261026.ffc59ab | 2026-10-26 | ffc59ab | 29,244 B | A | view · diff |
| git:20261001.19b93ed | 2026-10-01 | 19b93ed | 28,883 B | A | view · diff |
| git:20260929.4ad6eda | 2026-09-29 | 4ad6eda | 27,423 B | A | view · diff |
| git:20260906.9730907 | 2026-09-06 | 9730907 | 26,638 B | A | view · diff |
| git:20260906.63936c8 | 2026-09-06 | 63936c8 | 23,010 B | A | view · diff |
| git:20260904.3146662 | 2026-09-04 | 3146662 | 18,817 B | A | view · diff |
| git:20260902.baa5a16 | 2026-09-02 | baa5a16 | 18,525 B | A | view · diff |
| git:20260902.104b97d | 2026-09-02 | 104b97d | 17,621 B | A | view · diff |
| git:20260902.fc32402 | 2026-09-02 | fc32402 | 11,352 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 (37032 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
vibeic/vibe-ic · 32 stars · license Apache-2.0 · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_imyepob6k7i6447q GET https://markdownregistry.com/api/v1/resolve?ref=vibeic/vibe-ic/open-benchmark-methodology GET https://markdownregistry.com/api/v1/blob/fbb265bd71921efce0edfb7d1bc76e24d3f278acb9a111ff06e6c3f0baddf4e2
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.