oracle_certification_state_check
Skill724 starsChanged 2 months agoAGPL-3.0View on GitHub
O.R.A.C.L.E::certification_state_check — BLOCKING pre-flight, in-flight and post-flight oracle for a benchmark certification campaign (~4.5-5 GPU-hours). Invoke BEFORE starting a certification campaign, running the gates, `spark benchmark run … --pull-request-gate`, or `queue-perf-pr.sh`; between and DURING gates; and AFTER the campaign before committing `.benchmarks/` records, commenting `/stamp` or `/seal`, or believing `stamp status` / `seal status` / `PR Benchmark Certifications`. Also invoke when a stamp or seal check looks red, when asking whether the box or GPU is free, whether the tree is frozen, whether a signer is committed, or whether records agree. Fourteen litmus tests — clean PERF_PATHS tree, frozen sha, binary built from it, AVAROK_HOME and signer, stray shard dirs, subjects and hermetic pins, BFCL scorer imports, box free with a self-filtered pgrep, campaign-guard, other PRs mid-certification, top of stack, stamp/seal job sequencing, one git_sha across added records, one Speed-class signer — each tied to the code that enforces it. Hard block with advisory overrides recorded in the gitignored lockfile `.oracle_should_begin_cert`, read on start to detect a concurrent campaign and removed on release. Born from the 2026-08-28 nine-hour campaign invalidated twenty minutes before its end, and from two same-day false reds where a /stamp or /seal status was evaluated before the bot processed the command.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- site/CLAUDE.mdCLAUDE.md
- automergerSkill
- avarok-releaseSkill
- measurement-artifact-oracleSkill
- measurement-disciplineSkill
- oracle_pre_commit_cross_hardware_checkSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

