Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
speccheck
SkillsSpecification conformance checker: for every ID a SPEC.md declares, find where code and tests cite it, join JUnit results, and report one evidence-backed status per ID — with an optional downgrade-only LLM judge. Ships the spec-writing / spec-review / spec-build skills.
git clone https://github.com/rioffe/speccheck.git -
opengate-mcp
MCP serversCheck whether an AI answer is grounded in its context — deterministic, no LLM judge.
@pharmatools/opengate-mcp@0.1.4 -
Kojen
MCP serversTrain, evaluate, red-team and deploy AI agents: prompt tuning, LLM-judged evals, katas.
-
evalstats
PromptsStatistical inference for AI evaluations, from model comparisons to corrections for LLM judge bias, optimized for small sample sizes. All defaults battle-tested in Monte Carlo simulations.
git clone https://github.com/ianarawjo/evalstats.git -
CompletionKit
MCP serversPrompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.