Read the project statistical contract before changing a score or inference rule. State the null probability space, alternative, selection scope, and assumptions. Test exact toy cases before simulation
Imported from zchboswell/constant-atlas (constant_atlas_research_blueprint/constant_atlas_blueprint/nested-instructions/statistics/AGENTS.md). Install upstream with npx skills add zchboswell/constant-atlas --skill statistics. Copyright stays with the author.
Statistics-specific instructions
Install at src/constant_atlas/statistics/AGENTS.md after verifying instruction loading.
Read the project statistical contract before changing a score or inference rule.
State the null probability space, alternative, selection scope, and assumptions.
Test exact toy cases before simulation. Audit dependence and finite-tail resolution.
Never call a running score an e-process without its conditional guarantee.
Preserve the global error allocation and frozen confirmation configurations.
Add a regression test for every repaired inferential failure.
Scientific review is required; passing software tests alone is insufficient.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
yaml
targets:
- https://api.opensmartroute.ai/api/v1/registry/zchboswell-constant-atlas-statistics/manifest # or paste the manifest below
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
zchboswell-constant-atlas-statistics.ocm.jsonjson
{
"ocm": "1",
"id": "zchboswell-constant-atlas-statistics",
"kind": "skill",
"name": "statistics",
"description": "Read the project statistical contract before changing a score or inference rule. State the null probability space, alternative, selection scope, and assumptions. Test exact toy cases before simulation. Audit dependence and finite-tail resolution. Never call a running score an e-process without its conditional guarantee. Preserve the global error allocation and frozen confirmation configurations. Add a regression test for every repaired inferential failure. Scientific review is required; passing software tests alone is insufficient.",
"publisher": "zchboswell",
"version": "1.0.0",
"capabilities": {
"domains": [
"math",
"coding"
],
"tags": [
"skill-md",
"github-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Read the project statistical contract before changing a score or inference rule. State the null probability space, alternative, selection scope, and assumptions. Test exact toy cases before simulation. Audit dependence and finite-tail resolution. Never call a running score an e-process without its conditional guarantee. Preserve the global error allocation and frozen confirmation configurations. Add a regression test for every repaired inferential failure. Scientific review is required; passing software tests alone is insufficient."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-agents",
"repository": "https://github.com/zchboswell/constant-atlas",
"path": "constant_atlas_research_blueprint/constant_atlas_blueprint/nested-instructions/statistics/AGENTS.md",
"ref": "624bec4255937770fe9e55e70cd2ce2878eb5f78",
"url": "https://github.com/zchboswell/constant-atlas/blob/624bec4255937770fe9e55e70cd2ce2878eb5f78/constant_atlas_research_blueprint/constant_atlas_blueprint/nested-instructions/statistics/AGENTS.md",
"key": "zchboswell/constant-atlas/constant_atlas_research_blueprint/constant_atlas_blueprint/nested-instructions/statistics/AGENTS.md"
}
},
"instructions": "# Statistics-specific instructions\nInstall at `src/constant_atlas/statistics/AGENTS.md` after verifying instruction loading.\n\nRead the project statistical contract before changing a score or inference rule.\nState the null probability space, alternative, selection scope, and assumptions.\nTest exact toy cases before simulation. Audit dependence and finite-tail resolution.\nNever call a running score an e-process without its conditional guarantee.\nPreserve the global error allocation and frozen confirmation configurations.\nAdd a regression test for every repaired inferential failure.\nScientific re",
"cost": {
"context_tokens": 165
}
}
Fetch it by URL: GET /api/v1/registry/zchboswell-constant-atlas-statistics/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.