hashgraph-online/awesome-codex-plugins / plugins/alpoxdev/hypercore/skills/hyper-decision
hyper-decision
UnverifiedUse this skill when the user wants a decision API in software: a model call that returns a typed judgment (a yes/no probability, one option from a closed set, an ordered score, or an image box) instead of text, through TypeSafe Jev, OpenAI Decisions, Perplexity, Liquid, Cloudflare Clef, the Vercel AI SDK or AI Gateway, OpenRouter, or an emulation on a general LLM. It decides fit, writes typed questions, calling code, request templates, eval plans, audits of label-only LLM calls, and route setup. Do not use for chat or code generation, model training, moderation policy writing, or general prompt writing.
assets/templates/routing-table.template.json
View on GitHub{
"review_verdict": "review",
"verdicts": {
"billing": { "action": "route_to_billing_queue", "human_review": false },
"technical": { "action": "route_to_technical_queue", "human_review": false },
"account": { "action": "route_to_account_queue", "human_review": false },
"other": { "action": "open_triage_task", "human_review": true },
"review": { "action": "open_human_review_task", "human_review": true }
},
"question_types": {
"boolean": { "signal": "probability of true", "acts_at_or_above": "booleanActAtOrAbove" },
"choice": { "signal": "probability of the chosen option", "acts_at_or_above": "choiceProbabilityAtOrAbove" },
"score": { "signal": "confidence where the route reports one", "acts_at_or_above": "scoreConfidenceAtOrAbove" },
"box": { "signal": "confidence, which may be null", "acts_at_or_above": "scoreConfidenceAtOrAbove" }
},
"route": {
"tier": "T1",
"dialect": "systemone",
"name": "TypeSafe direct",
"returns_distribution": true
},
"notes": "The thresholds named in question_types are pre-tuning assumptions, so evaluate them on your own labeled cases; they live in constants.template.ts, which is the single place holding them. A verdict of review is what a below-threshold answer turns into, and it is the path a person has to complete. A route that returns no distribution (T3 emulation on a general language model) cannot fill the signal for choice or score, so every such answer takes review; the route block records the tier so a caller can check before branching."
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |