Results for “regime-verdict”

Outcome Eval

Structured visual QA verdict for screenshot-to-reference comparisons

Record a decision: finalized → ADR (optionally rule + guide or spec + plan); open proposal → RFC. Use for 'we decided', 'record this decision', 'make it a standard', 'draft an RFC', 'should we switch to Y'. Not for feature planning or documenting existing code.

Debugging constant Markov regime features in RL observations - when HMM probabilities show uniform values instead of dynamic regime estimates

Explains how Agent Script instruction resolution works across three phases, with patterns for pre-LLM setup, LLM reasoning, and post-action loops.

The single highest-leverage decision is recognizing that most of what teams call

Drafts a Motion for Judgment Notwithstanding the Verdict (JNOV) under FRCP 50(b) or state equivalents, with alternative new-trial request. Builds element-by-element evidentiary insufficiency arguments using transcript citations and preserves the appellate record. Use when drafting JNOV motions, post-trial motions, renewed judgment as a matter of law, or challenging jury verdicts for insufficient evidence.

Structured visual QA verdict for screenshot-to-reference comparisons

Analyse experiment results, run validity checks (SRM, exposure parity, data integrity, novelty/primacy), interpret causally, make a ship/iterate/kill decision against the pre-declared rule, and append to cumulative learnings. Forces honest readouts — strips significance claims from underpowered or peek-violating tests; never lets directional results masquerade as causal wins. Load when results exist, or when the user says "read out this experiment", "analyse the test", "did the test win", "interpret the results", "what did we learn", "ship or kill", or when the experimentation orchestrator routes here.

Verify a Jira issue against the current repository state, then post a Jira comment with a PASS, PARTIAL, FAIL, or BLOCKED verdict. Works in two modes: (a) feature-branch mode, comparing a checked-out branch to its base ref; or (b) main/trunk mode, verifying that an issue is already implemented on the current default branch (typical for stories that have already merged). Use when a user asks whether a branch or merged change completes a Jira ticket, or needs a Jira-visible verification comment.

Reconcile canonical declarative documents under docs/ with verified implementation discoveries after a FULLY_IMPLEMENTED moonspec-verify verdict. Use when an orchestration run must decide whether verified discoveries show the owning canonical document is impossible, unclear, or inconsistent, apply the smallest correct doc update, or escalate ambiguous authority conflicts and deliberate divergences instead of editing.

ATA RAI Remnant Ablation / Adjuvant Therapy Decision Tool

Decide

Perform a non-destructive post-implementation verification gate validating the implementation against spec.md, plan.md, tasks.md, and constitution.md.

PR Fleet

Prioritize product work with explicit criteria, scoring, tradeoffs, and decision rationale.

Processes a PR's review comments (Copilot or human), classifies them, applies the fixes that belong, replies to each thread, and pushes. Use whenever the user says "address the review", "fix what Copilot said", "handle the comments", mentions Copilot already reviewed a PR, or passes a PR number/URL with pending reviews — or in Spanish "revisá los comentarios", "arreglá lo que dijo Copilot", "atendé el review".

Analisa os efeitos da revelia (CPC 344-346) e suas excecoes (345), tanto quando o cliente e o revel quanto quando a parte contraria e revel. Cobre a presuncao de veracidade dos fatos (344), as quatro hipoteses em que ela NAO opera (345 — litisconsorte contestante, direito indisponivel, falta de instrumento que a lei repute indispensavel, fatos inverossimeis/contraditorios com a prova), a fluencia de prazos sem intimacao (346) e a possibilidade de o revel ingressar e produzir prova. Use quando o operador disser revelia, reu revel, parte nao contestou, efeitos da revelia, presuncao de veracidade, ou meu cliente perdeu o prazo de defesa.

PM-invocable protocol for Cargo publish and release operations in the trusty-tools Rust monorepo: semver rules, 10-step release sequence, macOS codesign safety, and cross-crate dependency ordering

Pressure-test any business idea with a five-angle adversarial panel (Critic, Champion, Analyst, Investigator, Customer) that returns a single GO/RESHAPE/KILL verdict with the cheapest test to de-risk it.

Verify tasks marked [X] in tasks.md are implemented, not phantom completions (marked done but backed by missing or dead code).

Adversarially verify an implementation against its objective, acceptance criteria, definition of done, and prohibitions using fresh evidence. Use for completion gates, release readiness, or independent verification after implementation and review.

Acceptance Eval

Decide