Results for “conviction-score”

Promove o cumprimento de sentenca (titulo executivo judicial) — disposicoes gerais (CPC 513), titulos judiciais (CPC 515), cumprimento DEFINITIVO de pagar quantia com intimacao em 15 dias e multa de 10% + honorarios de 10% se nao pago (CPC 523 §1, penhora/avaliacao §3), demonstrativo atualizado do debito (CPC 524), cumprimento PROVISORIO sob recurso sem efeito suspensivo (CPC 520-522), alimentos com prisao civil (CPC 528 §3) e Fazenda Publica (CPC 534-535). Use quando o operador disser cumprimento de sentenca, executar a sentenca, intimar para pagar em 15 dias, multa de 10% cumprimento, cobrar sentenca transitada.

Score LLM and agent outputs using LLM-as-judge techniques — direct scoring against rubrics or pairwise comparison between two outputs. Includes built-in bias mitigation for position bias, length bias, and self-enhancement bias. Load when the user asks to score an output, judge a response, evaluate against a rubric, compare two outputs, do direct scoring, run pairwise comparison, or says "rate this", "which response is better", "score this against the rubric", "judge this output", "LLM as judge this". Sub-skill of eval-output orchestrator.

Use to design or audit a QA dispute and appeal workflow with timeboxes, adjudication standards, and second-level consistency so appeals improve trust instead of rewriting scores without rules. Trigger for "QA appeal process", "agents disputing scores", "who adjudicates QA disputes", "overturn rate too high", second-level review standards, or calibration erosion from ad-hoc score changes.

Evaluate and rank agent results by metric or LLM judge for an AgentHub session.

Fixa o valor da causa civel conforme os criterios do CPC (arts. 291-293) e trata a impugnacao ao valor da causa. Cobre os criterios por tipo de pedido (cobranca, ato juridico, alimentos, divisao, indenizacao com pedido liquido), a soma de pedidos cumulados, e a impugnacao na contestacao. Use quando o operador disser valor da causa, quanto colocar de valor, impugnar valor da causa, custas, ou ao redigir a inicial/contestacao.

Evaluate and rank agent results by metric or LLM judge for an AgentHub session.

Use this skill to evaluate which DataQ challenges have winning evidence and which don't. Covers documented vs anecdotal evidence and the 8 high-success patterns.

Score raw leads as HOT/WARM/COOL based on config-driven weights from agency.config.json

Score and prioritize leads based on firmographic fit and behavioral engagement signals, producing ranked tiers for sales team focus. Use when the user requests lead scoring or provides relevant inputs for this workflow.

Redige apelacao do CPC 1.009-1.014 contra sentenca (terminativa 485 ou definitiva 487), no prazo de 15 dias uteis, com preparo sob pena de desercao (1.007), efeito suspensivo como regra (1.012, excecoes do §1), efeito devolutivo e causa madura (1.013 §3) e majoracao de honorarios recursais (85 §11). Use quando o operador disser apelar, apelacao, recorrer da sentenca, sentenca improcedente, error in judicando, efeito suspensivo da apelacao, causa madura.

Redige a impugnacao ao cumprimento de sentenca (CPC 525) — defesa do executado em titulo JUDICIAL, no prazo de 15 dias apos os 15 do art. 523 e independentemente de penhora, com as hipoteses do §1 (I-VII: nulidade de citacao, ilegitimidade, inexigibilidade, penhora/avaliacao, excesso de execucao, incompetencia, causa extintiva superveniente), dever de declarar o valor correto sob pena de rejeicao (§4-5) e efeito suspensivo so com garantia + grave dano (§6). Use quando o operador disser impugnar cumprimento, impugnacao ao cumprimento de sentenca, excesso de execucao, defender de cumprimento de sentenca, executado quer se defender de sentenca.

Evaluates an AI judge system's pairwise ranking accuracy on generated commit messages against a heuristic ground truth from five automatic text metrics, using the MCMD dataset.

Evaluate and rank agent results by metric or LLM judge for an AgentHub session.

Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHub agents.

Evaluates execution outcomes against defined success criteria, scoring each criterion and producing a structured verdict with actionable feedback.

Outcome Eval

Calculates CRAP (Change Risk Anti-Patterns) scores for .NET methods by combining cyclomatic complexity with code coverage data from Cobertura XML reports.

Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHub agents.

Compute the F1Score metric using torchmetrics when predictions and ground-truth labels are available.

Use this skill when the user asks about FMCSA Compliance Safety Accountability (CSA) program scoring — the seven BASIC categories, BASIC Severity Indicator (BSI), peer percentiles, intervention thresholds, how violations age out, SMS Methodology, ISS (Inspection Selection System), what "alert" status means, Safety Measurement System mechanics, or DataQ disputes. Cite SMS Methodology v3.20.

Structured visual QA verdict for screenshot-to-reference comparisons

Score a UI file's design quality 0-100 against StyleSeed's design language with per-category breakdown, worst offenders, and prioritized fix list.

Lightweight ContentShake AI self-check the /draft stage can call before saving. Returns just SEO + Quality scores (no full optimization) so the writer knows whether the draft is in winning territory before /quality-check runs. Fails soft when SEMRUSH_API_KEY is unset.

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

Computes the R2Score metric using torchmetrics, handling single and multi-output predictions with options for adjusted and variance-weighted scores.

Update or correct an existing skill file based on judge feedback or improved understanding.

Score and rank options contracts for any ticker using a multi-factor model covering liquidity, IV attractiveness, Greeks balance, and risk/reward. Returns scored option chains with the best contracts highlighted.

Diagnosing and fixing bimodal matching score distributions in MaxFuse

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.

实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

Honestly evaluate AI work quality using a two-axis scoring system with mandatory devil's advocate reasoning and cross-session anti-inflation detection.

Score and iteratively improve marketing content with an expert panel until 90+. Use for content quality gates, expert panel reviews, editorial scoring, or when another skill needs a content QA loop.

Parse RFP/RFI/RFQ documents, score fit per requirement with verifiable proof points, generate win-themes, estimate winrate, and produce a bid/no-bid recommendation using the Shipley method.

Scores real estate leads based on engagement, budget, timeline, and property preference matching