Results for “scoring”

Add a new deterministic scoring check in src/scoring/checks/ that evaluates config quality. Follows the Check[] return pattern, uses point constants from src/scoring/constants.ts, and integrates via filterChecksForTarget() in src/scoring/index.ts. Use when user says 'add scoring check', 'new check', 'modify scoring criteria', or works in src/scoring/checks/. Do NOT use for display changes or refactoring scoring logic.

The English summary is being prepared. Showing the original description.

Use when discovering niche signals, auditing ICP or won/lost evidence, rescoring accounts, or building account and lead scoring Plays. Triggers on fit scoring, engagement scoring, external proxies, and scoring leakage. Skip pure outreach copy or contributor skill installation tasks.

The English summary is being prepared. Showing the original description.

Use this skill when designing or documenting a lead scoring model in Salesforce Sales Cloud or Account Engagement: qualifying criteria, MQL/SQL threshold definitions, scoring dimensions (demographic, firmographic, behavioral), and sales handoff SLA. NOT for configuring the scoring, grading, and automation rules in Account Engagement — use admin/mcae-lead-scoring-and-grading. NOT for the whole marketing program's lifecycle stages and platform scope — use admin/marketing-automation-requirements.

The English summary is being prepared. Showing the original description.

Use this skill when gathering, documenting, or validating requirements for a Salesforce marketing automation program — covering MCAE (Account Engagement / Pardot) lifecycle stages, MQL/SQL threshold definitions, scoring model specifications (sources, weights, decay, ceiling), handoff notification design, CRM field updates on status change, and sales SLA. Trigger keywords: MQL criteria, marketing-to-sales handoff, lead lifecycle, scoring requirements, automation program requirements, Marketing Cloud Automation Studio scope. NOT for building the scoring and grading rules in MCAE — use admin/mcae-lead-scoring-and-grading. NOT for a Sales-Cloud composite score built from formula fields — use admin/lead-scoring-requirements.

The English summary is being prepared. Showing the original description.

Review completed AI work by scoring task difficulty and execution quality separately. A fixed scoring matrix, arguments for higher and lower ratings, and saved score history help examine weaknesses and detect repetitive scoring patterns across sessions.

• Evaluate a completed feature implementation
• Review the quality and coverage of a bug fix
• Reflect on work completed during a session

Use this skill when configuring MCAE (Account Engagement / Pardot) lead scoring models, grading profiles, score decay rules, or automation rules that fire on score/grade thresholds. Covers: scoring point values per activity, score decay for inactivity, Profiles for fit grading, combined MQL definitions (Score + Grade), and automation rules vs completion actions. NOT for defining the MQL model before build — use admin/lead-scoring-requirements. NOT for Engagement Studio nurture programs — use admin/lead-nurture-journey-design.

The English summary is being prepared. Showing the original description.

Creates a hiring packet from a role brief: a job post, interview guide with scoring criteria, and offer letter template. Can also prepare a DocuSign draft for review before the user approves sending it.

• Create a job post from hiring requirements
• Prepare interview questions and scoring criteria
• Draft an offer letter using an existing template

Design systems that use language models to judge AI responses. Covers scoring criteria, comparisons between two answers, bias reduction, confidence calibration, and checks against human judgments to make automated quality assessments more consistent and traceable.

• Compare responses from different models
• Run A/B tests for prompt changes
• Create shared scoring rubrics

Design workflows for completing business lead records, verifying contact details, and ranking prospects against an ideal customer profile. Plan provider sequences in Clay, scoring rules, and data quality checks around lead volume, existing tools, and budget.

• Designing a workflow to fill missing lead data
• Defining lead scores against an ideal customer profile
• Reviewing email verification when bounce rates rise

Generates complete phenotype-scoring bioinformatics research designs for any disease context and any user-defined phenotype, pathway, process, signature, or molecular program. Use when a study centers on gene-set or feature-set definition, intersection with DEGs or candidate features, phenotype scoring, feature selection, diagnostic or stratification assessment, immune or cellular-resolution interpretation, network analysis, and optional orthogonal validation. Covers five study patterns (signature discovery, phenotype scoring, feature selection, immune/cellular interpretation, multi-layer validation) and always outputs Lite / Standard / Advanced / Publication+ with a recommended primary plan, stepwise workflow, figure plan, validation hierarchy, minimal executable version, publication upgrade path, and strictly verified literature retrieval.

The English summary is being prepared. Showing the original description.

Performs ML-based protein-ligand pose prediction and scoring using DiffDock-L (diffusion-based), Boltz-1 / Boltz-2 (foundation model with affinity), Chai-1, AlphaFold3 ligand, EquiBind, TANKBind, NeuralPLexer, and hybrid workflows (DiffDock pose + GNINA rescore + PoseBusters QC). Explicit handling of when ML beats classical docking, when classical beats ML, the PB-invalid pose problem, and rescoring as the standard production hybrid. Use when modern docking is needed: foundation-model ligand-pose prediction, AI rescoring of classical poses, or scaffold-hopping in cross-docking scenarios.

The English summary is being prepared. Showing the original description.

smina molecular docking CLI. AutoDock Vina fork with customizable scoring functions, native SDF/MOL2/PDB ligand input, autoboxing, local energy minimization, and per-atom score breakdowns. Pipeline: receptor PDBQT prep -> ligand prep (RDKit/OpenBabel) -> dock via autobox or explicit grid -> rescore/minimize with custom scoring -> rank poses by affinity. Choose smina over Vina when you need custom scoring terms (--custom_scoring), local optimization of an existing pose (--local_only), per-atom contributions (--atom_term_data), or SDF/MOL2 ligands without manual PDBQT conversion. For unknown binding sites use diffdock; for the Python-bindings/Vinardo workflow use autodock-vina-docking.

The English summary is being prepared. Showing the original description.

Builds a custom lead scoring model for a business. Takes ICP definition, historical win/loss data, CRM export. Analyzes which attributes correlate with closed-won deals. Generates lead-scoring-model.md with scoring dimensions, point values, thresholds, CRM implementation guide, and validation methodology. Can also score a batch of current leads against the model.

The English summary is being prepared. Showing the original description.

Provides a structured risk scoring methodology for Data Protection Impact Assessments aligned with ENISA threat taxonomy and ISO 29134. Covers likelihood and severity assessment, risk matrix construction, inherent vs residual risk calculation, and risk appetite thresholds per EDPB WP248rev.01 guidance. Keywords: risk scoring, DPIA risk matrix, likelihood, severity, ENISA, ISO 29134, residual risk, risk appetite.

The English summary is being prepared. Showing the original description.

Deprecated alias. This skill was renamed to `deepline-scoring`. Use when a user or script still invokes `/niche-signal-discovery`: immediately load and follow the `deepline-scoring` skill instead. Triggers: ICP analysis, niche signals, won vs lost analysis, differential signals, signal discovery, ICP signal report, account scoring signals, lead scoring, first-party signals, buyer signals.

The English summary is being prepared. Showing the original description.

Performs ML-based protein-ligand pose prediction and scoring using DiffDock-L (diffusion-based), Boltz-1 / Boltz-2 (foundation model with affinity), Chai-1, AlphaFold3 ligand, EquiBind, TANKBind, NeuralPLexer, and hybrid workflows (DiffDock pose + GNINA rescore + PoseBusters QC). Explicit handling of when ML beats classical docking, when classical beats ML, the PB-invalid pose problem, and rescoring as the standard production hybrid. Use when modern docking is needed: foundation-model ligand-pose prediction, AI rescoring of classical poses, or scaffold-hopping in cross-docking scenarios.

The English summary is being prepared. Showing the original description.

Performs ML-based protein-ligand pose prediction and scoring using DiffDock-L (diffusion-based), Boltz-1 / Boltz-2 (foundation model with affinity), Chai-1, AlphaFold3 ligand, EquiBind, TANKBind, NeuralPLexer, and hybrid workflows (DiffDock pose + GNINA rescore + PoseBusters QC). Explicit handling of when ML beats classical docking, when classical beats ML, the PB-invalid pose problem, and rescoring as the standard production hybrid. Use when modern docking is needed: foundation-model ligand-pose prediction, AI rescoring of classical poses, or scaffold-hopping in cross-docking scenarios.

The English summary is being prepared. Showing the original description.

Performs ML-based protein-ligand pose prediction and scoring using DiffDock-L (diffusion-based), Boltz-1 / Boltz-2 (foundation model with affinity), Chai-1, AlphaFold3 ligand, EquiBind, TANKBind, NeuralPLexer, and hybrid workflows (DiffDock pose + GNINA rescore + PoseBusters QC). Explicit handling of when ML beats classical docking, when classical beats ML, the PB-invalid pose problem, and rescoring as the standard production hybrid. Use when modern docking is needed: foundation-model ligand-pose prediction, AI rescoring of classical poses, or scaffold-hopping in cross-docking scenarios.

The English summary is being prepared. Showing the original description.

Use PyTDC to discover therapeutic machine-learning datasets, create task-appropriate training and test splits, and evaluate predictions against curated benchmarks. Also score selected molecules with supported scoring functions, with explicit download plans and bounded outputs.

• Find datasets for therapeutic machine-learning tasks
• Plan and create task-appropriate data splits
• Evaluate predictions with benchmark-specific metrics

Rank problems and proposed fixes using four scored criteria: expected benefit, implementation cost, deployment ease, and risk. The skill produces a sorted priority table with scoring rationales and explains why the top three items should come first.

• Prioritize fixes from audit findings
• Rank improvement actions after a retrospective
• Sequence risk mitigation measures

Design interview processes for specific roles and experience levels, with round objectives, timing, suggested questions, and scoring criteria. Help interviewers align their judgments and review potential bias before using the process.

• Designing interview rounds for a specific role
• Preparing questions for each interview round
• Aligning scoring criteria across interviewers

Analyze SaaS customer data with three Python tools that calculate account health, rank churn risk, and prioritize expansion opportunities. Use repeatable weighted scores to plan customer outreach and prepare quarterly business reviews.

• Scoring customer health across an account portfolio
• Prioritizing outreach to accounts at risk of leaving
• Ranking upgrade and additional-seat opportunities

Evaluate AI models and agents on Google Cloud using test datasets and scoring criteria. Generate simulated user scenarios, analyze failures, and compare results across changes to guide improvements to prompts and code.

• Build evaluation datasets from conversation logs
• Generate simulated user scenarios
• Choose scoring criteria for responses and tool use

Prepare a Web3 bug bounty investigation by scoring targets, setting up analysis tools, reviewing past audits, and tracing how funds move. Use the findings to prioritize smart contracts and assess whether suspected issues have concrete impacts.

• Choose a protocol for a bug bounty investigation
• Prepare build, test, and static analysis tools
• Map fund flows and prioritize contract reviews