Results for “spearman-rank”

Evaluates how well internal model representations (hidden states) predict token-level information importance in summarization tasks, using NDCG@10 and Spearman's rank correlation.

Evaluates the correlation between a zero-cost NAS metric (epsilon) and actual training accuracy across different neural architecture search spaces, testing the metric's ability to rank architectures without training. It probes whether output dispersion from constant weight initializations can serve as a reliable.

Rank an existing set of context chunks by relevance, diversity, freshness, and utility. Use when retrieval has already produced candidates that must be scored or reranked; use context-retrieval when the source corpus still needs to be searched.

Rank the top-5 leads worth calling today with tailored, history-grounded talking points and proposed calendar blocks — no auto-send.

Ranks any list of impediments and their countermeasures using a value-stream scoring model (ROI, Cost to Implement, Ease of Deployment, Risk Factor) and a fixed prioritization formula.

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

Ranks mutual connections by bridge value for warm introductions, using a weighted graph model with decay and engagement bonuses.

Rank a backlog of feature ideas by impact, effort, risk, and strategic alignment to identify the top 5 to pursue.

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

OWASP Top 10 + Supabase-first hardening burndown. Use when "security audit plan", "OWASP audit", "hardening plan", or "security burndown". App-layer auth flows → audit-auth-flows. Table RLS → plan-rls-audit. Key rotation → plan-secrets-audit. App LLM attacks → audit-llm-security.

Diagnoses social threats and rewards across five domains to improve organizational, team, and product experiences.

采用孙宇晨的思维框架与表达方式，基于其公开言论和著作提炼的14个核心心智模型、18条决策启发式及表达DNA，用于分析加密行业、审视商业决策并提供反馈。

Provides SQL window function examples for ranking, aggregation, lag/lead, value extraction, frame specifications, and advanced analytics.

Recommend the right AI model for a task by scoring candidates across six dimensions (Reasoning, Engineering, Speed, Breadth, Reliability, Governance) and displaying a spider-chart profile.

Screens resumes with skill matching, experience evaluation, and bias-free candidate ranking

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

Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts. Handles copy, sequences, landing pages, strategy docs, titles, charts, recruiting evaluations, or anything else that needs a quality gate. Recursively iterates until all scores hit 90+ (max 3 rounds). Use when asked to: "expert panel this", "score this", "rate these variants", "quality check this", "panel review", "which version is better", "expert score", "evaluate this copy/strategy/page", or when another skill needs a quality gate on its output. Also triggers on: "score this landing page", "expert panel these email variants", "rate this headline", "panel these charts".

Internal harness probe for the OI-3 readability-guidance spike. Use only when explicitly told to invoke spike-probe. Verifies that a freshly-created project skill renders into a subagent's context via the Skill tool.

Scaffolds fullstack projects (Next.js, FastAPI, MERN, Django) and analyzes code quality with security and complexity scoring.

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題.

Audit a Supabase/Postgres project for Row-Level Security and access-control gaps, then produce a phased remediation plan. Use when "RLS", "is my Supabase secure", "anyone can read my data", "lock down my tables". App-layer session/route gates → audit-auth-flows.

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

Ranks weekly token unlocks by Absorption Ratio (unlock value / 7d avg volume) instead of supply percentage, with per-event cliff vs linear classification, recipient category, and a one-line market read.

Adopts the perspective and thinking framework of Justin Sun, using his mental models, decision heuristics, and communication style to analyze crypto industry topics and business decisions.

Evaluates the robustness and alignment with human judgment of reference-based and reference-free evaluation metrics for machine translation and summarization, particularly under adversarial conditions.

Provides a single 0-100 cycle score blending VIX, SPY IV Rank, Put/Call ratio, and valuation percentile to determine offense vs. defense posture, based on Howard Marks' market cycle framework.

Evaluate a paper's contribution novelty, identify best-fit SSCI journal fields and ABS star rating, and recommend 20 target journals. Trigger when user says "paper submission" / "paper-submission" / "投稿评估" / "期刊推荐" / "target journal" / "选刊".

Evaluate everything the PA agent manages — tasks, skills, PA network health, billing, calendar connections, and memory quality. Use when: owner asks for an evaluation, wants to know what's working and what isn't, or requests a performance report. Combines supervisor status with quality scoring.

Turn "which leads should I work?" into a lead-by-lead work plan. Per-lead status (never-touched, engaged-not-replied, gone-cold, hot), days-dark per lead, last-touch quality, a re-engagement ranker, and a recommended next action for every lead. Built for SDRs and full-cycle reps, customizable to your CRM and your outreach tool. Trigger on "which leads should I work?", "who haven't I touched?", "show me cold leads", "hot leads to follow up on", "who's gone dark?", "re-engagement candidates", or any lead-level work-assignment question.

Agent Roster

Calculates a per-ticker panic index (0-100) from six weighted signals including VIX, IV Rank, RSI-14, volume anomaly, put/call ratio, and consecutive down days, triggering Bull Put Spread entry signals at scores ≥60.

Turn a pile of accounts into a stack-ranked priority list with a reason on every row. A layered score (gates first, then an evidence-weighted base rank over the signals you actually have, then bounded boosts for product usage and buyer intent) that stays fair across channels and never scores a blank field as a zero. Built for B2B GTM teams, customizable to your signals and your ICP. Trigger on "score these accounts", "rank by fit", "composite ICP score", "stack-rank my list", "who should I work first", "prioritize these leads", or any multi-signal account qualification.

Spec Craft

Build and run the owner's self-branding system in a structured way across LinkedIn, Substack, dev.to, X, profile rewrites, recurring series, and comment strategy. Use when the owner asks for positioning, a branding plan, profile updates, content drafts, a publishing sequence, comment ideas, or help maintaining a consistent public voice. Optimize for operator credibility: specific experience, defensible numbers, concrete artifacts, and category ownership.

Test a pipeline stage's skill file by running the stage WITH and WITHOUT the skill on the same input, comparing outputs, and proposing skill edits. Ryan Law principle 3 — recursive self-improvement. Run after any board complaint about a stage, and monthly per core stage.