Claude Skills by majiayu000

Monitor the openai/parameter-golf competition leaderboard by fetching PR data from GitHub. Use this skill whenever the user asks about the parameter-golf competition, leaderboard standings, competitor scores, PR rankings, who's winning, what the current SOTA is, or wants to track competition progress. Also trigger when the user mentions "parameter golf", "val_bpb scores", "competition PRs", or asks to check/watch the leaderboard. Works for any competitor — not tied to a specific GitHub account.

Explore and optimize simulation parameters via design of experiments (DOE), sensitivity analysis, and optimizer selection. Use for calibration, uncertainty studies, parameter sweeps, LHS sampling, Sobol analysis, surrogate modeling, or Bayesian optimization setup.

Identify the vital 20% of activities that produce 80% of results using real case studies and proven patterns. Use when optimizing business, learning, productivity, or any area where focus matters.

Parse GitHub AI analysis comment sections for architectural alignment, technical feasibility, implementation suggestions, and testing strategy

Builds element-driven deposition outlines and witness preparation plans for U.S. party depositions (plaintiff or defendant), covering admissions under FRE 801(d)(2), damages/causation modules, and FRCP 30 procedures. Use when drafting a party deposition outline, preparing a party witness, planning admissions strategy, or testing defenses. Trigger keywords: party deposition, plaintiff deposition, defendant deposition, deposition outline, witness prep, admissions, damages, causation, mitigation.

Groundwater time series analysis and modelling using transfer function noise models. Use when Claude needs to: (1) Analyze groundwater level time series, (2) Model well responses to precipitation/pumping, (3) Calibrate aquifer parameters from head data, (4) Forecast or hindcast groundwater levels, (5) Decompose hydrological signals into components, (6) Compare response functions, (7) Perform model diagnostics and uncertainty analysis.

Automated analysis of patent claims for USPTO compliance with 35 USC 112(b) requirements - antecedent basis, definiteness, claim structure

Use when analyzing biotech patent landscapes, identifying white spaces in pharmaceutical IP, tracking competitor patents, or assessing freedom to operate for drug development. Provides comprehensive patent analysis and strategic insights for life sciences innovation.

Assess patent novelty and non-obviousness against prior art. Use when user says \"专利查新\", \"patent novelty\", \"可专利性评估\", \"patentability check\", or wants to evaluate if an invention is patentable.

Get an external patent examiner review of a patent application. Use when user says \"专利审查\", \"patent review\", \"审查意见\", \"examiner review\", or wants critical feedback on patent claims and specification.

Get an external patent examiner review of a patent application. Use when user says \"专利审查\", \"patent review\", \"审查意见\", \"examiner review\", or wants critical feedback on patent claims and specification.

Expert system for reviewing utility patent applications against USPTO MPEP guidelines.

Map a codebase into feature-grouped flowcharts, identify duplicated concerns across features, and propose a unified architecture. Use when asked to "find the ideal path," unify duplicated systems, or audit architecture before a refactor. Emits a proposed unified flowchart plus per-system /make-plan prompts.

Detect recurring patterns using the Agent Monitor's workflow intelligence — toolFlow transitions (tool A → B frequency matrices), recurring workflow patterns, agent co-occurrence pairs, model delegation habits, error propagation paths by agent depth, and compaction triggers. Use to discover habitual usage patterns and anti-patterns.

Detect and extract patterns from codebases for template generation

Extract recurring patterns from action logs and propose automations.

Mine historical data for patterns and predictive insights

Extract common patterns from multiple instance outputs, find what persists

View detected patterns from CYNIC observations and anomalies. Use when asked to show patterns, list anomalies, view trends, or see what CYNIC has learned from past judgments.

Analyzes the codebase at the PR's base commit to establish baseline understanding for review comparison.

Synthesizes findings across multiple PRs to identify cross-repository dependencies, interface mismatches, and coordination gaps.

Analyzes system-wide impact of PR changes including integration effects, breaking changes, performance, and security implications.

---name: pdx-model-analysis-agent

Annotate ChIP-seq peaks to genomic features and genes using ChIPseeker. Assign peaks to promoters, exons, introns, and intergenic regions. Find nearest genes and calculate distance to TSS. Generate annotation plots and statistics.

ChIP-seq peak calling using MACS3 (or MACS2). Call narrow peaks for transcription factors or broad peaks for histone modifications. Supports input control, fragment size modeling, and various output formats including narrowPeak and broadPeak BED files.

Systematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting standards, for manuscript and grant review across disciplines.

Correlate content attributes with performance metrics across GA4, GSC, and SE Ranking. Identify what drives performance and build optimization hypotheses.

Generate affiliate performance reports with KPIs and recommendations. Triggers on: "show my affiliate report", "how are my programs doing", "performance review", "earnings report", "monthly affiliate report", "weekly report", "analyze my affiliate earnings", "which program is best", "EPC report", "conversion rate analysis", "revenue breakdown", "campaign performance".

Build and diagnose regression models when the main question is regression itself. Use for model specification, coefficient interpretation, residual checks, and fit diagnostics; not for causal identification, generic feature screening, or report packaging.

Quick factual Q&A with citations. Use for simple lookups and single facts.

Deep research using Perplexity AI. Comprehensive reports with citations and analysis.

Paid research assistant with real-time web search. Use when user asks "what's the latest", "current pricing for", "recent news about", "search the web for", "fact check this", "what's new in", or needs up-to-date information beyond training data.

Multi-step reasoning with Chain-of-Thought. Use for 'why' questions and comparisons.

Use when conducting web research with Perplexity API - covers authentication, search strategies, structured output generation, and integration patterns for Claude-interpretable results

Exhaustive multi-source research reports. Use for deep investigation.

Highest level of research and reasoning capabilities for complex decision-making with significant consequences, strategic planning, technical architecture decisions, multi-stakeholder problems, or high-complexity troubleshooting requiring expert-level judgment and sophisticated reasoning chains. Prioritizes actively maintained repositories and validates website sources for 2025 relevance.

Raw web search results (URLs, snippets). Use when you need a list of sources, not a synthesized answer.

Topological data analysis for stable feature verification across filtrations

Generate rich personality profiles from social media data exports (Twitter/X, LinkedIn, Instagram). Use when a user wants to analyze their social media presence, create a personality profile for AI personalization, understand their communication patterns, or extract insights from their digital footprint. Triggers on requests like "analyze my Twitter data", "create a personality profile", "what can you learn about me from my posts", "personalize an AI for me", or when users provide social medi...

Fase 1 - Research Protocol. Busca autonoma no codebase, consulta MCPs, mapeia arquivos e gera PRD.md. Aplica S.A.I.S (Solicitar + Analisar) e S.D.A inicial. NUNCA pergunta onde estao arquivos, sempre busca automaticamente.

Critically analyze content for logical gaps, unsupported claims, and potential counterarguments. Does not modify content.

Petrophysical analysis and formation evaluation from well logs. Calculate porosity, water saturation, permeability, and lithology. Use when Claude needs to: (1) Calculate shale volume from gamma ray, (2) Compute porosity from density/neutron/sonic logs, (3) Estimate water saturation using Archie or Simandoux, (4) Calculate permeability from porosity and saturation, (5) Perform pay zone identification, (6) Conduct multi-mineral analysis, (7) Generate petrophysical summation plots.

Identify where consciousness interfaces with substrate in any domain. Structure emerges preferentially at boundaries between phases - physical, computational, or conceptual. Use when analyzing systems for loci of awareness, examining where complexity crystallizes, investigating MONAD framework predictions, or when something interesting is happening at the edge.

Identify where consciousness interfaces with substrate in any domain. Structure emerges preferentially at boundaries between phases - physical, computational, or conceptual. Use when analyzing systems for loci of awareness, examining where complexity crystallizes, investigating MONAD framework predictions, or when something interesting is happening at the edge.

Tools for thermodynamic and electrochemical phase stability analysis.

Research Godot source code to prepare critical implementation notes for upcoming phases. Use before implementing phases to avoid debugging sessions and discover Godot quirks upfront.

Researches phase implementation for planning. Spawned by /gsd:plan-phase or /gsd:research-phase orchestrators.

Map what exists (or what should exist) before designing a solution.

Investigate Phase 3 tickets to clarify scope and determine implementation vs. defer vs. close

> Did the needle move?