AI & ML

pjt222 Skill

Achieve distributed agreement without central authority using bee democracy, threshold voting, and quorum sensing. Covers proposal generation, advocacy dynamics, commitment thresholds, deadlock resolution, and consensus quality assessment. Use when a group must decide between options without a designated leader, when centralized decision-making is a bottleneck, when stakeholders have different perspectives to integrate, or when designing automated systems that must reach consensus such as distributed databases or multi-agent AI.

pjt222 Skill

Version machine learning datasets using DVC (Data Version Control) with remote storage backends, build reproducible data pipelines with dependency tracking, integrate with Git workflows, and ensure data lineage for model reproducibility. Use when versioning large datasets that do not fit in Git, tracking data changes alongside code changes, ensuring ML experiment reproducibility, sharing datasets across team members, or auditing data lineage for compliance requirements.

pjt222 Skill

AIコーディングアシスタントにプロジェクト固有の指示を提供する効果的な CLAUDE.mdファイルを作成する。構造、一般的なセクション、すべきこと・ すべきでないパターン、MCPサーバーとエージェント定義との統合をカバー する。AIアシスタントを使用する新しいプロジェクトを始める場合、既存の プロジェクトでのAIの動作を改善する場合、プロジェクトの規約と制約を 文書化する場合、またはMCPサーバーやエージェント定義をプロジェクト ワークフローに統合する場合に使用する。

pjt222 Skill

Separate expensive observation from cheap decision-making in autonomous agent loops using a two-clock architecture. A fast clock accumulates data into a digest file; a slow clock reads the digest and acts only when something is pending. Idle cycles cost nothing because the action clock returns immediately after reading an empty digest. Use when building autonomous agents that must observe continuously but can only afford to act occasionally, when API or LLM costs dominate and most cycles have nothing to do, when designing cron-based agent architectures with observation and action phases, or when an existing heartbeat loop is too expensive because it calls the LLM on every tick.

pjt222 Skill

AI systematic knowledge acquisition from unfamiliar territory — deliberate model-building with feedback loops. Maps spaced repetition principles to AI reasoning: survey the territory, hypothesize structure, explore with probes, integrate findings, verify understanding, and consolidate for future retrieval. Use when encountering an unfamiliar codebase or domain, when a user asks about a topic requiring genuine investigation rather than recall, when multiple conflicting sources require building a coherent model, or when preparing to teach a topic and deep understanding is required first.

pjt222 Skill

Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.

pjt222 Skill

Create a new team composition file following the agent-almanac team template and registry conventions. Covers team purpose definition, member selection, coordination pattern choice, task decomposition design, machine-readable configuration block, registry integration, and README automation. Use when defining a multi-agent workflow, composing agents for a complex review process, or creating a coordinated group for recurring collaborative tasks.

pjt222 Skill

按照 agent-almanac 智能体模板和注册表规范创建新的智能体定义文件。涵盖角色 设计、工具选择、技能分配、模型选择、前置元数据模式、必需章节、注册表集成 和发现符号链接验证。适用于向库中添加新的专业智能体、为 Claude Code 子智能体 定义角色，或创建具有精选技能和工具的领域专属助手。

pjt222 Skill

按照 Agent Skills 开放标准（agentskills.io）创建新的 SKILL.md 文件。 涵盖前置元数据模式、章节结构、编写包含预期/失败处理对的有效步骤、 验证清单、交叉引用和注册表集成。适用于为智能体固化可重复流程、 向技能库添加新能力、将指南或操作手册转换为智能体可消费格式， 或在项目和团队间标准化工作流。

pjt222 Skill

通过就地完善角色或创建高级变体来演进现有智能体定义。涵盖对照最佳实践 评估当前智能体、收集演进需求、选择范围（完善 vs. 变体）、对技能、工具、 能力和限制应用更改、更新版本元数据，以及同步注册表和交叉引用。适用于 智能体技能列表过时、用户反馈揭示能力缺口、工具需求发生变化、需要在原版 旁边创建高级变体，或智能体在实际使用后需要范围优化时。

pjt222 Skill

Separate expensive observation from cheap decision-making in autonomous agent loops using a two-clock architecture. A fast clock accumulates data into a digest file; a slow clock reads the digest and acts only when something is pending. Idle cycles cost nothing because the action clock returns immediately after reading an empty digest. Use when building autonomous agents that must observe continuously but can only afford to act occasionally, when API or LLM costs dominate and most cycles have nothing to do, when designing cron-based agent architectures with observation and action phases, or when an existing heartbeat loop is too expensive because it calls the LLM on every tick.

pjt222 Skill

AI systematic knowledge acquisition from unfamiliar territory — deliberate model-building w/ feedback loops. Spaced repetition → AI reasoning: survey, hypothesize, probe, integrate, verify, consolidate. Use when encountering unfamiliar codebase / domain, user asks topic requiring investigation not recall, conflicting sources require coherent model, or preparing to teach.

pjt222 Skill

Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.

pjt222 Skill

Create a new team composition file following the agent-almanac team template and registry conventions. Covers team purpose definition, member selection, coordination pattern choice, task decomposition design, machine-readable configuration block, registry integration, and README automation. Use when defining a multi-agent workflow, composing agents for a complex review process, or creating a coordinated group for recurring collaborative tasks.

holobiomicslab Skill

Use when you have raw mass spectra (e.g., from NIST 2017 or MassBank) and need to prepare them for Word2vec embedding or other token-based neural models. Use it as a preprocessing step before training spectral embedding models, especially when scale and accuracy of spectrum matching are priorities.

holobiomicslab Skill

Use when you have a formula-assigned dataset from FT-ICR MS or other mass spectrometry with molecular formulas assigned to each mass feature, and you want to identify and quantify the molecular transformations (e.

holobiomicslab Skill

Use when you have added or modified user-facing parameters to a model class (such as L1/L2 regularization in SiameseModel), written unit tests to verify the new functionality, and need to communicate these changes to users and maintain a historical record.

holobiomicslab Skill

Use when when you have validated link annotations from multiple independent datasets (≥2), individual scoring functions with per-dataset enrichment p-values, and you want to test whether a combined scoring strategy (e.

holobiomicslab Skill

Use when you have nuclear magnetic resonance (NMR) peak data (1H and 13C measurements) that you need to classify using a deployed SMART 3 model, and you want to submit peaks programmatically rather than through a web UI.

holobiomicslab Skill

Use when when you have a neural network or machine learning model with multiple tunable hyperparameters (layer size, regularization strength, dropout) or design choices (e.

holobiomicslab Skill

Use when you have a generic constraint-based metabolic model (SBML format) and cross-sectional omics data (RNA-seq, intracellular metabolomics, YSI or bioanalyzer extracellular flux measurements) for multiple biological samples and need to create sample-specific models that discriminate whether.

holobiomicslab Skill

Use when when training a deep neural network on paired MS/MS spectra to predict structural similarity scores, especially when the training dataset is moderate-sized (109,734 spectra across 15,062 molecules) and overfitting risk is high.

holobiomicslab Skill

Use when you have a collection of preprocessed tandem mass spectra (binned into 10,000 equally-sized m/z bins, intensities square-root transformed, top 1,000 peaks retained), a trained MS2DeepScore Siamese model, and you need to predict structural similarity scores (Tanimoto or Dice) for all or a.

holobiomicslab Skill

Use when you have intracellular metabolomics data paired with constraint-based metabolic model predictions and need to identify metabolically controlled reactions.

holobiomicslab Skill

Use when when you have grouped features consolidated into empirical compounds (EmpCpds) with inferred adduct assignments from khipu, and need to perform MS1-level annotation by matching neutral formulas against JMS-compliant reference libraries (HMDB, LMSD).

holobiomicslab Skill

Use when you have: (1) a trained IOKR model mapping from spectrum kernels to molecular fingerprints, (2) MS2 spectra from your sample, (3) a set of candidate BGCs with known or predicted structures (e.

holobiomicslab Skill

Use when you have developed a new machine learning model for predicting metabolomic profiles from microbiome data and need to quantify its performance improvement over existing methods.

holobiomicslab Skill

Use when you have trained a multitask NMR-to-structure model and need to quantify its predictive accuracy on held-out test molecules.

holobiomicslab Skill

Use when when you have (1) transcriptomics data and a metabolic network model with GPR rules to compute RAS scores; (2) constraint-based model predictions (RPS from optGpSampler or similar) quantifying how gene expression differences translate to flux differences;

pjt222 Skill

AI systematic knowledge acquisition from unfamiliar territory — deliberate model-building with feedback loops. Maps spaced repetition principles to AI reasoning: survey the territory, hypothesize structure, explore with probes, integrate findings, verify understanding, and consolidate for future retrieval. Use when encountering an unfamiliar codebase or domain, when a user asks about a topic requiring genuine investigation rather than recall, when multiple conflicting sources require building a coherent model, or when preparing to teach a topic and deep understanding is required first.

pjt222 Skill

Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.

pjt222 Skill

AI systematic knowledge acquisition from unfamiliar territory — deliberate model-building with feedback loops. Maps spaced repetition principles to AI reasoning: survey the territory, hypothesize structure, explore with probes, integrate findings, verify understanding, and consolidate for future retrieval. Use when encountering an unfamiliar codebase or domain, when a user asks about a topic requiring genuine investigation rather than recall, when multiple conflicting sources require building a coherent model, or when preparing to teach a topic and deep understanding is required first.

pjt222 Skill

Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.

pjt222 Skill

使用双时钟架构在自主代理循环中将昂贵的观察与廉价的决策分离。快时钟将 数据累积到摘要文件中；慢时钟读取摘要并仅在有待办事项时行动。空闲周期 零成本，因为行动时钟在读取空摘要后立即返回。在构建必须持续观察但只能 偶尔行动的自主代理时、当 API 或 LLM 成本占主导且大多数周期无事可做时、 在设计具有观察和行动阶段的基于 cron 的代理架构时，或当现有心跳循环因 每次 tick 调用 LLM 而过于昂贵时使用。

pjt222 Skill

AI systematic knowledge acquisition from unfamiliar territory — deliberate model-building with feedback loops. Maps spaced repetition principles to AI reasoning: survey the territory, hypothesize structure, explore with probes, integrate findings, verify understanding, and consolidate for future retrieval. Use when encountering an unfamiliar codebase or domain, when a user asks about a topic requiring genuine investigation rather than recall, when multiple conflicting sources require building a coherent model, or when preparing to teach a topic and deep understanding is required first.

pjt222 Skill

Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.