Browse Skills

evaluation-harness.md

2

1 export evaluation-harness

2 from "patricio0312rev/skillset"

3 Builds repeatable evaluation systems with golden datasets, scoring rubrics, pass/fail thresholds, and regression reports. Use for "LLM evaluation", "testing AI systems", "quality assurance", or "model benchmarking".

2026-01-05

project-metadata-builder.md

2

1 export project-metadata-builder

2 from "brianclaridge/.claude"

3 Build and update project metadata registry in ${CLAUDE_PROJECTS_YML_PATH}. Use when starting a session, after project analysis, when user says "update project metadata", "refresh projects", "register project", or when project-analysis agent completes analysis.

2026-01-05

monitoring-database-health.md

2

1 export monitoring-database-health

2 from "jeremylongshore/claude-code-plugins-nixtla"

3 This skill enables Claude to monitor database health using real-time metrics, predictive alerts, and automated remediation. It's designed for production-grade database health monitoring for PostgreSQL and MySQL, detecting performance degradation, resource exhaustion, and replication issues. Use this skill when the user requests to monitor database health, check database performance, receive database alerts, or automate database remediation. The skill is triggered by phrases like "check database health", "monitor database performance", "database health check", or "/health-check".

2026-01-05

stack-audit.md

2

1 export stack-audit

2 from "Euda1mon1a/Autonomous-Assignment-Program-Manager"

3 Comprehensive stack health audit for codebase and infrastructure. Runs 10 health checks covering frontend, backend, migrations, Docker, API integrity, and backup status. Use routinely to prevent "time loops" from accumulated issues.

2026-01-05

systematic-debugging.md

2

1 export systematic-debugging

2 from "third774/dotfiles"

3 Four-phase debugging framework with root cause tracing - understand the source before proposing fixes. Use when investigating bugs, errors, unexpected behavior, or failed tests.

2026-01-05

form-ux-patterns.md

2

1 export form-ux-patterns

2 from "Bbeierle12/Skill-MCP-Claude"

3 UX patterns for complex forms including multi-step wizards, cognitive chunking (5-7 fields max), progressive disclosure, and conditional fields. Use when building checkout flows, onboarding wizards, or forms with many fields.

2026-01-05

ousterhout-principles.md

2

1 export ousterhout-principles

2 from "phrazzld/claude-config"

3 Apply Ousterhout's software design principles: detect shallow modules, information leakage, and complexity red flags. Use when reviewing code, designing modules, refactoring, or discussing architecture.

2026-01-05

cost-latency-optimizer.md

2

1 export cost-latency-optimizer

2 from "patricio0312rev/skillset"

3 Reduces LLM costs and improves response times through caching, model selection, batching, and prompt optimization. Provides cost breakdowns, latency hotspots, and configuration recommendations. Use for "cost reduction", "performance optimization", "latency improvement", or "efficiency".

2026-01-05

tdd-enforcement-algorithm.md

2

1 export tdd-enforcement-algorithm

2 from "cipherstash/cipherpowers"

3 Algorithmic decision tree enforcing test-first development via boolean conditions instead of imperatives

2026-01-05

core-web-vitals-tuner.md

2

1 export core-web-vitals-tuner

2 from "patricio0312rev/skillset"

3 Systematically improves Largest Contentful Paint (LCP), Interaction to Next Paint (INP), and Cumulative Layout Shift (CLS) with prioritized fixes and verification. Use for "Core Web Vitals", "performance", "LCP", "INP", or "CLS".

2026-01-05

error-message-design.md

2

1 export error-message-design

2 from "daishiman/AIWorkflowOrchestrator"

3 ユーザーフレンドリーなエラーメッセージの設計を専門とするスキル。エラーコード体系、多言語対応（i18n）、アクション指向のメッセージ設計を提供。Anchors:- The Pragmatic Programmer / 適用: 実践的改善 / 目的: 品質維持- Nielsen Norman Group UX Guidelines / 適用: エラーメッセージ設計 / 目的: ユーザビリティ向上Trigger:Use when designing error messages, creating error code systems, implementing i18n for errors, or building user-friendly error responses.error message, error code, i18n, user-friendly, validation error, API error response

2026-01-05

instruction-clarity.md

2

1 export instruction-clarity

2 from "daishiman/AIWorkflowOrchestrator"

3 曖昧な指示を明確・具体的・実行可能な形式へ変換するスキル。「適切に」「よろしく」といった不明瞭な表現を、測定可能な成功基準と段階的ステップへ分解します。Anchors:• Made to Stick (Heath) / 適用: 簡潔性・具体性の原則 / 目的: 記憶に残る指示設計• The Pyramid Principle (Minto) / 適用: 論理構造 / 目的: 結論先行による理解速度向上• 5C Principle / 適用: 品質評価 / 目的: Clear, Concise, Complete, Concrete, CorrectTrigger:Use when instructions contain vague terms like "appropriately", "properly", "handle", or when steps lack clear success criteria. Apply before creating prompts, requirements, runbooks, or directive documentation.instruction clarity, vague expression, 5C principle, pyramid principle, success criteria

2026-01-05

fairdb-backup-manager.md

2

1 export fairdb-backup-manager

2 from "jeremylongshore/claude-code-plugins-nixtla"

3 Automatically manages PostgreSQL backups with pgBackRest and Wasabi S3 storage when working with FairDB databases

2026-01-05

requirements-verification.md

2

1 export requirements-verification

2 from "daishiman/AIWorkflowOrchestrator"

3 要件検証の専門スキル。要件の完全性・一貫性・実現可能性・検証可能性を体系的に評価し、品質を保証する。品質チェックリストと検証スクリプトを用いて、レビュー結果の整理と改善提案まで行う。Anchors:• Software Requirements (Karl Wiegers) / 適用: 要件検証全体 / 目的: 完全性・一貫性・実現可能性の評価• IEEE 830 SRS Standard / 適用: 要件品質基準 / 目的: 検証可能な構造化• Don't Make Me Think (Steve Krug) / 適用: ユーザー要件 / 目的: ユーザビリティ視点の確認Trigger:Use when verifying requirements quality, checking consistency/completeness, assessing feasibility, or drafting verification reports.requirements verification, requirements quality, consistency check, completeness check, feasibility assessment, 要件検証, 要件レビュー

2026-01-05

scanning-for-xss-vulnerabilities.md

2

1 export scanning-for-xss-vulnerabilities

2 from "jeremylongshore/claude-code-plugins-nixtla"

3 This skill enables Claude to automatically scan for XSS (Cross-Site Scripting) vulnerabilities in code. It is triggered when the user requests to "scan for XSS vulnerabilities", "check for XSS", or uses the command "/xss". The skill identifies reflected, stored, and DOM-based XSS vulnerabilities. It analyzes HTML, JavaScript, CSS, and URL contexts to detect potential exploits and suggests safe proof-of-concept payloads. This skill is best used during code review, security audits, and before deploying web applications to production.

2026-01-05

testing-skills-with-subagents.md

2

1 export testing-skills-with-subagents

2 from "cipherstash/cipherpowers"

3 Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes

2026-01-05

performing-regression-analysis.md

2

1 export performing-regression-analysis

2 from "jeremylongshore/claude-code-plugins-nixtla"

3 This skill empowers Claude to perform regression analysis and modeling using the regression-analysis-tool plugin. It analyzes datasets, generates appropriate regression models (linear, polynomial, etc.), validates the models, and provides performance metrics. Use this skill when the user explicitly requests regression analysis, prediction based on data, or mentions terms like "linear regression," "polynomial regression," "regression model," or "predictive modeling." This skill is also helpful when the user needs to understand the relationship between variables in a dataset.

2026-01-05

following-plans.md

2

1 export following-plans

2 from "cipherstash/cipherpowers"

3 Algorithmic decision tree for when to follow plan exactly vs when to report BLOCKED - prevents scope creep and unauthorized deviations

2026-01-05

docker-containerization.md

2

1 export docker-containerization

2 from "Euda1mon1a/Autonomous-Assignment-Program-Manager"

3 Docker development and container orchestration expertise. Use when creating Dockerfiles, docker-compose configurations, debugging container issues, optimizing images, or setting up isolated development environments. Integrates with CI/CD workflows and security scanning.

2026-01-05

karpenter.md

2

1 export karpenter

2 from "cosmix/claude-code-setup"

3 Kubernetes node autoscaling with Karpenter for efficient cluster scaling. Use when implementing node provisioning, consolidation, spot instance handling, or optimizing compute costs. Triggers: karpenter, node autoscaling, provisioner, nodepool, spot instances, cluster autoscaling, node consolidation.

2026-01-05

configuring-auto-scaling-policies.md

2

1 export configuring-auto-scaling-policies

2 from "jeremylongshore/claude-code-plugins-nixtla"

3 This skill configures auto-scaling policies for applications and infrastructure. It generates production-ready configurations based on user requirements, implementing best practices for scalability and security. Use this skill when the user requests help with auto-scaling setup, high availability, or dynamic resource allocation, specifically mentioning terms like "auto-scaling," "HPA," "scaling policies," or "dynamic scaling." This skill provides complete configuration code for various platforms.

2026-01-05

release.md

2

1 export release

2 from "Codename-11/Stash-Downloader"

3 Create a new version release with git tag and GitHub Release. Use when user asks to release, publish, create a new version, or ship a release. (project)

2026-01-05

python.md

2

1 export python

2 from "joeyagreco/dotfiles"

3 Guidelines when creating, reading, updating, or deleting Python code

2026-01-05

global-validation.md

2

1 export global-validation

2 from "adigunners/adigunners.github.io"

3 Validate data structures, user inputs, and loaded content to ensure the static website operates correctly. Use this skill when verifying JSON data integrity, validating form inputs, and ensuring DOM elements exist before manipulation.

2026-01-05