Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
startup-trend-prediction
Analyze 2-3 year historical trends in technology, market, and business models to predict 1-2 years ahead. Uses pattern recognition, adoption curves, and cycle analysis to identify timing windows and emerging opportunities. History is cyclical - products and markets follow predictable patterns.
majiayu000/claude-skill-registry 163
-
cms-content-pipeline
Master the Firestore CMS integration - content generation scripts, field mapping, and safe content modification patterns
majiayu000/claude-skill-registry 163
-
temporary-license-expert
Expert in temporary license agreements for very short-term occupancy (1 day to 3 months) that avoid creating landlord-tenant relationships. Use when drafting licenses for film shoots, pop-up retail, event space, interim occupancy during renovations, meeting room bookings, or testing space before committing to a lease. Also use when analyzing whether arrangement is truly a license vs lease, structuring revocable occupancy rights, or evaluating holdover and termination provisions. Key terms include license vs lease, temporary occupancy, short-term license, no landlord-tenant relationship, revocable, non-exclusive, film production license, pop-up retail, interim occupancy, no statutory protections
majiayu000/claude-skill-registry 163
-
python-data-engineering
Comprehensive Python data engineering patterns for AWS Data Lake, including PySpark, Pandas, Apache Airflow, AWS Glue, ETL pipelines, data quality, schema management, performance optimization, FastAPI services, streaming with Kafka/Kinesis, data validation with Great Expectations, testing strategies, error handling, logging, and production deployment on AWS EMR and Glue.
majiayu000/claude-skill-registry 163
-
screen-spec-guide
画面ID（SAPP-CTG-030 など）から仕様・ワイヤーフレーム・Figma ノードを特定し、関連ドキュメントや画面遷移を横断して確認したいときに使います。docs/2-requirements/24-画面一覧.csv・23-画面設計.md・assets/*.svg・figma・docs/3-external/31-画面遷移図.md を参照して要件を整理する用途を想定しています。
majiayu000/claude-skill-registry 163
-
squarespace
Squarespace API and design system integration
majiayu000/claude-skill-registry 163
-
type-checker-tests
Add integration tests for type checker inference and checking functions
majiayu000/claude-skill-registry 163
-
job-posting-intelligence
Detect when companies are hiring transportation managers as a 90-120 day leading indicator of upcoming RFPs. Use when finding companies about to issue RFPs, analyzing job postings for freight opportunities, or creating outreach campaigns based on hiring signals.
majiayu000/claude-skill-registry 163
-
powerful-framework
Applies the POWERFUL deal qualification framework to analyze sales opportunities. Use this skill when qualifying deals, assessing opportunity strength, identifying gaps in deal intelligence, or coaching sales teams on deal execution.
majiayu000/claude-skill-registry 163
-
using-pmm-team
7 product marketing skills + 6 specialist agents for go-to-market strategy,
positioning, messaging, competitive intelligence, and launch coordination.
majiayu000/claude-skill-registry 163
-
review
GitHub issueの対応内容をレビューし、改善タスクを作成します。専門家エージェント（coding/architecture/testing/document-specialist）によるレビューを実施し、指摘点を元にtmp/todoフォルダにタスクファイルを作成します。
majiayu000/claude-skill-registry 163
-
radulator-qa-tester
Automated QA testing for Radulator's 18 medical calculators across radiology, hepatology/liver, and urology specialties. Tests accuracy, collects browser diagnostics, generates Playwright tests, and manages three-branch Git workflow (dev1→test1→main). Use when testing Radulator calculators, reviewing PRs with qa label, verifying medical formulas, generating test reports, or creating comprehensive test suites.
majiayu000/claude-skill-registry 163
-
ctx:performance
Analyze and optimize parallel workflow performance. Use when users report slow parallel execution, want to improve speed, or need performance analysis. Activate for questions about bottlenecks, time savings, optimization opportunities, or benchmarking parallel workflows.
majiayu000/claude-skill-registry 163
-
large-instructions-skill
A skill with large instructions for performance testing
majiayu000/claude-skill-registry 163
-
medium-skill
Medium-sized skill for comprehensive token testing
majiayu000/claude-skill-registry 163
-
log-reader
Read MetaTrader 5 log files. TRIGGERS - MT5 logs, Experts pane, indicator errors, compilation errors.
majiayu000/claude-skill-registry 163
-
justfile-advanced-patterns
Level 3 patterns - test-smart, deploy, migrate, logs, status (production systems)
majiayu000/claude-skill-registry 163
-
clerk-auth-expert
Expert in Clerk authentication for React Native/Expo apps. Handles user authentication, session management, protected routes, and integration with backend services.
majiayu000/claude-skill-registry 163
-
web-test-wallet-setup
Set up MetaMask wallet extension for Web3 DApp testing - download extension, import wallet from private key. Run at test start if tests/config.yaml has web3.enabled=true.
majiayu000/claude-skill-registry 163
-
ab-test-calculator
Calculate statistical significance for A/B tests. Sample size estimation, power analysis, and conversion rate comparisons with confidence intervals.
majiayu000/claude-skill-registry 163
-
Delegating to Jira Agent
Recognize Jira queries and delegate to specialized sub-agent to avoid context pollution
majiayu000/claude-skill-registry 163
-
proof-of-work
Enforces "prove before claim" discipline - validation, testing, and evidence
requirements before declaring work complete.
Triggers: completion, finished, done, working, should work, configured,
ready to use, implemented, fixed
Use when: claiming ANY work is complete, recommending solutions, stating
something will work, finishing implementations
DO NOT use when: explicitly asking questions or requesting clarification
DO NOT use when: work is clearly in-progress and not claiming completion
CRITICAL: This skill is MANDATORY before any completion claim. Violations
result in wasted time and eroded trust.
majiayu000/claude-skill-registry 163
-
validate-run
Validate all checkpoints from an agent run directory in parallel. Spawns test-validator agents for each checkpoint and summarizes results. Invoke with /validate-run <run_path> [problem].
majiayu000/claude-skill-registry 163
-
e2e-test-agent
Generates end-to-end tests for complete user workflows
majiayu000/claude-skill-registry 163