Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
software-developer
software-developer skill
Trigger terms: implement, code, development, programming, coding, build feature, create function, write code, SOLID principles, clean code, refactor
Use when: User requests involve software developer tasks.
majiayu000/claude-skill-registry 163
-
mapper-validation
Mapper field validation process ensuring zero missing fields
majiayu000/claude-skill-registry 163
-
b2c-slas
Using the b2c CLI for SLAS (Shopper Login and API Access Service) client management
majiayu000/claude-skill-registry 163
-
workflow-enforcement
Workflow step compliance guidance with mandatory step reminders and visual progress tracking. Reminds Claude to complete all workflow steps before PR creation.
majiayu000/claude-skill-registry 163
-
issue-management-skill
majiayu000/claude-skill-registry 163
-
devops-expert
Expert-level DevOps practices, culture, automation, and continuous delivery
majiayu000/claude-skill-registry 163
-
whatsapp-messaging
Send and read WhatsApp messages via Kapso Meta proxy, manage templates (CRUD/send), and upload media. Use when sending messages, creating templates, or reading inbox history.
majiayu000/claude-skill-registry 163
-
agent-test-delegation
Test agent delegation patterns to verify hierarchy and escalation paths. Use after modifying agent structure.
majiayu000/claude-skill-registry 163
-
input-latency-governance
Achieve and maintain low input latency by engineering event-to-render pipelines.
majiayu000/claude-skill-registry 163
-
OSCP Penetration Testing Methodology
This skill should be used when the user asks to "perform OSCP-style penetration testing", "enumerate network services", "escalate privileges on Windows or Linux", "conduct Active Directory attacks", "transfer files between systems", "crack password hashes", or "execute lateral movement techniques". It provides a comprehensive methodology and command reference for offensive security certification preparation and real-world penetration testing.
majiayu000/claude-skill-registry 163
-
graphql-implementation
Builds GraphQL APIs with schema design, resolvers, error handling, and performance optimization using Apollo or Graphene. Use when creating flexible query APIs, migrating from REST, or implementing real-time subscriptions.
majiayu000/claude-skill-registry 163
-
model-evaluation-benchmark
Automated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3.
Auto-activates for model benchmarking, comparison evaluation, or performance testing between AI models.
majiayu000/claude-skill-registry 163
-
spark-engineer
Use when building Apache Spark applications, distributed data processing pipelines, or optimizing big data workloads. Invoke for DataFrame API, Spark SQL, RDD operations, performance tuning, streaming analytics.
majiayu000/claude-skill-registry 163
-
Debugging
Systematic debugging framework ensuring root cause investigation before fixes. Includes four-phase debugging process, backward call stack tracing, multi-layer validation, and verification protocols. Use when encountering bugs, test failures, unexpected behavior, performance issues, or before claiming work complete. Prevents random fixes, masks over symptoms, and false completion claims.
majiayu000/claude-skill-registry 163
-
quality-fixer
Automatically apply safe quality fixes including formatting (Black, isort), linting (Ruff auto-fixes), and resolve formatter conflicts. Use when quality checks fail or before committing code.
majiayu000/claude-skill-registry 163
-
go
Write Go code following best practices. Use when developing Go applications. Covers error handling, concurrency, and project structure.
majiayu000/claude-skill-registry 163
-
additional-htmx-and-flask-instructions
Provides additional instructions for HTMX and Flask, primarily related to templating.
majiayu000/claude-skill-registry 163
-
domain-storytelling
Collaborative domain modeling through pictographic stories. Use when gathering requirements, understanding business workflows, onboarding team members, or preparing for event storming. Follows Stefan Hofer & Henning Schwentner's methodology with actors, work objects, and activities.
majiayu000/claude-skill-registry 163
-
executing-plans-review
Verification, drift detection, and snapshot logic for executing-plans
majiayu000/claude-skill-registry 163
-
plan
Create PLAN.md file with phase-based breakdown for issues. Use after creating an issue with /issue to break down work into phases.
majiayu000/claude-skill-registry 163
-
design-of-experiments
Expert guidance for Design of Experiments (DOE) in Python - interactive goal-driven design selection, classical DOE (factorial, response surface, screening), Bayesian optimization with Gaussian processes, model-driven optimal designs, active learning, and sequential experimentation; includes pyDOE3, pycse, GPyOpt, scikit-optimize, statsmodels
majiayu000/claude-skill-registry 163
-
legacy-audit
技術的負債を評価
majiayu000/claude-skill-registry 163
-
when-releasing-new-product-orchestrate-product-launch
majiayu000/claude-skill-registry 163
-
standup
USE WHEN: returning to a project after time away (1 day to 30 days), needing project status briefing, understanding where work left off, determining next steps.
DO NOT USE WHEN: actively working on a known task, not in a git repository, or when specific file/code questions are asked.
majiayu000/claude-skill-registry 163