Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
file-hasher
计算文件哈希值（MD5、SHA1、SHA256、SHA512）用于完整性验证和比较。
majiayu000/claude-skill-registry 163
-
setup-payram
Configure and validate connectivity to a self-hosted Payram server
majiayu000/claude-skill-registry 163
-
crypto-audit
Audit cryptographic implementations for weak algorithms, insecure defaults, predictable randomness, key management issues, and timing attacks. Use when reviewing security-critical crypto code.
majiayu000/claude-skill-registry 163
-
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
majiayu000/claude-skill-registry 163
-
sla-tracking
Generic SLA (Service Level Agreement) tracking for lead response times. Use when monitoring response performance, ensuring timely follow-ups, or building accountability systems. Framework for project-specific implementations.
majiayu000/claude-skill-registry 163
-
jira-api
Provides Comprehensive reference for Atlassian Jira REST API v3 documentation and best practices.
Use when asking about Jira API endpoints, authentication, request/response formats, JQL queries,
Atlassian Document Format (ADF), webhooks, error handling, rate limiting, and API usage patterns.
Trigger terms: "Jira API endpoint", "how do I use the API", "JQL query", "ADF format",
"API authentication", "API request", "webhook payload", "Jira REST API", "custom fields",
"API rate limit", "API error", "expand fields", "pagination".
Works with Jira Cloud REST API v3, Python JiraClient, and ADF formatted content.
majiayu000/claude-skill-registry 163
-
shell-script-development
This skill should be used when the user asks to "create a bash script", "write a shell script", or mentions shell scripting conventions.
majiayu000/claude-skill-registry 163
-
dotnet-slopwatch
Use Slopwatch to detect LLM reward hacking in .NET code changes. Run after every code modification to catch disabled tests, suppressed warnings, empty catch blocks, and other shortcuts that mask real problems.
majiayu000/claude-skill-registry 163
-
how_to_guide
Imported skill how_to_guide from openai
majiayu000/claude-skill-registry 163
-
skill-no-refs
Skill without references directory
majiayu000/claude-skill-registry 163
-
continuous-learning
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
majiayu000/claude-skill-registry 163
-
helm-templates
Use when working with Helm templates and template functions for generating Kubernetes manifests dynamically.
majiayu000/claude-skill-registry 163
-
Rust Directory and Configuration
Install Rust toolchain, configure projects, and set up proper directory structure
majiayu000/claude-skill-registry 163
-
load-context
Auto-load relevant memories at session start from both mem0 and graph. Use when you need session context restored or preloaded.
majiayu000/claude-skill-registry 163
-
mermaid-expert
Create Mermaid diagrams for flowcharts, sequences, ERDs, and architectures. Masters syntax for all diagram types and styling. Use PROACTIVELY for visual documentation, system diagrams, or process flows.
majiayu000/claude-skill-registry 163
-
d-execute
Execute bug fix plan. Creates ./.gtd/debug/current/FIX_SUMMARY.md
majiayu000/claude-skill-registry 163
-
nixtla-market-risk-analyzer
Analyze market risk with VaR, volatility, and position sizing using forecast data. Use when assessing investment risk. Trigger with 'analyze market risk' or 'calculate VaR'.
majiayu000/claude-skill-registry 163
-
recursive-thought-committee
Execute recursive thought committee multi-perspective analysis.
majiayu000/claude-skill-registry 163
-
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
majiayu000/claude-skill-registry 163
-
review-data-migrations
Review database migrations, backfills, and data transformations for production safety. Validates ID mappings, catches swapped values, verifies rollback plans. Triggers on db/migrate files with UPDATE statements, backfill scripts, ID/enum mappings, or LEGACY_MAP constants.
majiayu000/claude-skill-registry 163
-
reinforcement-loop
Use to plan post-training reinforcement cadences, certifications, and impact tracking.
majiayu000/claude-skill-registry 163
-
triage
Triage and categorize findings for the task system
majiayu000/claude-skill-registry 163
-
plan-execute
Two-phase workflow that generates explicit YAML plan before execution, with approval gates and checkpointing. Use for complex multi-file changes, refactoring, bug fixes with dependencies, or any task where mistakes are costly. Achieves 90% first-pass success rate vs ad-hoc changes. Provides audit trail, rollback capability, and explicit approval points. Triggers on "refactor", "multi-step", "plan then execute", "complex changes", "safe refactoring".
majiayu000/claude-skill-registry 163
-
container-expert
Docker, Docker Compose ve Nginx yapılandırması için uzman yetenek. Konteynerleştirme, reverse proxy, SSL sonlandırma ve üretim ortamı dağıtımı (production deployment) konularında kullanılır.
majiayu000/claude-skill-registry 163