ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
using-serena-for-exploration
Use when exploring codebases with Serena MCP tools for architectural understanding and pattern discovery - guides efficient symbolic exploration workflow minimizing token usage through targeted symbol reads, overview tools, and progressive narrowing
majiayu000/claude-skill-registry 163
-
74-mid-session-save-150
[74] CLOSE. Quick checkpoint during active work when context is running low. Use multiple times per development cycle to preserve progress and lessons. Lighter than close-session — no full handoff needed. Triggers on 'save progress', 'checkpoint', 'context low', or automatically when nearing token limits.
majiayu000/claude-skill-registry 163
-
moai-alfred-rules
Alfred SuperAgent의 필수 규칙을 정의합니다. November 2025 enterprise standard 기반. 3-Layer architecture, 4-Step workflow, Agent-first paradigm, Skill invocation rules, AskUserQuestion patterns, TRUST 5 quality gates, TAG chain integrity, commit message standards. 사용: 워크플로우 규칙 검증, 품질 게이트 확인, MoAI-ADK 표준 준수, 아키텍처 규칙 검증.
majiayu000/claude-skill-registry 163
-
dart-remove-roots
To remove previously registered Dart project roots, revoke tool access by removing those roots.
majiayu000/claude-skill-registry 163
-
coderabbit
AI-powered code review using CodeRabbit CLI and GitHub integration. Use when running local code reviews before commits ("run coderabbit", "review my changes"), configuring .coderabbit.yaml files, integrating CodeRabbit with Claude Code for autonomous review workflows, using @coderabbitai commands in pull requests, or setting up automated code review pipelines.
majiayu000/claude-skill-registry 163
-
moai-domain-devops
Enterprise DevOps with Kubernetes 1.31, Docker 27.x, Terraform 1.9, GitHub Actions, monitoring with Prometheus/Grafana, and cloud-native architectures
majiayu000/claude-skill-registry 163
-
ansible-error-handling
This skill should be used when implementing error handling in Ansible, using block/rescue/always patterns, creating retry logic with until/retries, handling expected failures gracefully, or providing clear error messages with assert and fail.
majiayu000/claude-skill-registry 163
-
Visionary Team
Strategic AI council for product vision, innovation, and future planning
majiayu000/claude-skill-registry 163
-
webhook-receiver-hardener
Secures webhook receivers with signature verification, retry handling, deduplication, idempotency keys, and error responses. Provides verification code, dedupe storage strategy, runbook for incidents. Use when implementing "webhooks", "webhook security", "event receivers", or "third-party integrations".
majiayu000/claude-skill-registry 163
-
bio-workflow-management-nextflow-pipelines
Create scalable, containerized bioinformatics pipelines with Nextflow DSL2 supporting Docker, Singularity, and cloud execution. Use when building portable pipelines with container support, running workflows on cloud platforms (AWS, Google Cloud), or leveraging nf-core community pipelines.
majiayu000/claude-skill-registry 163
-
boost-union-config
Configure Moodle Boost Union theme settings and customizations. Use when theming Moodle, configuring layouts, or customizing Boost Union features.
majiayu000/claude-skill-registry 163
-
Global Tech Stack
Reference and maintain the project's technical stack including frameworks, languages, databases, testing tools, and third-party services to ensure consistency across the project. Use this skill when making technology choices, adding new dependencies, configuring frameworks, or ensuring consistency with existing stack decisions. When setting up new features that need to align with the project's chosen technologies. When documenting or updating the tech stack. This skill applies when working with any technology-specific configuration, framework setup, or when making architectural decisions about tools and libraries.
majiayu000/claude-skill-registry 163
-
codex-skills-index
Entry point for Codex-discoverable skills used by the Run-Smart AI coach.
majiayu000/claude-skill-registry 163
-
k-docs
Index of Mechanic documentation with summaries and links. Load this to understand what documentation exists and where to find detailed information on specific topics. Triggers: docs, documentation, reference, guide, help.
majiayu000/claude-skill-registry 163
-
rag-architecture
Use when building retrieval-augmented generation systems. Covers chunking strategies, embedding models, vector databases, retrieval patterns, and hybrid search. Apply when adding knowledge bases, document Q&A, or semantic search to applications.
majiayu000/claude-skill-registry 163
-
comp-scout-scrape
Scrape competition websites, extract structured data, and auto-persist to GitHub issues. Creates issues for new competitions, adds comments for duplicates.
majiayu000/claude-skill-registry 163
-
ci-cd-reviewer
WHEN: CI/CD pipeline review, GitHub Actions, GitLab CI, Jenkins, build optimization
WHAT: Pipeline structure + Job optimization + Security scanning + Caching strategy + Deployment patterns
WHEN NOT: Kubernetes → k8s-reviewer, Terraform → terraform-reviewer
majiayu000/claude-skill-registry 163
-
context-optimizer
Automatically optimizes context window usage when filling up (>70%). Uses hierarchical summarization, selective file loading, and intelligent compaction to maintain conversation quality while reducing token count by 60-80%. Proactively activates to prevent context overflow.
majiayu000/claude-skill-registry 163
-
agent-definition-creation
Use this skill when creating or refining Claude Code sub-agent definitions. Helps design specialized AI assistants with proper YAML frontmatter, system prompts, tool access, and example-driven descriptions. Automatically invoked when user requests "create an agent", "design a sub-agent", "make a specialist", or mentions agent development. Ensures agents follow Anthropic best practices with focused responsibilities, discovery-optimized descriptions, and proper tool restrictions.
majiayu000/claude-skill-registry 163
-
concept-critic
Rigorously critique concept designs through intellectual scrutiny. This skill should be used when validating concept definitions, reviewing concept quality, identifying design flaws, or evaluating whether something qualifies as a true concept. Applies demanding standards from Daniel Jackson's methodology. Handles queries like "critique this concept", "is this a good concept", "review my concept design", "does this meet concept criteria".
majiayu000/claude-skill-registry 163
-
clojure-babashka-json
babashka.json is a cross-platform JSON abstraction for Clojure/babashka. Use when working with JSON parsing, serialization, or writing portable code that runs on both JVM and babashka.
majiayu000/claude-skill-registry 163
-
bewirtungsbeleg
Creates German tax-compliant entertainment expense receipts (Bewirtungsbelege) from restaurant receipts with automatic signature and original receipt attachment. The generated PDF contains the original receipt as page 1 and the signed Bewirtungsbeleg as page 2. Use when the user uploads a restaurant receipt/bill and wants to create a formal Bewirtungsbeleg PDF for German tax purposes, or when they mention "Bewirtungsbeleg", "Geschäftsessen", "steuerlich absetzbar", or similar business meal expense documentation needs.
majiayu000/claude-skill-registry 163
-
abaqus-thermal-analysis
Complete workflow for heat transfer analysis - steady-state and transient thermal. Use when user asks about temperature distribution, conduction, convection, or heat flow.
majiayu000/claude-skill-registry 163
-
posting-instagram
Post content to Instagram using Meta Graph API.
Use when publishing Instagram posts, managing media, getting insights,
or optimizing hashtags. Requires Instagram Business Account.
NOT when posting to Facebook (use posting-facebook instead).
majiayu000/claude-skill-registry 163