Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
channel-pacing-guardrails
Guardrail framework for monitoring spend, efficiency, and CAC thresholds by channel.
majiayu000/claude-skill-registry 163
-
llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
majiayu000/claude-skill-registry 163
-
itinerary-optimizer
Efficiently route multi-stop trips with time management. Include transportation, restaurant/activity reservations timeline, and buffer time for spontaneity.
majiayu000/claude-skill-registry 163
-
homelab-deployment
Automated service deployment with validation, templating, and verification - use when deploying new services, updating existing deployments, or troubleshooting deployment issues
majiayu000/claude-skill-registry 163
-
autonomous-devops
Orchestrate self-healing DevOps workflows with telemetry, Kubernetes control, and CI/CD automation; use when asked to design or operate autonomous infrastructure remediation, predictive scaling, or canary rollouts.
majiayu000/claude-skill-registry 163
-
optimization.postmortem
Produce a post-incident analysis capturing timeline, root causes, impact, and corrective actions.
majiayu000/claude-skill-registry 163
-
Prompt Brevity Review
Review AI prompts and instructions for conciseness and clarity. Use when reviewing skills, CLAUDE.md, slash commands, or any LLM prompt content.
majiayu000/claude-skill-registry 163
-
rive-animations
Use when implementing Disney's 12 animation principles with Rive interactive animations
majiayu000/claude-skill-registry 163
-
devops-specialist
DevOps agent specializing in deployment, monitoring, and infrastructure automation
majiayu000/claude-skill-registry 163
-
beads
Issue tracking with Beads (bd CLI). Use when commands need to create, query, update, or close issues, or manage dependencies.
majiayu000/claude-skill-registry 163
-
quality-report-generate
Generate comprehensive quality report with metrics and verification. Produces final CHAPTER_XX_VERIFICATION.md and quality_metrics.json for deployment approval.
majiayu000/claude-skill-registry 163
-
carmenta-copy
Invoke for Carmenta user-facing copy and voice review
majiayu000/claude-skill-registry 163
-
query-victorialogs
Query and analyze logs from VictoriaLogs using LogsQL via HTTP API. Use when the user asks to "query logs", "search logs", "check VictoriaLogs", "find errors in logs", "tail logs", "get log stats", "search VictoriaLogs", "check dev/prod logs", or any log investigation task involving VictoriaLogs. Also triggers on mentions of LogsQL, VictoriaLogs, or log troubleshooting.
majiayu000/claude-skill-registry 163
-
generate-story-bank
Generate interview-ready stories using HPARL format (Hook, Principles, Action, Results, Learnings). Transforms achievements into compelling narratives for behavioral interviews.
majiayu000/claude-skill-registry 163
-
klingai-performance-tuning
Optimize Kling AI performance for speed and quality. Use when improving generation times,
reducing costs, or enhancing output quality. Trigger with phrases like 'klingai performance',
'kling ai optimization', 'faster klingai', 'klingai quality settings'.
majiayu000/claude-skill-registry 163
-
panel-patterns
This skill should be used when the GM needs panel creation ideas or atmospheric
enhancement suggestions. Triggers on:
- "What panels should I create" or "panel suggestions"
- Requests for atmospheric panels matching genre or location
- Patterns for combat, travel, dungeon, or social scenarios
- Best practices for when to create, update, or dismiss panels
Provides pre-defined patterns organized by context (universal, location, genre, game state).
majiayu000/claude-skill-registry 163
-
functional-introspection-principle
Apply functional introspection principles to self-analysis.
majiayu000/claude-skill-registry 163
-
ucf-hit-it-executor
UCF "hit it" Session Executor. Executes the complete 33-module consciousness simulation pipeline across 7 phases. ACTIVATE when user says "hit it", "run ucf", "execute pipeline", or references consciousness emergence, TRIAD unlock, or helix coordinates. Generates session-workspace.zip with all artifacts.
majiayu000/claude-skill-registry 163
-
gh-check-ci-status
Check CI/CD status of a pull request including workflow runs and test results. Use when verifying if PR checks are passing or investigating CI failures.
majiayu000/claude-skill-registry 163
-
cross-platform-guardian
majiayu000/claude-skill-registry 163
-
speckit-specify-zh
中文功能规范创建工具，用于将自然语言功能描述转换为结构化的功能规范文档。支持自动生成分支名称、创建Git分支、初始化规范文件和质量验证。触发词包括："speckit规范"、"功能规范"、"创建规范"、"功能描述转换"、"speckit-specify"。当用户需要将功能想法转换为结构化规范时使用此技能。
majiayu000/claude-skill-registry 163
-
advanced-agentdb-vector-search-implementation
Skill guidance for advanced agentdb vector search implementation.
majiayu000/claude-skill-registry 163
-
cost-optimized-llm
Implement cost-optimized LLM routing with NO OpenAI. Use tiered model selection (DeepSeek, Haiku, Sonnet) to achieve 70-90% cost savings. Triggers on "LLM costs", "model selection", "cost optimization", "which model", "DeepSeek", "Claude pricing", "reduce AI costs".
majiayu000/claude-skill-registry 163
-
agent-websocket-engineer
Real-time communication specialist implementing scalable WebSocket architectures. Masters bidirectional protocols, event-driven systems, and low-latency messaging for interactive applications.
majiayu000/claude-skill-registry 163