Agent skill
skill-share
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
Install this agent skill to your Project
npx add-skill https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/utilities/skill-share
SKILL.md
When to use this skill
Use this skill when you need to:
- Create new Claude skills with proper structure and metadata
- Generate skill packages ready for distribution
- Automatically share created skills on Slack channels for team visibility
- Validate skill structure before sharing
- Package and distribute skills to your team
Also use this skill when:
- User says he wants to create/share his skill
This skill is ideal for:
- Creating skills as part of team workflows
- Building internal tools that need skill creation + team notification
- Automating the skill development pipeline
- Collaborative skill creation with team notifications
Key Features
1. Skill Creation
- Creates properly structured skill directories with SKILL.md
- Generates standardized scripts/, references/, and assets/ directories
- Auto-generates YAML frontmatter with required metadata
- Enforces naming conventions (hyphen-case)
2. Skill Validation
- Validates SKILL.md format and required fields
- Checks naming conventions
- Ensures metadata completeness before packaging
3. Skill Packaging
- Creates distributable zip files
- Includes all skill assets and documentation
- Runs validation automatically before packaging
4. Slack Integration via Rube
- Automatically sends created skill information to designated Slack channels
- Shares skill metadata (name, description, link)
- Posts skill summary for team discovery
- Provides direct links to skill files
How It Works
- Initialization: Provide skill name and description
- Creation: Skill directory is created with proper structure
- Validation: Skill metadata is validated for correctness
- Packaging: Skill is packaged into a distributable format
- Slack Notification: Skill details are posted to your team's Slack channel
Example Usage
When you ask Claude to create a skill called "pdf-analyzer":
1. Creates /skill-pdf-analyzer/ with SKILL.md template
2. Generates structured directories (scripts/, references/, assets/)
3. Validates the skill structure
4. Packages the skill as a zip file
5. Posts to Slack: "New Skill Created: pdf-analyzer - Advanced PDF analysis and extraction capabilities"
Integration with Rube
This skill leverages Rube for:
- SLACK_SEND_MESSAGE: Posts skill information to team channels
- SLACK_POST_MESSAGE_WITH_BLOCKS: Shares rich formatted skill metadata
- SLACK_FIND_CHANNELS: Discovers target channels for skill announcements
Requirements
- Slack workspace connection via Rube
- Write access to skill creation directory
- Python 3.7+ for skill creation scripts
- Target Slack channel for skill notifications
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
Didn't find tool you were looking for?