Agent skill
save-skill
Save what we just did as a reusable skill. Use at the end of a session to capture a workflow, technique, or process that you want to repeat.
Install this agent skill to your Project
npx add-skill https://github.com/IyadhKhalfallah/clauditor/tree/main/src/skills/save-skill
SKILL.md
The user wants to save what was done in this session as a reusable Claude Code skill.
Steps
-
Review the session: Look at what was accomplished — the tools used, files modified, commands run, and the overall workflow.
-
Identify the reusable pattern: What was the core workflow or technique? Strip away project-specific details and extract the generalizable process.
-
Ask the user:
- "What should this skill be called?" (suggest a name based on what was done)
- "Should this be a project skill (.claude/skills/) or a personal skill (~/.claude/skills/)?"
- "Should only you be able to invoke it, or should Claude use it automatically when relevant?"
-
Create the skill: Write the SKILL.md file with:
- YAML frontmatter: name, description, and
disable-model-invocation: trueif user-only - Clear step-by-step instructions based on what was done
- Use
$ARGUMENTSfor any variable parts (file names, branch names, etc.) - Keep it under 500 lines — move detailed reference to supporting files if needed
- YAML frontmatter: name, description, and
-
Verify: Show the user the created skill and explain how to invoke it with
/skill-name.
Example output
If the session involved setting up a new API endpoint:
.claude/skills/new-endpoint/SKILL.md
---
name: new-endpoint
description: Scaffold a new REST API endpoint with tests and documentation
disable-model-invocation: true
---
Create a new API endpoint for $ARGUMENTS:
1. Create the route handler in src/routes/
2. Add request/response validation schemas
3. Write integration tests
4. Update the API documentation
5. Run tests to verify
Important
- Don't include project-specific file paths — use patterns like "src/routes/" not "/Users/alice/myproject/src/routes/"
- Include any commands that should be run (test, lint, build)
- If the workflow has multiple variants, use $ARGUMENTS to parameterize
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?