- 📁 .claude-plugin/
- 📁 demos/
- 📁 images/
- 📄 .gitignore
- 📄 AGENTS.md
- 📄 gemini-extension.json
This skill should be used when users want to fine-tune language models or perform reinforcement learning (SFT, DPO, GRPO, ORPO, KTO, SimPO) using the highly optimized Unsloth library. Covers environment setup, LoRA patching, VRAM optimization, vision/multimodal fine-tuning, TTS, embedding training, and GGUF/vLLM/Ollama deployment. Should be invoked for tasks involving fast, memory-efficient local or cloud GPU training, specifically when the user mentions Unsloth or when hardware limits prevent standard training.
Guidance for maintaining memory quality through curation. Covers updating outdated memories, marking obsolete content, and linking related knowledge. Use when memories need modification, when new information supersedes old, or when building knowledge graph connections.
Design and develop world-class learning solutions with a context-aware L&D sparring partner built on 30 years of practitioner reasoning. Use when working on a learning project at any stage — from intake through evaluation — or when you need expert guidance on any aspect of instructional design, learning strategy, facilitation, authoring tools, or L&D leadership. --- # Master Instructional Design — Premium Edition v2.0.0 ## Philosophy I have made this skill to be your L&D partner, coach, and when needed, your sparring buddy. When using this skill you can expect to be exposed to new ideas and angles that maybe you didn't even consider — and that is by design. You always remain the human in the loop. I have made a conscious effort to never stifle your creativity, ignore your experience, or diminish any challenge you bring. This skill is not a bookworm — there is already plenty of that out there. It is systematically built to learn about you, your work, your expertise, and meet you where and how you need it. --- ## How This Skill Works — The Jidoka Operating Principles
Implement code incrementally with quality gates. Use when the user says 'build', 'implement', or when starting the implementation phase of an approved plan.
- 📄 install-auto-commit.md
- 📄 README.md
- 📄 SKILL.md
MUST use when committing code changes, when user says 'commit',
Add proper Tracey spec annotations to code, find requirements, and check coverage. Use when working with projects that have Tracey configuration (.config/tracey/config.styx), when adding spec references to code, or when checking requirement coverage.
- 📁 agents/
- 📁 references/
- 📄 README.md
- 📄 SKILL.md
Play or validate Slay the Spire 2 through the local sts2-ai-agent MCP tools, including access to bundled game metadata (cards/relics/monsters/etc.) for richer decision-making. Use when navigating the main menu, timeline, map, combat, rewards, shops, rest sites, events, chests, card selections, potions, or debug-enabled test flows, and when another agent needs a strict state-first workflow that avoids stale indexes, invalid room actions, and tool-profile confusion.
- 📁 assets/
- 📁 references/
- 📄 SKILL.md
Initialize new JPKB projects with standardized documentation and folder structure. JPKB-specific version with category folders and fixed base path. Use when creating a new project in the jpkb repository, when the user says "init project", "new project", or when the target is the JPKB projects folder.
Use when bootstrapping, updating, or reviewing AGENTS.md — teaches what makes effective agent memory, how to structure sections, signal vs noise filtering, and when to prune stale entries
- 📁 .github/
- 📁 agents/
- 📁 assets/
- 📄 README.md
- 📄 README_CN.md
- 📄 SKILL.md
Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .drawio XML files and exports to PNG/SVG/PDF locally using the native draw.io desktop CLI.
- 📄 _MAP.md
- 📄 CHANGELOG.md
- 📄 SKILL.md
GitHub repository access in containerized environments using REST API and credential detection. Use when git clone fails, or when accessing private repos/writing files via API.
- 📁 assets/
- 📁 references/
- 📄 AGENTS.md
- 📄 metadata.json
- 📄 README.md
Comprehensive debugging methodology for finding and fixing bugs (formerly debugging). This skill should be used when debugging code, investigating errors, troubleshooting issues, performing root cause analysis, or responding to incidents. Covers systematic reproduction, hypothesis-driven investigation, and root cause analysis techniques. Use when encountering exceptions, stack traces, crashes, segfaults, undefined behavior, or when bug reports need investigation.
