skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
independent-research
Research-driven investigation skill for validating solutions and exploring documentation. Never ask questions you can answer yourself through research. Use WebFetch, WebSearch, and testing to validate ideas before presenting them. Deliver concrete, tested recommendations with evidence.
author-skills
Write SKILL.md for the user using all available wisdom and documented guidance about how Agent Skills are made. New skills are written carefully to be orthogonal to the existing skills in the same repo.
semantic-translation
This skill should be used when the user uses ambiguous terminology like "make it talk", "we need an api", "make it portable", "check for gaps", asks meta-questions like "am I making sense?", "does this make sense?", mentions being a "non-technical user", uses vague action verbs ("make it work", "do the thing"), mixes domain languages, uses invented terms, or when detecting semantic drift between human natural language and technical precision. Provides semantic translation, disambiguation, and domain knowledge mapping across Autogen, Langroid, MCP (Model Context Protocol), UTCP (Universal Tool Calling Protocol), FastAPI, Git/Gitflow, SRE (Site Reliability Engineering), and Memory Graphs domains. Bridges the gap between user intent and technical specificity through ontological translation.
github-actions-claude
Setup and troubleshoot GitHub Actions workflows using anthropics/claude-code-action for automated PR reviews. Use when creating CI/CD workflows that leverage Claude for code review, research validation, or automated feedback.
gitterflow
Spawn and coordinate parallel Claude Code sub-agents using git worktrees. Use this skill when you need to parallelize work across multiple independent tasks, delegate subtasks to sub-agents, or orchestrate complex multi-part implementations.
troubleshooting-gpt-oss-and-vllm-errors
Use when diagnosing openai_harmony.HarmonyError or gpt-oss tool calling issues with vLLM. Identifies error sources (vLLM server vs client), maps specific error messages to known GitHub issues, and provides configuration fixes for tool calling problems with gpt-oss models.
axolotl-config-management
Create, validate, and debug YAML training configurations for axolotl-rs fine-tuning
exps-logistic
Documentation for the logistic regression MI estimation experiment (exps_logistic)
recommendation-ml
ML recommendation system development with collaborative filtering (Matrix Factorization), content-based filtering, and hybrid approaches. Use when building recommendation models, implementing Feast feature stores, setting up MLflow model registry, handling cold-start problems for new users/products, implementing diversity with MMR algorithm, or adding exploration with Thompson Sampling/epsilon-greedy bandits.
clearml-architect
Recognize/Describe clearML architecture and extension points
supabase-setup
Initialize Supabase locally, manage database migrations, and configure Row Level Security. Use when setting up databases, creating tables, or managing schemas.
monthly-migration
Perform monthly journal migration using hledger close --migrate to close the previous month and open the new month with proper balance assertions and account initialization.
sync-docs
Updates schema documentation to synchronize with live database state after migrations or schema changes, preventing documentation drift by querying actual table structures, column definitions, and constraints to update VERIFIED_TABLE_NAMES.md and schema reference files. Use this skill when: (1) After applying database migrations to sync docs with new schema, (2) After pulling migrations from git to update local documentation, (3) When documentation seems outdated or incorrect, (4) Before writing SQL to verify current table names and structure, or (5) To ensure single source of truth between database and documentation
supabase-db-model
Chuẩn hoá cách đọc/viết DB model Supabase (migrations + TS types + services) trong repo này.
docker-compose-dev
Run mjr.wtf locally using Docker Compose (SQLite), including migrations, logs, and teardown.
database-migrations
Create, apply, and rollback goose migrations for SQLite using the embedded migrate tool.
supabase-mcp
Workflow chuẩn khi làm việc với Supabase (DDL/migrations, query/debug, RLS policies) cho repo này.