數據與 AI

Update index.json status. Use for: upsert index.json, update status/last_flow/updated_at. Deterministic writes - stable diffs, no creation. Use only in run-prep and *-cleanup agents. Invoke via bash .claude/scripts/demoswarm.sh index upsert-status.

Comprehensive development workflow specialist combining TDD, debugging, performance optimization, code review, and quality assurance into unified development workflows

Use when creating custom Bazel rules, toolchains, providers, or aspects. Use when extending Bazel for new languages, build systems, or custom actions. Use when debugging Starlark rule implementations or understanding Bazel build phases.

Automatically invokes init-explorer agent when project context is empty or unknown.

Automatically generate quick descriptive statistics and exploratory data analysis for CSV files with visualizations. Use when a CSV file is uploaded, when analyzing tabular data, when requesting data summaries, or when exploring dataset structure and quality. Proactively runs full analysis without asking questions or offering options.

Use the GitHub gh CLI to inspect pull requests, status checks, and CI failures. Trigger when triaging PRs/CI, fetching workflow logs, or summarizing check results. Prefer explicit --json field lists; avoid deprecated GraphQL fields like projectCards and invalid fields like checks by using statusCheckRollup.

This skill provides comprehensive guidance for learning and using GitHub, from fundamental concepts through practical workflows. Designed for complete beginners, this skill should be used when teaching GitHub concepts, explaining git workflows, debugging git/GitHub issues, or guiding through practical GitHub tasks like creating branches, commits, pull requests, and merging code.

Master MongoDB ACID transactions for multi-document operations. Learn session management, transaction mechanics, error handling, and production patterns. Guarantee data consistency across multiple operations.

Synchronize AI swarms with GitHub Projects for visual task management and progress tracking. Use for project board automation, task synchronization, sprint management, and team coordination with GitHub Projects.

Build tools, CSS architecture, and Git workflows for clemencefouquet.fr WordPress theme. Covers linting, @layer CSS, and sync between Laragon/Git/VPS.

Enterprise Claude Code context window optimization with 2025 best practices: aggressive clearing, memory file management, MCP optimization, strategic chunking, and quality-over-quantity principles for 200K token context windows.

Model fine-tuning with PyTorch and HuggingFace Trainer. Covers datasetpreparation, tokenization, training loops, TrainingArguments, SFTTrainerfor instruction tuning, evaluation, and checkpoint management.

스킬 건강도 진단 및 유지보수 가이드. 500줄 규칙, skill-rules.json 동기화, YAML 검증을 수행합니다.

Expert guidance for writing database migrations using golang-migrate for the mediaz SQLite database. Covers migration creation, testing, rollback capability, data preservation, and mediaz-specific patterns. Activates when users mention migrations, schema changes, database alterations, or golang-migrate.

Testing strategies and patterns (unit, integration, E2E, API tests). TRIGGERS: 'test', 'teste', 'testing', 'E2E', 'integration test', 'unit test', 'test failure'. Use when setting up tests, writing test cases, debugging test failures, implementing test patterns.

Enables AI agents to use Braintrust for LLM evaluation, logging, and observability.Includes scripts for querying logs with SQL, running evals, and logging data.

Design global error handling for the .NET 8 WPF widget host app: unhandled exceptions, UI error surfaces, crash reporting, and user-safe recovery. Use when wiring App.xaml.cs exception hooks, adding error boundaries in ViewModels, or integrating crash reporting services.

Cost Estimation & BOM Generation Agent

プロジェクトの CLAUDE.md を更新する。「CLAUDE.md を更新して」「ルールを追加」「プロジェクトルールを変更」「Claude のルール」「AI ドキュメント更新」「CLAUDE.md に追記」「ルールを編集」などで起動。プロジェクト固有のルールやガイドラインを管理。

This skill should be used when developing, optimizing, testing, or submitting algorithms for The Innovation Game challenges (3-SAT, CVRP, Knapsack). Use it for algorithm development, performance optimization, local testing, dry-run validation, or submission to earn TIG tokens through improved computational algorithms.