Use when fine-tuning LLMs, training custom models, or optimizing model performance for specific tasks. Invoke for parameter-efficient methods, dataset preparation, or model adaptation.
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →Use when fine-tuning LLMs, training custom models, or optimizing model performance for specific tasks. Invoke for parameter-efficient methods, dataset preparation, or model adaptation.
LLM fine-tuning with LoRA, QLoRA, and instruction tuning for domain adaptation.
finetuning
Complete the current task. Behavior depends on detected mode (MAIN, FEATURE_BRANCH, WORKTREE).
Complete feature development with structured options for merge, PR, or cleanup
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
>-
Cost optimization for AI workloads - model selection, GPU sizing, commitment strategies, and multi-cloud cost management
Provides expert guidance on building financial technology systems with proper accounting principles, regulatory compliance, and high-precision calculations. Specializes in ledger design, payment proce
Evidence-based diagnostic and treatment guidance for Feline Infectious Peritonitis (FIP). Use this skill when working with veterinary cases involving FIP or potential FIP, including (1) Differential diagnosis when clinical signs suggest FIP, (2) Interpreting diagnostic test results and determining next steps, (3) Treatment planning with GS-441524 or other antivirals, (4) Monitoring treatment response and adjusting protocols, (5) Managing relapses or treatment failures, (6) Client communication about prognosis and treatment options, (7) Prevention strategies and multi-cat household management, (8) Cattery breeding decisions after FIP cases, (9) Any questions about FIP diagnosis, treatment, prevention, or management. Also use when encountering mentions of FCoV, feline coronavirus, effusive/non-effusive disease forms, GS-441524, or related veterinary scenarios.
Scans Android APKs for Firebase security misconfigurations including open databases, storage buckets, authentication issues, and exposed cloud functions. Use when analyzing APK files for Firebase vulnerabilities, performing mobile app security audits, or testing Firebase endpoint security. For authorized security research only.
firebase-auth
This skill system guides Firebase development using proven patterns from production projects. It routes to specialized sub-skills based on detected intent.
firebase-firestore
firebase-storage
Guide for testing Firebase Admin SDK with Vitest mocks. Use when writing tests that involve Firebase Auth, Firestore, or Firebase App.
Fetch web content, take screenshots, extract structured data, search the web, and crawl documentation sites. Use when the user needs current web information, asks to scrape a URL, wants a screenshot, needs to extract specific data from a page, or wants to learn about a framework or library.
firecrawl
Expert firmware analyst specializing in embedded systems, IoT
Simulate a first-time CV Dashboard user experience. Tests if documentation enables new users to generate and access the password-protected variant dashboard. Generates UX audit reports.
Simulate a first-time UCV-CLI user experience. Tests if documentation enables new users to use the interactive variant management dashboard. Generates UX audit reports with friction points.
Simulate a first-time user experience by following only the documentation. Generates UX audit reports with friction points and recommendations. Use to test documentation quality and create improvement loops.
FirstSpirit CMS template development using fs-cli. Helps set up fs-cli environment, export templates from FirstSpirit server, modify templates with Claude Code, and import changes back to server. Use when working with FirstSpirit templates, CMS development, or when user mentions fs-cli, FirstSpirit, or template synchronization.
This skill provides comprehensive knowledge for templating in the FirstSpirit CMS, specifically focused on SiteArchitect development. This skill should be used when working with FirstSpirit templates including page templates, section templates, format templates, link templates, input components, template syntax, system objects, rules, and workflows. The skill is organized as structured reference documentation with topics covering architecture, template types, syntax, and development practices.
Create personalized workout plans and provide exercise guidance
Architecture test guidance for .NET using NetArchTest and ArchUnitNET. Use when enforcing architectural boundaries, testing module dependencies, validating layer constraints, or creating performance fitness functions. Includes code generation templates.
Systematically fixes all failing tests in a project by running test commands repeatedly until 100% pass with zero warnings. Use when tests are failing, validation is not passing, or when asked to fix test suites. Works with any testing framework (Jest, Pytest, Go test, etc.) and ensures complete test compliance without skipping or modifying tests.
Diagnose and fix build or type errors
Fetch GitHub CI failure information, analyze root causes, reproduce locally, and propose a fix plan. Use `/fix-ci` for current branch or `/fix-ci <run-id>` for a specific run.
Guidance for identifying and fixing security vulnerabilities in code. This skill should be used when asked to fix security issues, address CVEs or CWEs, remediate vulnerabilities like injection attacks (SQL, command, CRLF, XSS), or when working with failing security-related tests.
Repair broken imports automatically across the project
>
Continually test and repair solutions to benchmark problems until they pass. Use when a solution has failing tests. Invoke with /fix-solution <snapshot_path> <problem_name> <checkpoint_index>.
Intelligent TODO resolution with context-aware implementation
Use when encountering a bug - complete workflow from discovery through debugging, bd issue, test-driven fix, verification, and closure
Fix bugs, errors, test failures, CI/CD issues with intelligent routing. Use when reporting bugs, type errors, log errors, UI issues, code problems. Auto-classifies complexity and activates relevant skills.
Use when tests are failing, test quality issues were identified, or user wants to fix/improve specific tests
>
Create a fixup commit and autosquash rebase
Identify flaky tests from CI history and test execution patterns. Use when debugging intermittent test failures, auditing test reliability, or improving CI stability.
Suggest and apply fixes for flaky tests based on detected patterns. Use after flaky-detect identifies unreliable tests that need repair.
Diagnose and eliminate flaky tests systematically.
flask
Flask framework workflow guidelines. Activate when working with Flask projects, flask run, or Flask-specific patterns.
flesh out our plan by filling in gaps and clearly building out the specfification
Track flight status, delays, and search routes. Uses FlightAware data.
Use when you need to run Flow type checking, or when seeing Flow type errors in React code.
Create scenario files for testing migrated Output SDK workflows. Use to set up test inputs in the scenarios/ subfolder.
Creer un nouveau flow d'automatisation de formulaire complet, incluant exploration du site web, implementation et tests. (project)
Conduct an extremely thorough interview about a task/spec and write refined details back.