Implement secure file uploads with validation, size limits, type checking, virus scanning, and UUID naming. Use when handling file uploads like profile photos, documents, or resources.

Complete guide for implementing file uploads in IntelliFill with React-dropzone frontend, Multer backend, file validation, Bull queue processing, and security best practices

Strict detection and removal of unrelated files before PR creation

Manage filesystem context for offloading large context to files, persisting state between sessions, and reducing token usage. Use when managing cross-session state or context persistence. Not for small temporary data or in-memory variables.

Maintain context across Claude Code sessions using filesystem persistence. Prevents context loss, enables plan continuity, and supports multi-session workflows.

Filter and search event datasets (logs) using OPAL. Use when you need to find specific log events by text search, regex patterns, or field values. Covers contains(), tilda operator ~, field comparisons, boolean logic, and limit for sampling results. Does NOT cover aggregation (see aggregating-event-datasets skill).

Generate comprehensive session summary for Leavn work - commits, metrics, achievements, remaining work, ship readiness

Final Approach - the landing sequence. Runs Go Poll with review agents (mission-control, telemetry, flight-director) using Haiku model. Supports A+ skip rule for efficient re-reviews.

>

Final validation before task completion. Verifies all skills were consulted, documentation updated, tests pass. HAS VETO POWER - blocks incomplete tasks.

Comprehensive verification before website launch.

Start dev server, generate QA checklist, guide manual verification. Use before creating PR.

Once we are confident our recent changes have captured the essence of the change we want to commit, finalize the commit.

Completes feature/epic workflows after deployment with comprehensive walkthrough generation for epics (v5.0+), roadmap updates, artifact archival, documentation, and branch cleanup. Use after /ship-prod, /deploy-prod, or /build-local completes, or when user asks to finalize. (project)

World-class SaaS financial expert specializing in subscription accounting, revenue recognition (ASC 606), MRR/ARR tracking, cash flow management, unit economics, and financial planning for indie founders and SaaS companies.

Analyze financial data, build models, evaluate investments, and provide data-driven financial recommendations

financial-close

<!-- STATIC CONTEXT BLOCK START - Optimized for prompt caching -->

Build comprehensive 3-5 year financial models projecting revenue, expenses, headcount, cash flow, and runway. Model unit economics, scenario planning, and path to profitability. Generate investor-ready HTML reports with detailed projections and charts.

financial-models

Generate comprehensive financial reports including P&L, balance sheets, and cash flow statements

Generate income statements, balance sheets, and cash flow statements with GAAP presentation and period-over-period comparison.

Use when evaluating business model viability, analyzing profitability per customer/product/transaction, validating startup metrics (CAC, LTV, payback period), making pricing decisions, assessing scalability, comparing business models, or when user mentions unit economics, CAC/LTV ratio, contribution margin, customer profitability, break-even analysis, or needs to determine if a business can be profitable at scale.

Deep investigation to find actual root cause (not just symptoms)

Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.

Find the active phase directory based on status. Use when you need to locate which phase to work on.

Find incomplete series in your Calibre library and identify the next book to read in each series.

Searches journal for past work related to current task, finding relevant context, solutions, and decisions

Locate development tasks and TODO comments across the codebase

Search markdown files, Nextflow scripts, and config files for TODO/FIXME comments, categorize by priority, and provide actionable recommendations. Use when you need to identify pending work or track technical debt.

>

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

LLM fine-tuning with LoRA, QLoRA, and instruction tuning for domain adaptation.

Use when generating synthetic training data for multi-turn conversation fine-tuning. Triggers - have design artifacts ready, need to generate conversations, ready to assess quality. Requires finetune-design first.

Use when training a fine-tuned model and evaluating improvement over base model. Triggers - have filtered training data, ready to submit training job, need to convert to GGUF. Requires finetune-generate first.

finetuning

Identifies binary file characteristics including compiler signatures, version information, and build environment details. Use when analyzing unknown binaries, investigating binary origins, or identifying build configurations.

Clean up after a feature branch or experiment is complete. This skill deletes the git worktree and branch ONLY AFTER the associated PR has been merged. It also closes any related GitHub issues. Use this after your PR has been merged to keep the repository clean.

Complete and merge feature branch

Complete and merge hotfix branch

Prepare a GitHub issue branch for PR with quality checks, cleanup, and review recommendations.

Complete and merge release branch

Complete the current task. Behavior depends on detected mode (MAIN, FEATURE_BRANCH, WORKTREE).

This skill performs a comprehensive end-of-day wrap up for the **current working directory**. It analyzes all work done, creates a detailed log, commits changes, and pushes to the remote repository. W

Completes feature branch work by rebasing, pushing, monitoring CI, and squash merging to main

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

>-

Auto-generated CLI patterns using Google Fire with class-based structure, docstring parsing, and nested classes. Use when building Python CLI applications, creating Fire CLIs, implementing auto-generated commands, designing class-based CLIs, or when user mentions Fire, Google Fire, CLI generation, docstring commands, nested command groups, or Python command-line tools.

Guide for integrating Gemini AI models with Firebase using Firebase AI Logic SDK. This skill should be used when implementing Gemini features (chat, content generation, structured JSON output), configuring security (App Check), or troubleshooting issues (rate limits, schema errors).