Adding Firebase features can break tests, rules, or authentication when project patterns are unclear. This skill guides a test-first workflow for Cloud Functions, Firestore collections, API endpoints, and emulator verification.

Firebase work spans setup, functions, Firestore rules, emulators, and deployment checks. This skill provides routed workflows for setup, feature work, debugging, and validation.

Documentation can drift after refactors, releases, and deleted files. This skill extracts claims, checks them against code, and produces an evidence-based audit report.

CSS reviews can miss naming, dark mode, composition, and test gaps. This skill guides a systematic validation pass with structured findings and fixes.

Repeated utility classes and inline styles make frontend code harder to maintain. This skill guides Claude, Codex, and Claude Code through semantic CSS refactoring with tests.

Teams often add CSS components without consistent naming, dark mode, or tests. This skill guides reuse, Tailwind composition, documentation, and verification.

CSS styles often drift across components and utility classes. This skill guides semantic class creation, Tailwind composition, dark mode coverage, tests, and refactoring.

Complex features often have several valid implementation paths. This skill runs independent agent implementations, reviews them, and helps select the strongest result.

Executives often lose insight across reviews, goals, and leadership decisions. This skill builds a structured private system for reflection, planning, and pattern tracking.

Multi-agent projects often fail from unclear orchestration, weak boundaries, and unmanaged tool access. This skill provides architecture patterns, safety controls, and production checklists for coordinated agents.

Unknown executables and firmware blobs need quick facts before deeper reverse engineering. This skill guides Claude, Codex, and Claude Code through fast metadata, ABI, dependency, string, and import checks.

Reverse engineering work stalls when essential tools are missing or misconfigured. This skill guides setup for radare2, Ghidra, GDB, QEMU, Frida, and related toolchains.

Binary analysis often produces scattered facts that are hard to share. This skill helps Claude, Codex, and Claude Code turn evidence into clear reports with confidence levels and next steps.

Binary analysis is slow when function maps, xrefs, and decompiler output are scattered. This skill gives Claude, Codex, and Claude Code a staged static-analysis workflow.

Unknown binaries can hide behavior that static review cannot confirm. This skill guides controlled execution, tracing, debugging, and evidence capture for dynamic analysis.

Binary analysis requires many tools, safe execution choices, and careful evidence tracking. This skill gives Claude, Codex, and Claude Code structured workflows for triage, static analysis, dynamic testing, setup, and reporting.

Web pages often include navigation, ads, and dynamic content that obscure useful information. This skill guides Claude, Codex, or Claude Code to capture pages and return clean content.

PDF workflows often require extraction, conversion, merging, and form filling across many documents. This skill provides practical Python and command-line recipes for repeatable PDF processing.

Manual commit preparation can miss staged changes, message style, or sensitive files. This skill reviews git state and helps create clear conventional commits.

Code reviews can miss bugs, security flaws, and maintainability issues. This skill guides Claude, Codex, and Claude Code through structured review steps.