Best practices for Android Intent security. Use this skill when auditing component configurations in AndroidManifest.xml activities, services, receivers) or source code handling incoming Intents (getIntent, getParcelableExtra) to prevent Intent Redirection and unauthorized access.

SwiftUI view refactor/review: layout, DI, Observation, view models.

Oracle second-model review: bundle prompts/files, debug, refactor, design.

OpenAI Images API: batches, prompt sampler, gallery.

GitHub quota/cache hygiene: gh, ghx, xcache, gitcrawl, mirrors, limits.

Codex debugging: codex-rs core/tui/exec/cli/app-server/config.

Beeper cache: contact hints, room lookup, WhatsApp/iMessage traces, FTS.

追本之箭——纵向深钻思维工具。给一个观点、现象或问题，像箭一样一路向下钻到不可再分的本质。Use when user says '想透', '追本', '本质是什么', '为什么会这样', '深挖', '钻到底', 'think deep', 'drill down', or wants to trace any idea/phenomenon vertically to its irreducible root. Also trigger when user provides a statement and wants depth analysis, not breadth survey.

把 ~/.agents/skills/ljg-* 里所有更新过的 skills 同步到 github repo (ljg-skills)，先推 master 分支（org-mode 输出风格），再切 md 分支（markdown 输出风格）做基础 markdown 化后推。Use when user says '/ljg-push', 'push skills', '推送 skills', '同步 skills', 'sync ljg', or whenever ljg-* skills get updated and need shipping. NOT FOR pushing non-ljg skills or arbitrary git repos.

Use when creating or modifying OpenChamber shared UI data access, OpenCode SDK calls, `RuntimeAPIs`, runtime fetch/auth/URLs, authenticated browser assets, bridges/proxies, runtime switching, or server API routes.

Execute Python scripts for spreadsheet operations with mandatory source data validation and fallback protocols

Delegate complex tasks to shell_agent when direct tool execution fails, leveraging autonomous error recovery and library selection

Systematic fallback workflow for PDF generation through pandoc, reportlab, and fpdf2 with installation verification

Fallback workflow for document generation when code sandbox returns opaque errors

Use run_shell with inline Python as a fallback when execute_code_sandbox fails for openpyxl/spreadsheet operations

Use run_shell as fallback when execute_code_sandbox or shell_agent fail on filesystem operations

Audit generated Excel reports by enumerating populated output rows, exposing formulas, and checking that each subtotal range includes all visible detail rows.

Create Excel files with openpyxl by falling back to run_shell with inline Python heredoc when execute_code_sandbox fails

Unicode-safe fallback workflow for multi-format document generation with character sanitization and explicit error capture

Debug Python code execution failures by capturing partial traces, isolating failing functions, and incrementally verifying outputs