Development

End-to-end iOS malware/spyware forensic assessment of a non-jailbroken iPhone from a Mac. Installs tooling (libimobiledevice + Mobile Verification Toolkit), pulls crash logs, creates a full ENCRYPTED device backup (auto-resuming on lock/disconnect), decrypts it, runs MVT against every spyware IOC feed (Pegasus, Predator, Candiru, Cellebrite, Intellexa, stalkerware, ...), sweeps every file in the backup manifest, analyzes crash logs for injected dylibs, and produces an assessment report. Use w...

Use when the user mentions logic analyzers, signal capture, waveform acquisition, protocol decoding, sigrok, sigrok-cli, .sr files, bus traces, or debugging digital signals on hardware — including I2C, SPI, UART, JTAG, 1-Wire, I3C, MCTP, and DDR5 SPD/PMIC traffic.

Rebuild public websites as clean, maintainable local projects with disciplined visual, interaction, and media fidelity. Use when the user asks to clone, replicate, reproduce, port, or study a public website, including video-led landing pages, MP4/WebM or HLS experiences, scroll-scrubbed and masked video, Three.js/WebGL/R3F scenes, Pixi.js or Canvas2D toys, animated product pages, and phrases such as "复刻这个网站", "clone this site", "pixel-perfect copy", "rebuild this page", or "rewrite this scree...

Performs engineering review across frontend, backend, infrastructure, and tests. Writes reports/runs/<workflow-run-id>/code-review-report.md with owner-routed findings. Reports only to Team Lead.

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.

This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on adva...

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.

Pre-landing code review for the current OPC branch or diff. Use before merging, shipping, or asking whether a change is safe.

Read-only QA report for an OPC desktop flow, CLI command, local URL, staging URL, or documented user journey. Does not modify code.

Systematic root-cause debugging for OPC work. Use when there is a bug, crash, regression, failing command, flaky behavior, provider issue, or unexplained output. Requires evidence before fixes.

Update or audit OPC documentation after code changes. Use when behavior, setup, CLI flags, desktop workflow, provider support, or plugin surfaces changed.

Security audit workflow for OPC code, providers, plugins, Electron surfaces, local HTTP bridges, filesystem access, and command execution.

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.

Use when writing hardware, firmware, verification, or tooling code that will reach real silicon, and you face a tradeoff between shipping fast and shipping correct; covers failures-should-fail, no over-engineering, no-panic, and test coverage

Clones a website with high fidelity from its live source of truth. Use when the user says clone this site, copy this page, rebuild this landing page, recreate this design, make me a site like X, or pastes a URL and asks for the same thing in their stack. Drives Chrome DevTools MCP to measure computed styles, CSSOM, fonts, geometry, motion, and breakpoints, mirrors every asset byte-for-byte, recovers the motion system from the site's own bundle when it is hand-rolled, then builds it with a par...

Look up the safe idiom and known-risky API/library for a language or framework (Python, JS/TS/Node, Java, Go, C/C++, Ruby) before or while writing code — a design/build-time cheat-sheet, distinct from post-hoc scanning. Use when writing or reviewing code, scoping a PRD's tech stack, or advising an AI-assisted/vibe-coded change on which APIs and libraries to avoid up front.

Run a MASTG-based mobile penetration test (Android/iOS) combining static and dynamic analysis: storage inspection, traffic interception, platform-interaction abuse, and resilience checks. Use to actively test a mobile app you're authorized to assess.

Aggregate a fast, diff-scoped security check before `git commit`/`git push` — secrets/gitignore hygiene, SAST/SCA on changed files, and IaC/Claude-config checks where relevant — into a single go/no-go verdict. Use before committing or pushing, not as a full-repo audit.

Read a Claude Code session as a story with the git-receipts CLI — what was asked, what the agent did, what landed, commit by commit. Use when the user asks what happened, what an agent did, to catch up on an unattended or overnight run, to recap a session or a commit, to understand work from a while ago, or after any long run. ALSO use to catch up on a lane or sub-agent the user did not watch, and after this conversation has been compacted — the receipt holds the prompt-to-commit chain the se...