Enforces strict test-driven development -- write a failing test first, implement minimal code to pass, then refactor. Use when implementing a feature, fixing a bug, adding behavior, refactoring, or any time production code will be written or changed. Also use when the user says "write tests", "add tests", "TDD", or "test first". DO NOT TRIGGER for throwaway prototypes, generated code, or config-only changes unless the user explicitly requests TDD.

Coordinates parallel subagent dispatch to solve multiple independent problems concurrently, with structured prompts and conflict-free integration. Use when there are 2+ independent failures, bugs, tasks, or investigations that do not share state -- e.g. multiple test files failing for different reasons, unrelated subsystems broken, or batch tasks that can run simultaneously. DO NOT TRIGGER when failures are related, require shared context, or agents would edit the same files.

Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.

Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says \"DSE\", \"design space exploration\", \"sweep parameters\", \"optimize\", \"find best config\", or wants iterative parameter tuning.

Use when writing or reviewing Python code in this repo that builds an interactive voice agent via `agent.deepgram.com/v1/agent/converse`. Covers `client.agent.v1.connect()`, `AgentV1Settings`, `send_settings`, `send_media`, event handling, and function/tool calling. Full-duplex STT + LLM + TTS with barge-in. Use `deepgram-python-text-to-speech` for one-way synthesis, `deepgram-python-speech-to-text` / `deepgram-python-conversational-stt` for transcription only. Triggers include "voice agent", "agent converse", "full duplex", "interactive assistant", "barge-in", "agent.v1", "function calling", "AgentV1Settings".

Use when writing or reviewing Python code in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio transcription. Covers `client.listen.v1.media.transcribe_url` / `transcribe_file` (REST) and `client.listen.v1.connect` (WebSocket). Use this skill for basic ASR; use `deepgram-python-audio-intelligence` for summarize/sentiment/topics/diarize overlays, `deepgram-python-conversational-stt` for turn-taking v2/Flux, and `deepgram-python-voice-agent` for full-duplex assistants. Triggers include "transcribe", "live transcription", "speech to text", "STT", "listen endpoint", "nova-3", "listen.v1".

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST via `client.speak.v1.audio.generate` and streaming WebSocket via `client.speak.v1.createConnection()` / `connect()`. Use `deepgram-js-voice-agent` when you need full-duplex STT + LLM + TTS instead of one-way synthesis. Triggers include "TTS", "text to speech", "speak", "aura", "streaming TTS", and "speak.v1".

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming transcription. Covers `client.listen.v2.createConnection()` / `connect()`, Flux models, and turn events like `TurnInfo`. Use `deepgram-js-speech-to-text` for standard v1 ASR and `deepgram-js-voice-agent` for full-duplex assistants. Triggers include "flux", "v2 listen", "conversational STT", "turn detection", "end of turn", "EOT", and "listen.v2".

Use this skill any time the user wants to create a Google Slides deck from a template, mentions "Google Slides" with a template in mind, provides a Google Slides URL plus a content brief, or asks to "make slides", "build a deck", "generate a presentation", or "fill this template" in a Google Workspace context. Requires the Studio Google Slides + Google Drive MCP connectors. Do NOT use for PowerPoint (.pptx) creation (use the pptx skill), for editing without a template, or for authoring a new template (template authoring has its own skill).

Use this skill at the end of a Google Slides deck-creation flow run by the same agent in the current session, before reporting the finished URL to the user. Catches the failure modes a creating agent reliably misses — surviving placeholder text, unswapped template imagery, layout overflow, hidden-original leaks. Trigger when the parent google-slides workflow reaches Step 9 / QA, or when the user asks "is this deck ready?" / "QA my deck" about a deck this agent itself just edited. Do NOT trigger for reviewing decks the agent did not create — without the Step 5 pre-fill snapshot the leak check silently degrades and the result is misleading.

Diagnose and resolve RevenueCat integration issues — inspects dashboard configuration through the RevenueCat MCP, walks the SDK debug logs, and covers code-side gotchas. Use when the user says offerings are empty, products not loading, entitlement not active after purchase, paywall won't load, transactions not appearing, customer info shows no entitlements, sandbox purchase not working, or RevenueCat is broken on iOS, Android, Kotlin Multiplatform, Flutter, or React Native.

Define reusable Airflow task group templates with Pydantic validation and compose DAGs from YAML. Use when creating blueprint templates, composing DAGs from YAML, validating configurations, or enabling no-code DAG authoring for non-engineers.

Excel CLI automation skill for Windows workbooks. Use when a coding agent needs token-efficient, scriptable, or unattended Excel automation via excelcli commands. Best for CI/CD, scheduled jobs, batch processing, PowerShell workflows, and bulk workbook edits. Supports Power Query, DAX, PivotTables, Tables, Ranges, Charts, VBA, Data Models, screenshots, and formatting. Triggers: excelcli, Excel CLI, command line, batch, script, automation, CI/CD, scheduled, PowerShell, unattended, coding agent, workbook processing.

Security patterns for Falcon Foundry apps including OAuth scopes, RBAC, input validation, UI security, and credential management. TRIGGER when user asks to "configure OAuth scopes", "secure a Foundry app", "handle secrets", "add input validation", or needs to review a Foundry app for security concerns (XSS, CSP, credential management). Also trigger during pre-deployment security reviews.

Plan and run a media pipeline for images, video, and downloadable assets. Use this skill when designing image storage and delivery, choosing formats (WebP, AVIF), setting up responsive images, picking a video host, organizing a brand asset library, or auditing a slow image pipeline. Triggers on image pipeline, asset library, DAM, image optimization, WebP, AVIF, responsive images, video hosting, image CDN, asset workflow, media management. Also triggers when images are slow, broken, or scattered across systems.

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

Analyzes bootkit and advanced rootkit malware that infects the Master Boot Record (MBR), Volume Boot Record (VBR), or UEFI firmware to gain persistence below the operating system. Covers boot sector analysis, UEFI module inspection, and anti-rootkit detection techniques. Activates for requests involving bootkit analysis, MBR malware investigation, UEFI persistence analysis, or pre-OS malware detection.

Parses and analyzes the Windows Amcache.hve registry hive to extract evidence of program execution, application installation, and driver loading for digital forensics investigations. Uses Eric Zimmerman's AmcacheParser and Timeline Explorer for artifact extraction, SHA-1 hash correlation with threat intel, and timeline reconstruction. Activates for requests involving Amcache forensics, program execution evidence, Windows artifact analysis, or application compatibility cache investigation.

Uses the Linux Audit framework (auditd) with ausearch and aureport utilities to detect intrusion attempts, unauthorized access, privilege escalation, and suspicious system activity. Covers audit rule configuration, log querying, timeline reconstruction, and integration with SIEM platforms. Activates for requests involving auditd analysis, Linux audit log investigation, ausearch queries, aureport summaries, or host-based intrusion detection on Linux.