Total 50,313 skills, AI & Machine Learning has 8452 skills
Showing 12 of 8452 skills
Transcribe audio with StepFun's stepaudio-2.5-asr — an SSE endpoint (NOT /v1/audio/transcriptions) with 32K context, ~85-101x RTF on long audio, and a single-call ceiling around 30 minutes (no client-side chunking). Use when transcribing Chinese / English audio with StepFun, when long-form recordings (5-30 min) need to land in one request, when migrating from step-asr / step-asr-1.1, or when hitting the misleading `model stepaudio-2.5-asr not supported` error (which actually means wrong endpoint). Triggers on 阶跃 ASR, StepFun ASR, stepaudio-2.5-asr, 转录, 语音识别, 长音频转写, 语音转文字. For TTS with the sibling stepaudio-2.5-tts model, use the stepfun-tts skill instead.
Phase quiz for AI Engineering from Scratch. Trigger with "quiz me", "test phase", "check my understanding", "do I know phase 3", or `/check-understanding <phase>`.
Use when a task needs connected MCP servers, external services, dynamic MCP tool discovery, schema inspection, sandboxed MCP execution, or routing across many possible MCP tools.
Reference: review of an inbound vendor agreement against the team playbook in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`. Flags deviations, assesses risk, generates specific redline language, and routes to the right approver. Loaded by /commercial-legal:review when a vendor MSA, services agreement, or similar is detected.
This skill should be used when the user asks to "create an agent", "make an agent", "write an agent", "build a subagent", "add an agent to a plugin", "design an autonomous agent", "generate an agent file", "write a system prompt for an agent", "what frontmatter does an agent need", "create a specialized agent". Not for skills or commands — use create-skill.
This skill should be used when the user says "interview me about", "help me clarify", "stress-test my idea", "let's explore this concept", "challenge my assumptions about", "grill me on", "drill into my plan", or needs structured questioning to refine and articulate their thinking.
Turn papers, technical articles, or knowledge content into highly realistic AIGC slides. First create a narrative structure and page-by-page visual direction, then call an image generation model to produce a 16:9 slide image for each page, and finally synthesize into PPTX/PDF. Suitable for paper presentations, group meetings, open courses, technical sharing, and commercial research presentations; use this skill when users mention "paper PPT", "AI-generated PPT", "PPT that doesn't look like AI", "high-quality slides", or "page-by-page AI-generated PPT".
Build an operator-level compute template for an LLM and estimate FLOPs/MFU for a serving shape. Use when you need tensor shapes, per-op FLOPs, kernel-to-op MFU mapping, or parallelism what-if analysis.
For use when students **have completed WG-12 to WG-21** (single-file consolidation blueprint) and are working on **WG-22 Code Splitting** (`agent_core.py` + `main.py`). **First message in a new session**: Display PEAS brand screen and confirm readiness first; after confirmation, **lay out the context** before proceeding to requirement clarification. If **`prompts/` or `templates/`** are missing, copy them from `references/project_assets/` to the project root. Process: Spec Alignment (2d′) → Six-column Contract → **In-session Handoff Implementation** → Acceptance. Starting point: starter_main_wg21.py; Standard reference: reference_agent_core.py + reference_main.py. Triggers: peas-workshop-advanced-coach, PEAS workshop advanced coach, WG-22, code splitting coach, Agent.chat.
Read a story file and implement it. Loads the full context (story, GDD requirement, ADR guidelines, control manifest), routes to the right programmer agent for the system and engine, implements the code and test, and confirms each acceptance criterion. The core implementation skill — run after /story-readiness, before /code-review and /story-done.
Generate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles. Produces structured spec files and updates the master asset manifest. Run after art bible and GDD/level design are approved, before production begins.
Redis LangCache guidance for semantic caching of LLM responses on Redis Cloud — calling search/set via the SDK or REST API, tuning the similarity threshold, separating caches per task type, and filtering with custom attributes. Use when caching LLM completions or RAG answers to cut API cost and latency, building a cache-aside layer in front of OpenAI / Anthropic / etc., tuning hit rate vs precision, or splitting one app's LLM workloads into multiple LangCache caches.