Total 56,145 skills, AI & Machine Learning has 9349 skills
Showing 12 of 9349 skills
Forensic audit of the user's recent Claude Code sessions to surface step-change workflow improvements — not marginal ones. Use when the user asks to "audit my Claude Code sessions", "analyze how I use Claude Code", "find patterns in my usage", "improve my Claude Code workflow", "review my sessions", "find leverage in my setup", or wants to understand where their Claude Code setup is leaking time. Samples dozens of real transcripts, extracts quantitative signal via scripts, uses parallel subagents for deep reads, then synthesizes into a short prioritized report with drafted implementations (new skills, CLAUDE.md rules, hooks, settings diffs) that the user can install directly. Trigger even when the user doesn't say the word "audit" — if they're asking about improving or reviewing their Claude Code habits at scale, use this skill.
Use this skill when pricing, ranking, or researching X/Twitter KOLs for a creator marketing campaign, especially when the user provides handles, asks for batch KOL analysis, wants outreach recommendations, or wants an agent-native version of the KOL Pricing framework. Prefer UnifAPI MCP tools for public X data, then run the deterministic pricing workflow before drafting outreach.
Generate images with gpt-image-2 through an OpenAI-compatible Image API using the current OPENAI_API_KEY, OPENAI_BASE_URL, or CUSTOM_IMAGE_URL environment variables. Use when the user asks to call gpt-image-2 via API/CLI, /v1/images/generations, the prior /api/image/generate endpoint flow, or wants the faster API route instead of Codex CLI image_generation/session extraction.
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>`.
This skill should be used when the user asks to "fix my skill" or "audit this skill". Make sure to use this skill whenever the user mentions skill quality, structural issues, broken skills, or skill diagnostics — even if they don't explicitly say "repair-skill". Not for adding features or improving effectiveness — use improve-skill. Not for agents — use repair-agent.
Scan the portfolio for the highest-leverage AI opportunities and rank where to deploy operating-partner time. Ingests quarterly updates and financials across multiple portfolio companies, identifies quick wins at each, and stacks them into a single ranked action list. Use during quarterly portfolio reviews, annual planning, or when deciding which companies get AI investment first. Triggers on "AI readiness", "AI opportunity scan", "where should we deploy AI", "AI across the portfolio", "AI quick wins", or "which portcos are ready for AI".
Generates llms.txt and llms-full.txt files for LLM-friendly project documentation following the llms.txt specification. Use when the user wants to create LLM-readable summaries, llms.txt files, or make their wiki accessible to language models.
Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.
Use Po Once's organization-scoped agent API to list connected accounts, upload media, create content, schedule or publish posts, inspect status, and delete eligible scheduled posts through a local helper script.
Interactive QA session where users report bugs or issues through conversation, and the agent creates GitHub issues. Explore the codebase in the background to obtain context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".
Turn a vague, messy, or multi-part user ask into a clean, self-contained prompt that a fresh agent could execute without further questions. Interview the user one question at a time — walking down the decision tree, branching on each answer — until the prompt is tight, then output the final prompt as the deliverable. Trigger eagerly: any voice-dictated input, filler-heavy prose, underspecified references ("the thing", "that script"), multi-part requests, or any plan the user wants stress-tested. The skill itself can be skipped for trivial one-line requests where producing a prompt artifact would be pure ceremony — but once invoked, always produce the prompt, even if execution looks trivial.
Validate and use packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs, and applying the right CP constraints.