Loading...
Loading...
Found 5,484 Skills
Deploy vLLM using Docker (pre-built images or build-from-source) with NVIDIA GPU support and run the OpenAI-compatible server.
Format values for display using the FormatStyle protocol and its concrete types. Use when formatting numbers (integers, floating-point, decimals), currencies, percentages, dates, date ranges, relative dates, durations (Duration.TimeFormatStyle, Duration.UnitsFormatStyle), measurements, person names (PersonNameComponents.FormatStyle), byte counts (ByteCountFormatStyle), lists (ListFormatStyle), and URLs (URL.FormatStyle). Also covers creating custom FormatStyle conformances and replacing legacy Formatter subclasses. FormatStyle is available iOS 15+; Duration styles require iOS 16+.
LLM-as-a-judge HTTP/HTTPS proxy that secures AI agents by intercepting and evaluating outbound requests against security policies before they reach external APIs.
GEOFlow open-source GEO/SEO content production system with AI generation, review workflow, and publishing pipeline built on PHP and PostgreSQL.
Richard Feynman's Integrity Audit applied to any analysis, business plan, or decision. Spawns a team of specialist agents — Source Auditor, Self-Deception Hunter, Translation Tester, Cargo Cult Inspector, Confidence Inverter — who each apply a distinct lens from Feynman's framework to detect dishonesty, self-deception, and cargo cult reasoning. The lead synthesizes into a verdict: is this analysis honest, or is it fooling itself? Use when the user says "feynman this", "integrity audit", "is this honest", "am I fooling myself", "cargo cult check", or wants to stress-test any analysis, plan, or claim before trusting it. Works standalone or as a meta-audit after /munger or /thiel.
Momentum platform help — AI revenue orchestration with automated CRM updates, Slack Deal Rooms, MEDDIC Autopilot, AI coaching, churn signals, and executive briefs. Use when Salesforce fields never get updated after calls, deal rooms in Slack are noisy or disorganized, MEDDIC tracking is inconsistent across reps, post-call action items aren't making it into the CRM, you need churn risk signals from customer conversations, or AI coaching scores don't match what you see on calls. Do NOT use for building outbound sequences (use /sales-cadence) or picking an AI note-taker (use /sales-note-taker).
People.ai (now Backstory) platform help — automatic activity capture, deal intelligence, pipeline health, revenue forecasting, MCP integration, Salesforce/Dynamics/Oracle CRM sync. Use when reps aren't logging activities and CRM data is stale, deals are slipping without warning and you need early risk signals, forecast accuracy is poor because it's based on gut not data, evaluating People.ai vs Gong vs Clari vs Revenue.io for revenue intelligence, activity data isn't tying back to pipeline or revenue outcomes, or you want to connect People.ai to AI agents via MCP. Do NOT use for conversation intelligence with call recording and transcription (use /sales-gong or /sales-note-taker), building outbound sequences (use /sales-cadence), or general CRM data cleanup strategy (use /sales-data-hygiene).
Auto-generate viral 9:16 YouTube Shorts (or TikTok/Reels clips) from a long-form YouTube URL or hosted video. Pipeline downloads the source, transcribes locally with Whisper, ranks highlights through a virality framework (hook / emotional peak / opinion bomb / revelation / conflict / quotable / story peak / practical value), dedupes overlapping candidates, and vertically auto-crops the top N as mp4s via `muapi edit clipping`.
Handles Taubyte login/profile setup and first-time browser GitHub auth via tau login --new when no account exists; tau login for existing profiles. Stops immediately when browser login is required. Uses non-interactive login when the user supplies a GitHub username; otherwise asks for it explicitly. Must run before cloud/project/resource operations.
Build fact-grounded short-form video personas and visual consistency packs from validated benchmark research. Use this when you need to define a repeatable creator archetype, image prompt pack, or persona lock for batch video production. This skill must derive personas from real benchmark evidence such as creator types, protagonist descriptions, visual styles, hooks, and audience language. Do not invent personas or visual traits without source support.
Professional-grade contract review skill that adds comment-based issue annotations without changing original text. Enforces a four-layer review (entity verification, basic, business, legal), writes structured comments (issue type, risk reason, revision suggestion) with risk level encoded via reviewer name, and generates a contract summary, consolidated opinion, and Mermaid business flowchart (with rendered image). Output language must follow the contract’s language.
Verifies a Taubyte Go function locally via the `taubyte/go-wasi` Docker recipe (preferred over `tau build`, with tmpfs+bind-mount-ro to avoid root-owned artifacts in the source tree), and verifies a function actually serves on Dream by curling the gateway with the right `Host:` header (plus `/etc/hosts` mapping for `*.localtau`). Use when locally compiling a Go function to WASM, when smoke-testing a function before pushing, or when probing a Dream-hosted HTTP function from the laptop.