Loading...
Loading...
Found 479 Skills
Set up Jetty for the first time. Guides the user through account creation, API key configuration, and introduces runbooks — human-readable markdown files that tell an agent how to accomplish multi-step tasks with measurable outcomes. Use this skill whenever the user wants to set up, configure, or get started with Jetty — including 'set up jetty', 'configure jetty', 'jetty setup', 'get started with jetty', 'install jetty', 'connect to jetty', 'jetty onboarding', 'I am new to jetty', 'how do I start with jetty', or even just 'jetty' if they do not appear to have a token yet. Also trigger if the user mentions needing an API key for Jetty or storing their OpenAI/Gemini key in Jetty.
GANG Worker Skill. You are a worker, receiving features assigned by orch, performing minimal self-checks, handing off to validator-N, and the validator will issue a verdict to the upstream.
Audit, plan, and safely optimize Shopify image alt text for product media, collection featured images, article featured images, and article inline images. Use when a merchant wants an AI agent to scan Shopify images, test whether the active AI model can inspect images, generate concise alt text with multimodal image understanding when available or context-only fallback when it is not, review the proposed changes in batches, and apply approved Shopify Admin updates.
A hybrid pattern where the system pauses execution to request human approval, input, or disambiguation before proceeding with critical actions. Use when user asks to "add human approval", "require human review", "human-in-the-loop", or mentions approval workflows, human oversight, or escalation.
Use this skill whenever the user asks about live sports scores, standings, team stats, game summaries (with box score, leaders, scoring plays, odds, and win probability), NFL / NBA / MLB / NHL / NCAA / MLS / EPL / WNBA games, team schedules, polls, or rankings. ESPN sports CLI with live scores across 10 leagues, offline search, head-to-head comparisons, and rich per-game summary payloads. No API key required. Triggers on natural phrasings like 'what's the score of the Lakers game', 'Patriots schedule this week', 'NFL standings', 'box score for tonight's Mavs game', 'Chiefs vs Eagles head to head', 'who's on top of the AP poll'.
Compare a paper's claims against its public codebase. Use when the user asks to audit a paper, check code-claim consistency, verify reproducibility of a specific paper, or find mismatches between a paper and its implementation.
Optimize and structure context for agents and LLMs by reducing noise, prioritizing relevance, organizing memory, defining constraints, and managing token budgets.
Create and manage DESIGN.md files. Useful for capturing design direction, tokens, and visual rules in a single source of truth.
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.
Review and approve (or reject) pending playbook update proposals from the playbook-monitor agent and apply approved changes to the practice profile. Use when the playbook-monitor agent has surfaced proposals, when the user says "review playbook proposals", "what playbook updates are pending", or wants to step through deviation-driven playbook changes.
Use when tasks are complex and require full microservices collaboration: The main agent acts as a pure Orchestrator, strictly prohibited from writing code personally, and is responsible for accurately assigning responsibilities such as positioning, planning, coding, testing, and review to corresponding sub-agents (explorer, planner, worker, verifier, reviewer, fixer). This Skill enforces microservices workflow discipline, requiring full Chinese communication, minimal routing output, and minimized context transfer.
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.