Loading...
Loading...
Found 5,519 Skills
Générez des prompts optimisés pour chaque modèle de génération vidéo IA (Veo 3, Runway Gen-3, Kling 2.6, Pika), en exploitant leurs forces spécifiques. Use when: **Animer des frames de storyboard** - Transformer des images fixes en vidéo; **Choisir le bon modèle** - Sélectionner Veo, Runway, Kling ou Pika selon le besoin; **Optimiser la qualité de génération** - Prompts structurés pour meilleurs résultats; **Créer des transitions fluides** - Scene extension, first/last frame; **Utiliser le mo...
Activate this when users need to understand extreme events (bubbles, crashes, mass hysteria, cults, mob behavior), diagnose systemic organizational failures, or assess the risk of multiple psychological/market/institutional forces aligning in the same direction. Typical trigger signals: the phenomenon described by the user "far exceeds what any single factor can explain"; the user attempts to explain an extreme outcome with a single cause; the user is concerned about "multiple adverse factors erupting simultaneously". Not applicable to conventional single-factor decision analysis or assessment of mild incremental changes.
Phase 2 of the feature workflow — Write code according to the implementation sequence in {slug}-design.md, and submit a completion report in a unified format for user review after finishing. Prerequisites: {slug}-design.md has been approved (standard design includes test design, or fastforward design includes acceptance criteria), and {slug}-checklist.yaml exists in the same directory. Trigger scenarios: User says "The plan is confirmed, start implementation", "Write code according to the plan", "Start working". If you encounter situations not covered by the plan during implementation (new concepts, out-of-scope files, need for patch branches), proactively stop and discuss with the user based on the plan, do not proceed forcefully.
Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.
Generate reference documentation entry by entry for the public surface of libraries (components, functions, commands, etc.), with manifest tracking, supporting both single-entry and batch modes. Fundamental differences from guidedoc: guidedoc teaches you how to use things, while libdoc tells you what each part looks like; guidedoc's information sources are solution docs + user knowledge, while libdoc's information source is the source code itself. Trigger scenarios: When users say "write API documentation", "component documentation", "libdoc", "write documentation for each component", or when new public library interfaces are found after feature-acceptance.
Upgrade any Pulumi provider to a newer version and reconcile the resulting diff. Use when users want to upgrade or update a provider (including editing package.json, requirements.txt, pyproject.toml, go.mod, or Pulumi.yaml to bump a provider SDK), check for breaking changes before or during an upgrade, fix resources that broke after a provider upgrade, or resolve unexpected replacements, creates, or deletes in a post-upgrade preview. Applies to all providers (aws, azure-native, gcp, kubernetes, aws-native, cloudflare, datadog, etc.) — not just Tier 1. Do NOT use for querying which stacks use what package versions; use skill `package-usage` for cross-stack audits. Do NOT use for general infrastructure tasks.
Monetize a DFlow integration by collecting a builder-defined fee on trades your app routes through the Trade API — either a fixed percentage (spot + PM) via `platformFeeBps`, or a probability-weighted dynamic fee (PM outcome tokens only) via `platformFeeScale`. Use when the user asks "how do I take a cut of trades?", "add a builder fee", "monetize my swap UI", "charge a platform fee", "how does platformFeeBps / platformFeeScale work?", or "where do my fees get paid?". Do NOT use to run a trade itself (use `dflow-spot-trading` or `dflow-kalshi-trading` — both also cover priority fees and sponsored / gasless flows).
YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to "brainstorm this", "I have an idea", "help me think through this", "office hours", or "is this worth building". Proactively suggest when the user describes a new product idea or is exploring whether something is worth building — before any code is written. Use before /plan-ceo-review or /plan-eng-review.
Solidroad platform help — AI-powered QA and training for CX teams. Use when reps ramping too slowly and need AI practice simulations, QA only covers 2% of conversations and you want 100% automated scoring, training and QA are disconnected and insights don't turn into coaching, setting up Solidroad scorecards or custom quality rubrics, connecting Solidroad to Salesforce Service Cloud or Zendesk or Intercom, or evaluating Solidroad vs Observe.AI vs Balto vs Cresta for contact center QA. Do NOT use for general coaching strategy without a specific platform (use /sales-coaching).
LeadIQ platform help — Chrome extension-first B2B prospecting with AI outreach writing, champion tracking, and CRM enrichment via GraphQL API. Use when captured contacts from LinkedIn have wrong phone numbers, Salesforce sync keeps assigning leads to wrong accounts, Chrome extension freezes or won't load on LinkedIn, credits are burning too fast on phone lookups, HubSpot integration is too complex through Workato, or Scribe AI emails sound too generic. Do NOT use for building prospect lists across multiple tools (use /sales-prospect-list), general enrichment strategy across providers (use /sales-enrich), outbound sequence design (use /sales-cadence).
Diagnoses live CockroachDB cluster performance issues by identifying long-running queries, busy sessions, and active transactions using SQL-only interfaces. Use when users report cluster slowness, high CPU, or need to find runaway queries and their source applications without DB Console access.
Fetch a company/product logo from public sources (Clearbit, og:image, favicon) given a brand name or URL, score candidates (wide-aspect + transparent preferred), and archive the best + runner-ups to ~/.lovstudio/logo-collection/<slug>/. Trigger when the user says "find logo", "找 logo", "抓 logo", "收集 logo", "brand asset", "需要 <brand> 的 logo", or wants logos laid out for a website/PPT/poster.