Trending Agent Skills

Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent.

Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.

Run a pre-mortem risk analysis on a PRD or launch plan, categorizing risks as Tigers, Paper Tigers, and Elephants, with action plans.

The convex-verify skill proves a Convex feature works by seeding, driving as multiple mocked users via convex-test, and asserting behavior including negative authz cases.

Run every Convex audit (authz, reviewer, advisor, insights) into one scored, deduped readiness report with an ordered fix plan — Lighthouse for your backend.

Seed or import data into the Convex database.

Set and wire Convex deployment env vars / secrets for the app.

Set up Convex backups and run a restore drill that proves recovery, including snapshot, restore into a throwaway preview, data assertion, plus an RPO-matched schedule and a gated recovery runbook.

Add recurring scheduled jobs (crons) to the Convex app.

Suggest the matching Convex component when the user hand-rolls a pattern it already solves.

Design and build reactive, type-safe, production-grade backends on Convex, covering schema, queries/mutations/actions, indexes, auth, file storage, scheduling, real-time multiplayer, mobile backends, and LLM/agent workflows on Convex's one-platform stack.

Add an AI agent/RAG backend to the Convex app with durable threads, message history, tool-calls, and vector search.

Preview Convex spend — rank functions by bytes/documents-read × call-volume from insights, project each cost driver's growth curve, name the cheapest fix; confirm-cost for paid actions.

Generate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy, bundled with documented prompting patterns for sharper output.

The Convex Self-Heal skill triages production errors, root-causes them, repairs them, and certifies the fix via tsc, rehearsal, and reproduce-then-gone checks, then proposes a PR for a human to merge and confirms the error stops recurring.

Add Stripe billing/payments to the Convex app via @convex-dev/stripe (checkout + webhook + gating).

Point a domain you already own at your Convex app (DNS records, custom-domain attach, auth-origin rebind).

Explain an existing Convex app: data model, functions, auth, components, and request flow, read-only.

Lark video meeting skill: query meeting records and artifacts (notes/transcripts/minutes), search/upload/download/edit minutes, bot participation and in-meeting interactions.

Set up Sentinel production error capture in your own Convex deployment.

Watch for the next dev/prod error or request in a Convex app and react to it.

Rehearse a live-app schema change and backfill on a snapshot-seeded preview deployment, verify, then promote the proven change to prod with the snapshot as rollback.

Generate and edit images with OpenAI GPT Image 2 on RunComfy, with strengths in embedded text, logos, multilingual typography, and instruction precision.

Create AI avatar, talking-head, and lip-sync videos on RunComfy via the `runcomfy` CLI, routing across OmniHuman, Wan 2-7, HappyHorse, and Seedance v2 models.

Smart router to the right image-to-video model in the RunComfy catalog for portrait animation, custom-voiceover lip-sync, or multi-modal composition.

Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

Region edits across video frames via the RunComfy CLI — remove an object that appears across many frames, clean up wires or watermarks, and replace a region with matching motion.

Swap a face or character into videos or images via the RunComfy CLI, automatically selecting the best model for the user's intent.

Edit images on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog.

RunComfy CLI is a command-line tool that provides a single binary and single authentication to access hundreds of model endpoints, including image generation, video generation, image editing, video editing, lip-sync, face swap, inpainting, outpainting, extend, ControlNet, relight, upscale, and LoRA training.

Kling 3.0 video generation skill that invokes six endpoints via the RunComfy CLI, spanning Standard, Pro, and 4K rendering tiers in both text-to-video and image-to-video modes.

Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy, featuring multi-modal references and native lip-synced audio.

Extend an image beyond its original canvas via the RunComfy CLI, changing aspect ratio, uncropping, and filling in missing content while preserving the original.

Relight a still image via the RunComfy CLI, changing lighting direction, color temperature, intensity, or mood while preserving subject identity.

Edit images with Google Nano Banana 2 on RunComfy, supporting subject identity preservation, background swaps, localized edits with spatial language, and batch edits of up to 20 images.

Generate a Codex-compatible Codex Pet spritesheet.webp and pet.json from a single reference image via RunComfy, and install it into Codex's custom pet directory.

Edit images with Flux 1 Kontext Pro for precise local edits on RunComfy, with documented prompting patterns for sharper results.

Mask-driven image inpainting via the RunComfy CLI for object removal, watermark cleanup, and region replacement.

Edit images with OpenAI GPT Image 2's /edit endpoint on RunComfy, bundled with prompting patterns for sharper output.

Pose-conditioned generation on RunComfy via the `runcomfy` CLI, routing across Kling motion control, Wan 2-2 Animate, and Z-Image ControlNet LoRA.

Generate text-to-video with Wan 2.7 on RunComfy, featuring multi-reference conditioning, audio-driven lip-sync, and smooth transitions.

Generate images with Flux 2 Klein (Black Forest Labs' distilled fast variant of Flux 2) on RunComfy, bundled with the model's documented prompting patterns for sharper output.

Extend a video's spatial canvas via the RunComfy CLI, changing aspect ratio while preserving the central action.

Generate full songs and instrumental tracks with ElevenLabs Music on RunComfy via the `runcomfy` CLI, producing 44.1 kHz stereo audio from 5 seconds to 5 minutes.

Generate, inpaint, and outpaint music with ACE Step on RunComfy via the `runcomfy` CLI, featuring tag-driven composition, multilingual lyrics, and 5-second to 4-minute stereo output.

Generate text-to-video with HappyHorse 1.0 on RunComfy, featuring native 1080p, synchronized audio, and multi-shot character consistency.

Lip-sync a face to an audio track via the RunComfy CLI, routing across OmniHuman, Sync Labs, Kling, and Creatify models.

Generate AI music on RunComfy via the runcomfy CLI, routing to ElevenLabs or ACE Step models for generation, repair, and extension.