Agent Skills en tendance

Makes SDK, API or protocol documentation something a coding agent can integrate from unattended - crawler access, machine-readable entry points (llms.txt, markdown endpoints, OpenAPI and JSON Schema files), self-contained copy-paste-safe pages, and a measured first-attempt agent success rate.

Generate images with Pruna P-Image models via inference.sh CLI, supporting text-to-image, image editing, LoRA styles, and multi-image compositing.

Generate and edit videos with Alibaba HappyHorse 1.0 models via inference.sh CLI.

Run influencer, creator, or ambassador partnerships to promote your product—covering partner discovery, deal structuring, creative briefs, compliance, and ROI measurement.

Chooses the business model for a developer tool - proprietary SaaS, open core, hosted open source, support and LTS subscription, dual licensing, source-available, consumption metering, marketplace take-rate, OEM licensing - and the go-to-market each one forces.

Generate and edit images with OpenAI GPT-Image-2 via inference.sh CLI.

Generate AI videos via the RunComfy CLI with smart routing across the full video-model catalog, covering text-to-video, image-to-video, and video extension.

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

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

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.

Optimize in-app paywalls, upgrade screens, and feature gates to convert free users to paid.

Guide for writing idiomatic Rust code based on Apollo GraphQL's best practices handbook.

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

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.

Turns support tickets, issue history and error telemetry into troubleshooting and error-reference pages a developer finds by pasting the error string - symptom, conditions, cause, fix and verification entries, an error-code catalog generated from one source of truth, and fixes wired back into the product's own error output.

>

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

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

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

Defines the policy every code sample in developer documentation must meet and audits an existing sample corpus against it, returning a ranked fix queue.

仕事の日本語文書を読みやすくわかりやすく書く・直すためのスキル。議事録（文字起こしからの議事録化を含む）、調査レポート・分析レポート、社内ガイド・マニュアル、リサーチメモ・ディスカッションペーパー・企画書・提案書・報告書・メール、スライド構成案といったビジネス文書の作成・校正、「結論から書いて」「論旨を明確に」「見出しを端的に」「専門用語をわかりやすく説明して」といった指示のいずれでも使用する。AI臭さの除去（「AIっぽい」「AI臭い」「機械翻訳っぽい」「不自然」「もっと自然な日本語に」「機械っぽい」「人間っぽくして」「単調」「〜することができる、と言えるだろう、のような言い回し」といった直接・間接・口語の指摘、AIで書いたと言われた/疑われた）、読みにくい・わかりにくい文章の改善依頼（語順がおかしい、一文が長い、何が言いたいか分からない、読点の位置がおかしい等）、note記事やブログ記事・エッセイの新規執筆（任意のテーマをゼロから書く・書き起こす依頼を含む）、既存文章のリライト・推敲、AI臭さの診断・採点（「この文章AIが書いた？」「AI臭さをスコアで出して」「どれくらいAIっぽいか判定して」という書き換えを伴わない依頼）、自分の文体を学ばせたい・プロファイル化したいという要望（過去の文章を読ませて自分らしく書いてほしいという依頼も含む）にも対応する。禁止語の除去、リズムの単調さ・段落構造の均質さ・英語統語の直訳調に加え、語順・読点・一文一義・主語述語の距離といった読みやすさの原則にも対応する。技術文書の章構成やMarkdownフォーマットの整形自体（一文一行化・引用ブロック・脚注記法など）は対象外——それは別スキルの領域であり、本スキルは文章の自然さ・読みやすさ・わかりやすさに特化する。

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.

MUST USE when reviewing ClickHouse schemas, queries, or configurations.

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.

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

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

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.

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.

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

Create and manage tickets at every level — slice an initiative into epics, break an epic into stories, write or refine a ticket, and run the board (publish, ready, move, assign, status, cancel).

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

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 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.

Operate email via the agently-cli command-line tool: send, reply, forward, search, read, download attachments, and manage the inbox.

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

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.

Extend or continue an existing video clip on RunComfy via the `runcomfy` CLI, using Google Veo 3-1's extend-video endpoints to produce a coherent continuation.

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

The convex-deploy-guard skill classifies and announces the target Convex deployment before any deployment-affecting command, requires fresh explicit consent for production actions, and supports session read-only mode.

Plan, build, and optimize SMS/MMS marketing campaigns including welcome flows, abandoned cart, post-purchase, win-back, promotional, and transactional texts, with TCPA and carrier compliance.

Convex is an all-TypeScript reactive backend platform where database, server functions, scheduling, file storage, auth, and realtime sync are one type-safe system, every function is a transaction, and tsc catches most mistakes before deploy.

When the user wants to earn backlinks or third-party mentions that lift rankings and AI citations.

Sort many texts into your own categories without reading them, using a keyless HTTP API that returns a calibrated confidence per answer.

A single feature card orbits a dot sphere on approved Blender camera motion.

The RevOps skill helps design and optimize revenue operations systems that connect marketing, sales, and customer success, covering lead lifecycle, scoring, routing, pipeline management, and CRM automation.

The marketing council skill convenes a simulated board of legendary marketers to provide multi-perspective takes, disagreement mapping, and a synthesized recommendation.

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

Writes a developer community's code of conduct and the moderation playbook behind it - scope, enforcement ladder, reporting channels, incident-response runbook, moderator roster, platform controls.