القائمة
استكشف منشورات X المراجَعة عن المهارات، ومن يشاركونها، والمشاريع المذكورة فيها.
يشمل العدد فقط منشورات المهارات التي جُمعت وروجعت. اليوم الفارغ يعني عدم جمع منشورات هنا. التواريخ بحسب UTC.
54 منشورات جُمعت
A Skill for drafting and revising Japanese prose in Codex with Gemini. Codex prepares the facts and brief, while Gemini handles the wording through gemini-ja. The source requires an existing Antigravity CLI login.
The author shares an open-source AI film crew with 11 Skills, from screenplay and visual design through sound and final editing. A 26-second film illustrates the workflow in Claude Code and Codex; the post emphasizes the recorded production decisions as well as the finished film.
The creator introduces biaodian, a Chinese punctuation Skill grounded in GB/T 15834-2011. A mechanical scan and semantic review produce an issue list, explanations with source references, and corrected text. It changes punctuation without rewriting words, numbers or style.
The author shares douyin-download for fetching one Douyin work from share text, a link or an ID. It can save the available original images, clean video stream, Live Photo media and BGM, with metadata and SHA256 checks. It requires a logged-in browser and does not collect creator profiles in bulk.
Chooses writing, diagrams, interactive pages, or video around a learning goal and audience, then gives a reusable prompt with its rationale. Actual artifact creation is a separate request.
This recommendation highlights a Codex Skill that turns keywords, articles, files, and screenshots into Xiaohongshu knowledge posts. It researches the topic before planning the pages and creating the image cards.
Packages a character-replacement video workflow, from reference-video checks and reusable character profiles to prompts and comparison clips.
A recommendation of yomiyasu for rewriting stiff AI-generated Japanese. The Skill works on technical articles, business documents, and essays while preserving the source’s meaning and constraints.
This share highlights qisi-video-remix, which adapts a reference video into a new script, character and scene plans, storyboards, and copyable prompts for each video segment. The repository’s default deliverable is a production plan.
Claritymaxx's explain skill reads the source material and builds a mental model before choosing prose, a diagram, or an HTML explainer. It separates what the source shows from what the explanation infers.
A recommendation of ip-as-logo for rounded square mascot images with simple silhouettes and a solid background. The workflow proposes design directions before generating a set of independent candidates.
The vgpu Skill guides Blender modeling, baking and asset validation for web projects, alongside version-matched WebGPU documentation.
Shares an explain skill for Claude Code that chooses plain text, diagrams, HTML reference sheets, or a requested video, with simplified technical English and an everyday-analogy mode.
Pratzyy shares dissect, a Claude Code Skill that measures a reference video and writes a reusable production blueprint. His Kurzgesagt comparison shows an original short beside a remake made from the blueprint; the Skill itself produces the blueprint, rather than rendering the remake.
Peng Chujin releases LiveCanvas, quoting his own Live image demo. The Skill researches a topic, plans a cover and storyboard, then renders an animated information card with Remotion and packages Apple Live Photo resources in a supported macOS environment.
The author shares six Douyin transcript workflows: single videos, three-video trials, full archives, resuming, metric updates and separate proofreading.
The creator explains how yomiyasu uses sentence structure to make AI-generated Japanese easier to read.
Guizang describes a daily AI news video workflow in Muse: curate notes and media, then use Pi with K3 and GLM 5.3 to assemble a video with guizang-product-video-skill and return it in chat. This is his own integration example.
Rewrites AI-generated Japanese into clearer prose by fixing sentence structure and vague metaphors. Works with Claude Code and Codex.
The creator shares Zuse’s launch-video Skill in a same-author reply. The workflow combines HyperFrames, accurate Zuse UI, Blender assets and music timing for continuous product and partner-announcement films.