Explora publicaciones de X revisadas sobre Skills, las personas que las comparten y los proyectos que mencionan.
El recuento incluye solo publicaciones sobre Skills recopiladas y revisadas. Un día vacío significa que aquí no se ha recopilado ninguna. Fechas en UTC.
28 publicaciones recopiladas
The author shares a Roblox VFX and animation Skill covering particles, beams, trails and character motion, with a workflow for checking captured frames in Studio.
Zen_with_AI recommends cathrynlavery's Skill for: 一句话生成自包含 HTML+SVG 图（45 种图型：架构/时序/桑基/爆炸轴测等），审美规则内置. The poster is a recommender, not the author.
rryssf recommends LilMGenius's Skill for: 28 个「做减法」agent skills（debloat/删除冗余等低层设计模式），教 agent 主动精简而非只加代码. The poster is a recommender, not the author.
Zen_with_AI recommends android (Google)'s Skill for: Google 官方 Android 工程 Agent Skills（Compose/CameraX/Navigation/R8/Wear/TV/XR 等最佳实践）. The poster is a recommender, not the author.
Autohand releases four Skill packs for code review, Next.js App Router, Rails and Django. Each pack provides task-specific playbooks rather than a single representative Skill.
Creator released a Skill that turns a written plan into a narrated explainer video (plan → narrated explainer MP4).
Fardeen shares an Android TV cleanup Skill that starts from the TV model and the apps to keep, with setup and rollback steps.
Dhruv releases transit-lab, a Skill that turns natural-language birth details into sourced Jyotisha charts covering local time, nakshatra, D9 and Vimshottari dashas.
Fluyeporlaweb recommends cathrynlavery's Skill for: 生成可双击打开的品牌化架构/流程/象限等 HTML 图（非乱盒子）. The poster is a recommender, not the author.
QingQ77 recommends 1weiho's Skill for: 按电影感机位/焦平面/打光剪辑参数，把产品界面拍成发布短片. The poster is a recommender, not the author.
Sketchbook Style turns an object into an industrial designer’s sketchbook drawing, with pen, marker, ink and contrast variants using open image models.
Huashu Motion creates product launch videos as editable code. The author demonstrates a workflow that offers visual directions, renders a film and accepts comments on specific frames.
OpenScreen combines screen recording with agent-directed edits such as zooms, cuts and captions. The author demonstrates a repository video made from a short request.
The maintainer introduces Research Agent Skills, a collection of playbooks for literature reviews, citation checking, scientific writing and research workflows across disciplines.
0xGky recommends joeseesun (X vista8)'s Skill for: 沿搜索链路排查抓取/JS渲染/收录/Canonical/内链与意图匹配的 SEO 审计与诊断. The poster is a recommender, not the author.
COVENANT introduces a Skill for inspecting paid API requirements before an approved payment, keeping discovery separate from wallet, credential and settlement actions.
Qian Xigua demonstrates video-privacy-blur on a video containing a phone number: the author says it checked 5,116 frames and exported a separate copy while retaining duration, dimensions, and audio.
Agent Glyphs helps agents find icons by meaning and visual style, export SVG or React assets and retain attribution.
Room Kang Ali shares three VulnVerify Skills for triaging web vulnerability reports, building proofs of concept and checking false positives.
dontbesilent updates the dbs router to read each Skill’s handoff metadata and coordinate multiple Skills for one task.