確認済みの X 投稿から、Skill の実践例や共有者、言及されたプロジェクトを探せます。
集計対象は収集・審査済みの Skill 関連投稿のみです。空白の日は本サイトで未収集を意味します。日付は UTC です。
289 件の収集済み投稿
Uriah, an actual contributor to impeccable-rust, shares the Rust review and verification Skill and says he used it for OpenGrok. Its source organizes checks around failure risks and explicit evidence limits.
Launch Video Craft brings real product UI into Remotion launch films, with checks for clicks, zoom framing, and rendered frames before delivery.
Boring Video Studio reorganizes video planning into 11 coordinated Skills, from topic research and an approved article to narration, scenes, and a storyboard, with production handed to HyperFrames.
Dani shares a before-and-after paragraph using a local adaptation of Peter Yang’s no-ai-slop rules to remove press-release phrasing while keeping the writer’s voice.
Orbital Desk built Honeypot as a free, machine-readable index of AI agent Skills. Agents can read one JSON file to find entries and their installation instructions, without signing up.
animation-performance gathers rules for diagnosing dropped frames, including animated shadows, large blur values, inherited CSS variables, and a busy main thread.
Sahil Gulihar asks users to try Dispatch, a Skill for consulting external coding-agent CLIs and evaluating their responses within the current workflow.
The boss-skill creator explains why copying Skill files does not ensure hooks are connected. The project tracks installed files with a lockfile and checks expected files across target agents with an installation test matrix.
Oil UI’s author reports new insights and simpler debugging scripts. The post’s pictured works use Oil UI Pro; the linked open-source Skill focuses on design directions, comparison, and screenshot-based refinement.
dontbesilent explains how to start with the dbskill toolkit: its onboarding conversation introduces the available Skills and helps users choose an entry for their current task.
Email Assistant writes concise emails while preserving facts, deadlines, commitments and tone. Its creator also separates reading and drafting from authorized actions such as sending, forwarding or deleting.
stop-describing-ui trims explanatory text from generated interfaces and replaces vague labels with specific actions. Its rules retain critical consequences such as deletion, charges and customer notifications.
grim:lock-in helps resume work after a context switch by reconstructing the current project state, open loops, and three small next steps.
communicate-clearly helps revise handoffs and explanations without changing their meaning. The author’s thread emphasizes preserving requirements, recommendations and what has actually been verified.
Paweł Huryn answers how to use his work-humanizer Skill on pasted workplace text. In the linked author post, he emphasizes preserving facts, commitments and meaning when revising AI-sounding business prose.
An imagegen Skill brings APIMart image generation into Claude. Its creator built it for workflows that need higher-resolution images.
motion-render turns an explanation topic into a Claude Motion animation with Gemini narration and Lyria background music, then assembles an MP4. The creator shares a video demonstration of this workflow.
Marco highlights /render, his text-to-3D Skill using build123d and a browser viewer where models can be inspected and edited.
songci-guofeng-visualizer turns a Song-dynasty ci poem into character and scene designs plus image and video prompts. The creator describes using Liu Yong’s “Wang Hai Chao” for a 23-shot video example.
backend-performance-review examines backend code with evidence and workload context, and forbids invented performance numbers. The creator shares a test series comparing speculative review advice with findings that identify their evidence and unknowns.