The author packages DeepSeek Search and Fetch into a Skill for source-backed research and reading web pages.
Community für Agent Skills
Entdecke geprüfte X-Beiträge über Skills, die Menschen dahinter und die erwähnten Projekte.
Beiträge pro Tag
21 erfasste BeiträgeGezählt werden nur erfasste und geprüfte Beiträge über Skills. Ein leerer Tag bedeutet, dass hier nichts erfasst wurde. Datumsangaben in UTC.
Neue Beiträge
21 erfasste Beiträge
Erik MacKinnon shares ambition, a Skill that asks the user and agent to define a more ambitious outcome, useful methods, and a way to judge success before work begins.
JC shares how-it-works, a Skill that reads the current codebase and creates or updates HOW_IT_WORKS.md for a product owner. It traces a user request and separates behavior backed by evidence from code that has not been verified in use.
Recommends penciled for pencil-style architecture diagrams, highlighting its layout checks and the author’s browser-based visual feedback loop. The post explains how a deliberately sketch-like style can invite discussion.
Shares a food-delivery architecture diagram made with SeeCode, showing connection highlighting and component details on interaction. Recommends the Skill for technical explanations and presentation material.
yourturn creates interactive explainers, guided code reviews, presentations and decision documents. Comments and feedback from the page go back to the agent harness.
SeeCode turns a short brief into an animated diagram you can explore by tracing, focusing and following a route. This creator update describes 45 diagram types, brand styling, Mermaid input and SVG, PNG, GIF or MP4 export.
The creator invites people to try yourturn while continuing to dogfood it. The Skill builds interactive browser pages for explanations, walkthroughs, diagrams and reviews, and can collect structured user input in the same page.
Yuya introduces a Skill for creating Japanese explainer-style HTML pages with Zundamon and Metan. His demo shows the dialogue format within YES, a plugin containing several tools for learning and explanation.
djfunboy shares a favorite Skill that turns 'explain how X works' into a diagrams-first, self-contained HTML workflow document.
The creator turns a four-tier explanation framework into an open-source Skill: controlled technical English, structural diagrams, interactive HTML and narrated Manim animations. It also includes a local prompt compiler and linter.
The author shares materials-simulation-skills after its inclusion in Kimi’s Claude Code collection. The repository gives agents instructions for numerical stability, convergence and simulation workflows, with the stated aim of getting the simulation right rather than merely running the code.
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.
Turns a photo of six-line guitar tablature with jianpu into a play-along page, with a moving cursor, synchronized melody and accompaniment, tempo control, and loops.
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 book-to-skill, which turns technical books and document collections into a reusable Agent Skill with frameworks and chapter references that an agent can load on demand.
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.
Brings Kun Chen's public engineering knowledge into your agent, using the same knowledge base as his Grok bot.
Melvin introduces challenge-ideas in his devils-advocate plugin for Claude Code and Codex. It tests assumptions, weighs counterarguments and alternatives, and gives an evidence-based provisional recommendation without disagreeing merely for effect.
Leo introduces x-reader v0.3.1 and its source-first approach: read the original link and report what is still missing. The post describes a webpage fallback and distinguishes retrieved X text from attached media that has not been read; those update examples are the author’s reported results.