Measures a research replication package's peak RAM and memory trace, including child processes, then records the measured requirements and evidence in its README.
Comunidade de Agent Skills
Explore publicações revisadas no X, quem as compartilha e os projetos mencionados.
Publicações por dia
208 publicações coletadasA contagem inclui apenas publicações sobre Skills coletadas e revisadas. Um dia vazio indica que nada foi coletado aqui. Datas em UTC.
Publicações recentes
208 publicações coletadas
The vgpu Skill guides Blender modeling, baking and asset validation for web projects, alongside version-matched WebGPU documentation.
The author releases a Claude Code plugin marketplace with two named Skills: dev-flow for resumable engineering changes across multiple pull requests, and dependency-audit for reviewing CVEs and outdated packages.
Google Traffic combines GA4 and Search Console reports for project-specific traffic, page-performance, and indexing reviews.
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.
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.
Build a private Markdown knowledge base from your WeChat history. GreenBubbles supplies live chat access; the personal-memory Skill organizes and updates the notes.
Review SwiftUI code for deprecated APIs, accessibility gaps and performance pitfalls. SwiftUI Pro reports issues by file with suggested fixes.
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.
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.
The author shares six Douyin transcript workflows: single videos, three-video trials, full archives, resuming, metric updates and separate proofreading.
Collects two layers of Douyin search suggestions with Codex, scores commercial intent, and exports the results to Excel.
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.
Average AI Bro quotes a prior anti-slop recommendation and links its rules and Skills for reviewing generic interface patterns, filler copy and code comments.
Rishi introduces remembrandt, an open-source Skill and CLI for storing project decisions and recovering them in later coding-agent sessions. Memory is kept as local JSON entries and a generated Markdown summary.
Scar3croW recommends Emil Kowalski’s review-animations Skill for focused motion-code critique. It checks why an animation exists, how it responds, its performance and accessibility, then reports concrete findings and an explicit verdict.
Advancedcskills shares eight construction-office Skills for minutes, site diaries, RFIs, inspection records, variations, defects, tender comparisons and inbox triage. The source pack stops at drafts and human approval, without inventing missing numbers or making commercial commitments.