Recently updated open-source projects

Analyze a YouTube video by combining a downloaded 720p file, scene-change frames, a NotebookLM transcript and briefing, and Claude's multimodal reading. The skill writes a structured Markdown synthesis with a TL;DR, technical stack, step-by-step workflow, annotated frames, quotations, and actionable decisions. It requires yt-dlp, ffmpeg, the NotebookLM CLI, and an authenticated NotebookLM session.

Use the two skills when an AI coding task needs code from elsewhere without pulling in an entire repository or runtime dependency. One extracts the smallest useful unit with a provenance comment; the other vendors only the slice you own, records its origin, trims unused parts, and supports selective resync. They are aimed at keeping borrowed code deliberate and maintainable.

Keito Time Track installs lifecycle hooks for Claude Code and Codex, maps each Git worktree to a Keito company, client, project, and task, and records one agent-sourced time entry when a session ends. Credentials stay with the Keito CLI, while the repository stores only local identifiers in `.keito/config.yml`. Each repository needs its own setup, and the best-effort hooks log failures without breaking the coding session.

GameClaw is a self-hosted app and agent skill for recurring account chores across HoYoLAB, Miyoushe, Kurogames, and Skland-supported titles. Its live layer covers check-ins, community tasks, account listing, selected redemption codes, and some real-time status queries, with natural-language plans that can be previewed and saved for scheduled reuse. Mail claims, stamina spending, dungeons, and automated battles are listed as later or limited capabilities.

claude-skill-informe-pericial helps Spanish architectural experts assemble construction-pathology reports as versioned DOCX files. It brings case materials, photos, budget lines, and Word revisions into one workflow, including imports from PDFs, notes, and Presto or Arquímedes. The signed report remains the professional's responsibility: experts must validate causation, responsibility, and repair proportions, and complex revisions or other budget formats may need manual handling in Word.

Recover mistyped English messages without retyping when the Israeli Hebrew keyboard layout was active. The skill detects likely gibberish, maps Hebrew characters back to their physical QWERTY keys, preserves real Hebrew and mixed text, and includes a deterministic Python decoder plus an optional prompt hook. It also has a reverse mode for English-to-Hebrew mistakes; other layouts are not included.

Claude Skill Mesh turns connected MCP services into a self-organizing set of readable agent specifications. It discovers available tools, observes recurring patterns and bottlenecks, spawns specialized agents for worthwhile automations, and periodically promotes, merges, or prunes them. A registry, short observation window, digest, and per-agent logs keep the state compact. It requires at least one MCP connection and is designed for Claude workflows rather than a standalone runtime.

Use this Claude Code skill to turn a loose coding request into a condition with a clear end state, visible proof, scope safeguards, and a turn limit. It includes six task patterns, worked examples, and eight rules for avoiding weak completion criteria. You still need to supply project-specific commands and boundaries; the template does not verify the work itself.

video-context lets Claude inspect a video by extracting scene-change frames and an audio transcript from local files, public URLs, or authenticated private URLs. ffmpeg finds and caps keyframes, yt-dlp resolves supported web sources, and whisper-cpp supplies an optional transcript. ffmpeg is required, the transcript model is an extra download, and Windows installations need manual setup.

Prompt Architect treats prompt writing as an engineering exercise. It diagnoses the task, asks for constraints, recommends suitable frameworks, drafts two or three alternatives, and scores them for clarity, specificity, context, completeness, and structure. The skill includes eight prompt frameworks, agent patterns, and anti-pattern examples, with model-specific guidance for Claude, GPT, Gemini, and local models. It returns a recommended version with tradeoffs and hallucination-risk notes.

Design Log adds a gated Stop & Think protocol to Claude Code development. It asks clarifying questions, researches several sources through an MCP tool, explores the repository in plan mode, records the design, waits for one approval, and then hands unfinished checks to testing. Projects need a design-log index and research-tool configuration, and the workflow does not auto-merge to the main branch.

Use this Claude Code skill to move a smart-home idea from discovery and scenario design through prioritization, a 16-section PRD, hardware requirements, communication protocols, and firmware architecture. Its reference set covers 30 automation scenes, more than 50 chips, 178 vendors, and over 40 certification standards across categories such as locks, lighting, security, and environmental control. Vendor, component, and standards data should be rechecked before a real launch.

Stem Cheat Sheet helps students turn course materials and past exams into a compact, exam-targeted reference. It asks about weak topics and page constraints before laying out source-grounded formulas, recognition rules, procedures, traps, and small examples. The generated PDF must be checked against the allowed page count, paper size, sides, color, and example policy. Without shell access, it can still produce HTML but cannot verify the printed page count.

CoFoundr’s handoff and pickup skills keep a multi-session coding epic in one living Markdown file. Handoff appends completed features, decisions, files, debt, and session notes, while pickup briefs the next session on current state, remaining work, open questions, and priorities. The document is archived only when the epic ships, so context accumulates instead of scattering across dated files. These skills manage continuity, not implementation.

This sample demonstrates how a Windows WPF application uses MSAL.NET to obtain an access token and call Microsoft Graph through the Microsoft identity platform. It is preconfigured for a quick run in Visual Studio, while developers can replace the supplied coordinates with their own app registration. Its token cache uses DPAPI, so the cache file must be removed before moving a built application to another machine.

This collection provides four Claude Code skills for Adobe analytics work: conceptual guidance for Adobe Analytics and Customer Journey Analytics, server-to-server OAuth setup for AEP and CJA APIs, and SDR generation with Data View comparison and configuration tracking. Skills can be installed individually or copied together.

Issue Creator turns a bug, feature request, or infrastructure need into a repository-aware GitHub issue. It inspects the code to cite verified file and line locations, searches for duplicates, follows repository templates and triage rules, and prepares acceptance criteria without prescribing the fix. A full preview appears before `gh issue create`, and publication waits for approval. It does not implement changes, open pull requests, or triage existing issues.

Drop lecture PDFs into the input folder and run the Claude Code skill to produce a site configuration and deployable HTML containing equation sandboxes, flashcards, multiple-choice quizzes, diagram labels, and concept checks. It targets students, instructors, and ed-tech builders, but the pre-0.3 packages are not yet published, so the repository must be cloned, installed with Bun, and served over HTTP for local use.