Recently updated open-source projects

Shiprocket-API Skill pairs a stdlib-only cross-platform Python CLI with a Claude skill, keeping the API password and JWT out of AI context. It covers common order, courier, serviceability, tracking, and pickup-location queries and exposes a generic gateway for other endpoints. Requests use six safety tiers; a short-lived JWT is kept in OS-native storage with a restricted local-file fallback, while mutations require explicit flags and an audit log. The project is an early alpha, so audit the code and use --dry-run before production.

Pokedex presents information from all Pokémon generations through an animated application that runs across mobile and desktop platforms. Stable targets are listed for Android, iOS, macOS, and Windows, giving users a similar reference experience on several device types. A web build is also available, but it is explicitly marked alpha rather than stable. Developers who want to run the source can install its Flutter dependencies and launch it on a connected or configured device.

Name a book and Book Companion creates front matter that explains its shape, difficulty, pacing, and the honest case for or against reading it without spoiling the story. Depending on the title, it can also reconstruct what the original audience knew, outline the author's circumstances and chronology, and suggest useful translations, editions, or illustrations.

This skill translates the International Typographic Style into web layouts for coding agents. It supplies a 12-column grid, modular spacing, neo-grotesque type hierarchy, OKLCH color guidance, and a compact starter HTML skeleton. Accessibility, reduced motion, dark mode, print styles, and performance-minded rules are included, making it a useful starting point for editorial or agency-clean pages.

Google Map Voices collects public Google Maps reviews with SeleniumBase, supports several sort modes, merges duplicates, and saves fields such as text, stars, names, and dates to JSON. You can pass that file to Claude or GPT using the included analysis guide to extract positive quotes, pain points, and a concise insight. It is intended for small reconnaissance jobs, not paid bulk scraping or automated review replies, and Google’s UI changes may require maintenance.

Reality Citation Audit checks a LaTeX paper’s bibliography end to end. It verifies DOI metadata through Crossref and related sources, resolves anonymous authors and published versions, finds missing or dead entries, and tests whether citations actually support the surrounding claims. It can merge duplicate keys, rewrite references, rebuild the paper, and report remaining issues. A `.tex` project, `.bib` file, network access, Python, and LaTeX tools are required.

OSS Contributor helps aspiring AI engineers find and track open-source work instead of browsing random good-first-issue labels. It searches configured repositories through the GitHub REST API, filters candidates with a five-point verification, and monitors claim comments, pull-request status, and escalating deadlines. A small setup script stores per-project state in `.claude/oss-config.json`; the runtime uses only Python’s standard library.

Biz Fiction turns a real business person or event into an immersive long-form narrative. It uses cinematic scene changes, concrete details instead of stated emotions, layered dialogue, a six-part arc, and an open-ended final image rather than conventional business analysis. Its attribution license requires credit to the original author.

Feed the agent a mobile UI screenshot, a style reference, and a required description of the screen's behavior. It analyzes the layout, uses Gemini to generate image assets, and writes a browser-openable single-page HTML demo with a phone shell and real interactions. Individual assets can be regenerated, and the workflow requires a Gemini API key.

yss-overtime-submission reads attendance and effort data from ZenTao, applies mainland China workday, holiday, and makeup-workday rules, then compares existing Kingdee s-HR submissions before filling the form with Playwright. It supports dry runs and splits days longer than eight hours into multiple entries, but real submission requires an explicit --confirm after a person logs in. The default selectors target ZenTao plus Kingdee s-HR Cloud.

Devloop turns Claude Code into an unattended worker for a repository’s issue queue. For each task it branches, implements in small steps, builds and tests, opens a pull request, requests a fresh code review, merges, checks the live deployment, and logs the result before moving on. ScheduleWakeup controls pacing, while explicit stop conditions pause the loop for conflicts, product decisions, credentials, or guardrail violations. Because it can push and merge, permissions deserve careful setup.

Resume Writing Skill turns an unstructured career dump or an existing resume into three artifacts: a clean Markdown resume, a moderncv-banking LaTeX version, and a personalized teaching handbook. It diagnoses whether the problem is packaging or thin experience, compares the target role with current US job descriptions, and flags numbers that need verification instead of silently carrying them forward. It is scoped to US-market resumes, not cover letters or interview preparation.

Iterate is a meta-skill for improving other Claude Code skills through run evidence. An opted-in target records structured friction events, and Iterate accumulates them across runs before asking a read-only agent to propose an SKILL.md diff in a pull request. It never auto-merges, weakens deny rules, skips safety hooks, or changes files outside the target skill. Friction state is isolated per project.

Teams lets a lead Claude decompose a complex request, spawn specialized teammates, coordinate their shared task list, and synthesize the result. It chooses breadth for independent subtasks, depth for sequential research-to-test phases, or a mixed approach, with an optional voice per agent. The setup requires Claude Code 2.1.32 or later and the experimental agent-teams flag, and it caps a team at five agents.

OpenClaw Add Agent walks through adding a Telegram bot agent to OpenClaw. It collects the bot token, agent ID, optional display name, and an allowlist of user IDs, then updates `openclaw.json`, creates the agent workspace, and asks whether memory should be isolated. Afterward it tells you to restart OpenClaw. The skill assumes OpenClaw and its existing configuration are already installed, along with a token obtained from BotFather.

Taurine is a starter for combining a Tauri desktop shell with a Node.js server compiled into a sidecar binary. It gives web developers a ready React, Vite, Fastify, and tRPC setup that can be launched or built with the usual Tauri commands. The repository is explicitly experimental rather than a production foundation: it relies on a localhost protocol that Tauri discourages for security reasons, may not work on every platform, and only builds for the operating system running the build.

Interview Sim turns an interview protocol and a real or fictional persona into a text transcript with calibrated pacing, hesitations, self-corrections, and natural follow-up probes. It begins with an intake to align duration, language, scenario, interviewer style, and fidelity, then runs a self-check for persona consistency and fabricated claims. The output is text only, with one interviewer and one interviewee; it is not an audio transcription tool.

Agentic AI Security applies a five-category framework while an LLM-based agent is being designed or coded. It checks privilege and identity boundaries, configuration and segmentation, behavior risks such as specification gaming, structural risks such as tool injection and cascading failure, and accountability gaps in monitoring. The coverage spans design through operation, but excludes infrastructure hardening, model-training security, and regulatory compliance.