Recently updated open-source projects

open-campsite-watcher polls recreation.gov for the campground and nights you choose, compares each response with saved state, and sends a Telegram alert when a new cancellation appears. The alert includes a one-tap Add to Cart link, while expiry dates, repeat limits, and trips crossing months are handled for you. It runs as a zero-dependency Python watcher on macOS or Linux; booking remains a manual step.

Experience Skill searches Xiaohongshu, Doubao, Baidu, Zhihu, and Douyin for travel tips, tutorials, product advice, and everyday experience, then deduplicates and compares the results into a structured report. Each point carries a source so you can see where advice converges or comes from a single platform. It relies on browser automation, with the Xiaohongshu connector optional.

strong-ads-google-skill is for Google Search/RSA and Performance Max, not Meta or Instagram. It studies the business, competitor ads, and real buyer frustrations before producing angle-based headlines, long headlines, and descriptions that fit Google’s character limits. Pain points are tied to sources, and the output is organized for Google Ads Editor rather than padded with generic marketing language.

Harvey Specter Legal AI Skills provides separate UAE and US variants for preliminary research on company formation, healthcare licensing, employment, contracts, and selected intellectual property questions. The materials are designed to return jurisdiction-specific information with citations, examples, and risk considerations. They explicitly provide legal information only, not legal advice, and users should verify current law and consult a licensed attorney before acting.

This skill teaches a structured approach to dynamic programming: define the set of candidate solutions and its attribute, then partition by the last point of difference to derive a transition. It includes a reusable analysis template and examples for 0/1 knapsack, complete knapsack, interval DP, and longest common subsequence.

shva-marketplace is a small personal plugin collection for Claude Code, separate from the author’s product-specific tools. Its `shva` pack includes briefing, LinkedIn and Medium writing, teaching design, worksheet generation, GenAI use-case discovery, source finding, and persona profiling from text. Install it by adding the local marketplace and then the plugin; the marketplace is intentionally narrow and may grow over time.

schedule-reminder is a persistent, queryable store for todos, events, deadlines, and progress rather than a calendar UI. Its state machine covers pending, doing, done, blocked, and cancelled; a local Discord relay dispatches due reminders, while other skills can use the stable JSON CLI. It also handles idempotent ticks, missed-fire catch-up, retries, and concurrent read/write checks without becoming a cloud service.

fullstack-deploy takes a natural-language website idea through requirements, Supabase schema and access design, application development, GitHub repository setup, and Vercel deployment. It is aimed at prototypes and independent projects and can work with several Vercel-supported frameworks before handing back a public URL. The workflow still depends on the user’s third-party accounts, permissions, quotas, and regional access.

mogscore-skill opens the MogScore rating page in a visible headed browser, uploads a local selfie, triggers the score action, and captures the resulting report JSON. It includes installers for Codex, Claude Code, Hermes, and OpenClaw and uses Playwright-based scripts when the host cannot capture responses directly. Headless Chrome is explicitly unsupported because the local scan may fail, so the workflow needs an interactive graphical browser and an image upload.

Use renwei-zh to review Chinese product copy, reports, essays, or social posts for formulaic phrasing, promotional tone, overclaims, and dense pattern clusters. It marks numbers, dates, citations, and named sources as facts that must be preserved before producing a structural rewrite and follow-up audit. The project works as a Claude or Codex skill and as a deterministic Python CLI with JSON output; no API key is required.

bbyt applies Dan Martell’s Buy Back Your Time to a real workload. It calculates the Buyback Rate, sorts tasks through the DRIP audit, returns a prioritized offload list, and identifies the next hire on the Replacement Ladder. Other modes transfer a task into a Definition of Done and playbook, build an energy-matched Perfect Week, plan the year, or diagnose recurring time traps.

gtd operates Getting Things Done on your actual work instead of explaining the method. Give it a brain-dump, inbox, or vague task and it returns concrete next actions, projects with outcomes, waiting-for and calendar items, plus a short list of tasks that take under two minutes. It can also run weekly reviews and system audits, with every next action expressed as one visible physical step.

hom turns Andrew Grove’s High Output Management into a working advisor for real management problems. It diagnoses the underlying lever or bottleneck, then applies the relevant mechanics for delegation, one-on-ones, OKRs, decisions, organization design, motivation, or training. Responses are bilingual and grounded in the book’s terminology, with the emphasis on a concrete situation rather than a generic summary.

App Tester reads an app's navigation source, adds accessibility identifiers and structured logs, and drives end-to-end flows through agent-device on iOS, macOS, tvOS, or Android. It verifies steps with compact accessibility snapshots and console output, taking screenshots only on failure, and persists the screen graph and flows as YAML. Platform SDKs and Node.js 22+ are still required.

Tensorlake Skill is a lightweight instruction package that tells Claude Code, Codex, and similar agents to verify Tensorlake APIs against current documentation before suggesting code. It fetches the live documentation index, selects relevant pages for sandboxes, orchestration, or SDK tasks, and falls back to a bundled snapshot only when fetching fails. This is guidance rather than a runtime tool server: using Tensorlake still requires the appropriate Python, TypeScript, or CLI installation and the user's own API configuration.

Agent Sandbox Skill gives Claude Code, Codex, and Gemini CLI managed E2B environments for engineering work that should not touch the local filesystem or production systems. Agents can install dependencies, run untrusted code, scaffold and build full-stack applications, expose a hosted port, and perform Playwright-based visual checks. Commands cover small sandbox tasks as well as plan, build, host, and test workflows, with lifecycle tools that preserve a sandbox across turns. An E2B API key is required, and compute and hosted previews depend on the E2B service.

pentest-report normalizes existing penetration-test findings or scanner output into German or English reports and checks them against a selected BSI, OWASP, PCI-DSS, DiGA, or OSCP profile. It can detect missing fields, enrich findings with CVSS, CWE, OWASP, and MITRE references, deduplicate hosts, and render Markdown, PDF, or SysReptor JSON. It does not scan or exploit systems and does not certify compliance.

Apply the review layer to an HTML or Markdown artifact, select the exact phrase or element that is wrong, and add a note in place. Markup Mode compiles those comments into Markdown with quotes and locators so an agent can edit the intended spot without guessing. It runs entirely in the browser, changes only a generated copy, and declines client-rendered SPA shells by default.