Recently updated open-source projects

Describe a workload such as daily chatbot volume or document processing, and the skill applies provider pricing, token formulas, caching, and batch discounts to estimate the bill. It compares models across OpenAI, Anthropic, Google, DeepSeek, Mistral, and others while showing the math. Because model prices change frequently, its reference files need regular updates before budgeting decisions.

Docker Optimizer checks layer ordering, multi-stage build opportunities, base images, production dependencies, package cleanup, `.dockerignore`, working directories, and non-root execution. It can run as a Claude Code skill or a standalone TypeScript command, then reports concrete fixes and estimates how they may affect build time, image size, and cache reuse.

CI Doctor scans GitHub Actions configuration for Node.js version mismatches, masked failures, missing package caches, duplicate build steps, broken job dependencies, and artifact-sharing mistakes. It can run as a Claude Code skill or as a standalone TypeScript command, producing a readable or JSON report and a nonzero exit code when critical issues are detected.

Version Sync compares Node.js version declarations in `.nvmrc`, `package.json`, Dockerfiles, GitHub Actions workflows, and Docker Compose files. It can report mismatches or update every supported file to a target version, either as a Claude Code skill or a standalone TypeScript command. Dry-run previews and optional backups help control bulk changes.

Praxis turns requests such as data analysis, web scraping, page building, or media production into a tool-driven workflow in Claude Code. It analyzes the intent, selects tools, installs missing dependencies, and can use available credentials, create the appropriate output, or email the result after one confirmation. It requires Claude Code 2.1+, Python 3.8+, Git, and curl.

Skycenter analyzes pasted IAM policies, Terraform files, Kubernetes manifests, and other AWS, Azure, or GCP configuration material. It connects individual misconfigurations into attack paths with entry points, lateral movement, blast radius, MITRE ATT&CK mappings, detection gaps, and remediation. It does not connect to cloud accounts or call provider APIs, and is intended for authorized security assessment.

This fourteen-skill bundle gives Minis on iOS structured workflows for architecture, change-risk review, worktree isolation, root-cause tracing, test-driven development, browser validation, performance debugging, release readiness, deployment checks, incident triage, rollback planning, postmortems, and observability. It recommends an order based on the kind of task rather than applying every skill at once. The current scope guides safe decisions and verification, but does not yet provide a dedicated skill that executes full production incident recovery.

The pack separates risk in actions from risk in content. One skill governs shell commands, file changes, browser automation, uploads, personal data, and device-side effects; the other treats instructions found in webpages, PDFs, OCR, repositories, and logs as untrusted data. Both promote least privilege, read-only work first, explicit confirmation, and secret-exfiltration prevention, with shared review checklists, red-flag references, and adversarial test cases tailored to Minis on iOS.

Specify a research area, desired result count, and optional university or country to collect matching faculty information. The skill prioritizes official department, faculty, and research-group pages, then uses Google Scholar for publication context, returning public emails and recent papers in Markdown or Excel. Students should still verify the records before contacting prospective supervisors.

Using the fictional Ding Hai archetype as a memory aid, this skill organizes patterns such as self-righteous reframing, victim reversal, intimidation, and loyalty pressure into recognition cards and countermeasures. The default mode favors documentation, falsifiable questions, and escalation to a third party when appropriate. Writing, simulation, and sparring modes require explicit entry and preserve a counter-path, while the material is not a substitute for legal, mental-health, or real-world safety support.

Use the playbook directly or install its Claude skill to investigate slow training, low utilization, data-loading stalls, out-of-memory failures, weak multi-GPU scaling, and LLM serving latency or throughput problems. Its workflow starts with measurement, classifies the limiting resource, applies the smallest relevant change, and verifies the result. Separate guides cover training, inference, distributed systems, kernels, profilers, and recurring performance anti-patterns in code review.

Activate the skill for a session with `/diligence` to require primary-source checks for verifiable technical claims such as API signatures, hardware specifications, protocol behavior, and CLI flags. Claude also pauses for clarification when the platform, environment, constraints, or intended meaning are unclear. If a claim cannot be confirmed after several searches, the answer may proceed but must label what remains unverified and identify the sources already checked.

Use this skill when you want Claude to create a frontend, poster, dashboard, or editorial layout rooted in Bauhaus and Swiss International Typographic Style. It translates those traditions into concrete rules for mathematical grids, type scale, geometric forms, active whitespace, and restrained color. Web output is covered directly, with a separate SwiftUI adaptation, while gradients, shadows, and broad color palettes are intentionally excluded.

Describe the Notion workspace you need, such as a roadmap, team dashboard, content calendar, kanban board, or PARA system, and the skill guides Claude through a structured design. It combines visual conventions with practical database architecture, relations, rollups, formulas, and native automations, making it useful for people building a coherent workspace rather than a single isolated page.

AI Video Tracker packages a model snapshot into a Claude Code and Claude skill for comparing leaderboard signals, public access, approximate pricing, and notable background details. Its editable JSON dataset is useful for quick recommendations and forks, but the bundled v1.0.0 snapshot was captured on April 9, 2026, so rankings, availability, and costs should be checked against live sources before making a current selection.

Use this Claude Code skill to audit interfaces or propose UX changes with cognitive biases and behavioral principles organized around information, meaning, time pressure, and memory. It can support behavioral reviews, pricing and onboarding recommendations, client briefs, and training. Its ethical guardrails favor transparent nudges over manipulation, reject false scarcity or urgency, and require clear ways to cancel, leave, or unsubscribe.

prd-writer interrogates each feature for its data source, business rules, and exception handling before designing the document and drafting each section. It includes explicit non-goals, Given/When/Then acceptance criteria, metrics, and owned open questions, followed by a self-review for completeness and testability. Word export requires the companion document-generation skill, and Chinese PRDs also require the documented Chinese string-handling fix.

Run a seven-phase workflow on Atari ST PRG, TOS, ACC, or raw binaries to identify sections, system calls, data regions, and subroutines. The skill coordinates analysis and review, then produces an annotated 68000 listing, a technical analysis, a user manual, and a context file for later sessions. Its tooling is designed for games, demos, GEM applications, utilities, and other Atari ST software.