Find the open-source solution that fits.

Biomedical Research Analyst gives Claude a disciplined workflow for verifying a public dataset against the research question, choosing suitable statistics, and keeping data-derived findings separate from cited literature. Before delivery, it requires specific claims, pathway-gene assignments, thresholds, and inferential language to be checked against the underlying results. Included Python components support GEO parsing, differential expression, figures, and PPTX assembly, but the outputs remain hypothesis-generating unless the study design supports stronger conclusions.

storm-research adapts Stanford’s STORM method into a Claude Code skill that creates an outline and a citation-checked HTML briefing. It discovers a panel of perspectives or uses a fixed market panel, interviews them, records contradictions and open questions, and verifies source claims before rendering the report. The method is aimed at decisions and due diligence; simple lookups do not justify its multi-agent cost.

Travel Planner collects missing trip details in one round, then previews the itinerary, budget, risks, and every item it plans to write. After confirmation, it creates a linked Apple Notes itinerary and checklist, Calendar events for fixed times, Reminders for pre-departure tasks, and Apple Maps links. Writing to Apple apps requires macOS and the relevant AppleScript automation permissions.

Use the skill in audit, scan, guide, or harden mode to review a backend project. It detects the stack, maps the attack surface, traces untrusted input to dangerous sinks, checks dependencies and configuration, and reports verified findings with file locations, severity, and fix guidance. Its coverage is anchored to OWASP and ASVS, but it is not runtime testing, a professional penetration test, or a compliance program, and it does not edit code without approval.

Claude to Codex adds a /handoff command that packages the current Claude transcript, writes hot working context, captures a git snapshot, and starts an interactive Codex terminal. Durable details stay on disk while the prompt carries only hot state and pointers, so Codex can verify the repository before acting. Setup requires authenticated Claude Code and Codex CLI plus Node.js 22 or newer.

Give the skill leads, findings, files, or any other list that needs human judgment, and it builds one self-contained HTML page with a card for every item. Reviewers can mark keep, review, or drop, add notes, follow source links, and copy the final selection back to the agent. The page opens offline, needs no server or build step, and preserves progress in localStorage.

zuiti-jiafang handles client messages about discounts, extra requests, delayed payment, or restoring an earlier version without moving the deadline. It explains the implied cost transfer, then offers polite, pointed, and firm replies organized around scope, timing, definitions, and value. Its firmest advice stays within documentation, contract, and lawful remedies; it does not encourage threats, public shaming, or retaliation.

Ask about a container tradelane, port, liner service, carrier network, or freight-rate movement, and the skill searches public alliance documents, carrier releases, port statistics, indices, and trade reporting with citations. It bundles a research method rather than a dataset and excludes air, inland, bulk, and tanker transport. Exact rotations, transit times, cut-offs, and rates still need confirmation from the carrier or forwarder before a commercial decision.

Learn From Failure organizes sourced corporate case studies by failure mechanism, such as fraud, governance, cash burn, denial, or scaling too fast. Describe a decision and it can point to three to six relevant cases with the warning questions those companies raise, or you can browse the Markdown site and checklist without AI. It is a reflection tool, not a prediction engine, and its public cases should be checked against their sources.

ai-security-guard combines zero-dependency TypeScript runtime guards with a Claude skill for prompt injection, replayed-history attacks, privilege escalation, forged action markers, cross-tenant PII leaks, media abuse, and unsafe rendering. It can log blocked attacks and propose new patterns, but each candidate must pass a regression check before a human promotes it, so nothing becomes live automatically. The reference code uses Express-style functions that can be ported to other stacks.

claude-for-pro-max-user adds an absolute-mode communication style and a repeatable engineering loop: scope, explore, plan, implement, verify, and report evidence. Its references cover context budgeting, persistent CLAUDE.md rules, delegation, hooks versus skills, headless automation, and failure patterns. It is a protocol layer rather than a feature library, so its main effect is on how future sessions work and communicate.

Prompt Mentor turns a rough request into a clearer instruction before carrying it out. It activates only when invoked, scales its explanation from a quick fix to a multi-file project, and shows the revised prompt, implementation, concepts, takeaways, and final prompt used.

Use this skill to audit and rewrite resume layout so systems such as Workday, Greenhouse, Lever, and iCIMS are more likely to extract company names, job titles, and dates correctly. It targets specific parsing failures such as year-only ranges, fused header lines, stylized company names, and parenthetical titles, then adds pre-upload and post-upload checks. It does not improve or invent resume content, and no format can guarantee a perfect parse.

Give the skill a URL and it observes the site in a real browser, then converts its motion tracks, scroll model, assets, and design parameters into a structured specification, an implementation-oriented design manual, and an interactive timeline diagram. It is useful before rebuilding or studying a motion-heavy site, but it requires claude-in-chrome and network access rather than a headless browser.

angular-material-skill generates an AI reference skill for Angular Material and CDK from the official angular/components repository. A manifest pins the source tag, while release checks and a manual sync regenerate only changed references for review. The project is still marked as a v1 work in progress, and generated updates are never committed automatically.

yt-playlist-subs creates one ordered Markdown transcript from a YouTube playlist. It prefers creator subtitles, skips machine-translated tracks, uses local faster-whisper for videos without captions, and accepts an exported member cookie for restricted videos; each entry carries a source badge and silent clips receive an extra transcription safeguard.

wechat-article-formatter-skill converts Markdown into styled HTML for WeChat Official Account articles. It supports custom CSS, automatic image uploads, and quick export, letting authors choose an article, adjust its presentation, and save a publishable version. It is intended for writers who want to reduce repetitive copying and manual layout work.

AI Skill Hub is a collection of small AI skills for reducing repetitive operational work and making execution easier to see. Its Standup Agent can combine changes from Jira, GitHub, Slack, and meeting tools into structured updates while surfacing blockers and stale work; the collection is intended for quick, lightweight integrations.