Shape agent capabilities into your workflow.

compbio-pi gives Claude Code an opinionated decision framework for routine computational-biology work, answering with a decision, reason, and next step instead of a menu of options. It favors simple baselines, reproducibility, interpretability, targeted ablations, and reviewer-style stress tests. The skill still asks the researcher before changing a core scientific claim or journal tier, purchasing new data or compute, seeking collaborators, or handling ethics and data agreements.

CLI Trainer guides a no-code fine-tuning run on Baidu AI Studio. It lists allowed models, checks dataset formats, recommends framework-specific hyperparameters, submits the job, polls its status, opens TensorBoard when available, and summarizes loss and artifact usability. It supports ERNIE through PaddleFormers and several open models through LlamaFactory, but requires Python, requests, an AI Studio access token, and network access to the training service.

Find What You Live By uses guided conversation to help someone derive personal principles from meaningful life experiences rather than adopting a generic list. Each principle is translated into observable behavior, and the skill is designed to preserve the user’s own language and agency. A quiet 30–60 minute session suits reflective work, but the project explicitly excludes acute crises, severe trauma, active psychiatric symptoms, and uncontrolled addiction.

Playing to Win applies Roger Martin and A.G. Lafley’s choice cascade to an idea, offer, codebase, or market move. It gathers context, labels claims as fact, inference, assumption, or speculation, tests the winning aspiration, where-to-play and how-to-win choices, and ends with one of five verdicts. Each run writes an offline interactive HTML page plus Markdown, with assumptions highlighted for follow-up validation.

Specdd turns a vague feature request into a tech-free specification and short plan before implementation. It scales the workflow from a small Quick change to a Feature or Project, asks only missing questions, and runs a production checklist for states, accessibility, keyboard use, mobile behavior, and observability. It works with coding agents that can read skill instructions and needs no dedicated CLI.

personal-brand-ops starts by identifying an audience-size stage, then routes founders, creators, or media operators to relevant frameworks and fillable worksheets. It covers positioning, content cadence and distribution, hiring, team structure, and monetization without giving the same playbook to every account size. The methodology is deliberately opinionated and does not cover paid acquisition, SEO, or visual design, so those areas need separate tools.

Use this Claude skill to design recommendation, feed, search-reranking, or task-prioritization systems as six stages: Source, Hydrator, Filter, Scorer, Selector, and SideEffect. It walks through the trade-offs between candidate sources, filtering, scoring, selection, and asynchronous effects, then emits a runnable scaffold in TypeScript, Go, or Python. Examples cover feeds, a Go module, and a FastAPI task ranker.

This skill structures the academic lifecycle into nine stages and lets Claude work in mentor, reviewer, or mixed mode. It can help narrow a topic, plan literature and methods, challenge experimental design and reproducibility, improve a manuscript, simulate peer review, prepare a rebuttal, and shape submission strategy. Phase-specific references provide checklists, prompts, and reviewer red flags for researchers who want both direction and rigorous self-review.

image-studio turns a plain-language design request into HTML and CSS, then renders it as a sized PNG or JPEG with headless Chromium. It supports ads, social cards, thumbnails, and other static formats, while its reverse-template workflow can convert an existing ad screenshot or URL into a parameterized template for versioning and batch variants. It requires Node.js and Playwright's Chromium download.

This skill separates Amazon seller intelligence into a deterministic feed stage and an editorial stage. A script collects eight configured public sources into raw JSON, then the agent writes Chinese, English, or bilingual digests with item-specific summaries; authenticated signals stay in stdout, and social publishing is never automatic.

This skill draws visually rich slide bodies in HTML and inline SVG, renders them to PNG with headless Chrome, and embeds the result through python-pptx. Headlines, footers, and page numbers remain editable native text while shadows, gradients, curves, arrows, and icons are rasterized consistently. The workflow includes verification through Keynote or LibreOffice and builds on Anthropic's PPTX skill.

This Claude skill drafts or critiques X posts against a policy set derived from public ranking code, Community Notes materials, and cited analyses. It can run a pre-flight review, explain failed checks, suggest rewrites, and advise on format, timing, or media. Confidence labels distinguish confirmed evidence from inference, and the project explicitly does not guarantee reach because ranking systems and learned weights change.

This skill lets Claude Code hand off expensive or specialized work to Google Antigravity CLI, including web research, image generation, codebase analysis, browser debugging, and scientific database queries. Claude receives the result without carrying the entire delegated workflow in its context. Users must install and authenticate the agy binary and set its correct path in the skill before use.

This Claude skill simulates a product team spanning product, architecture, design, frontend, backend, testing, operations, and optional specialists. It asks clarifying questions, supports standard, resource-constrained, and MVP modes, and moves work through Phase 0–5 with gates for requirements, design, security, testing, acceptance, risk, cost, and technical debt.

InferSpec reconstructs OpenSpec documents for brownfield systems by reading code, git history, project docs, and optional Jira, Confluence, or web sources. It creates one spec per capability, cites requirements to file lines or ticket IDs, marks ambiguity with GAP or TBD, and offers bulk scans, focused capability passes, and installed-skill updates without a separate model API key.

The review skill inspects Java 8, 11, or 17 code for issues such as null handling, monetary precision, thread safety, dated APIs, and concurrency choices, then writes an analysis file with priorities and a 1–100 score. After approval, the implementation skill applies the recommendations to a new *Modern.java file beside the original. Its rules are especially tailored to financial and messaging systems.

This skill processes a book into an optional Chinese translation, chapter-by-chapter reading notes, and a cross-chapter theme index stored in an Obsidian vault. It preserves chapter links and can export the translation as EPUB, PDF, DOCX, or Markdown; Python dependencies are required, while full-format export also needs Calibre and Pandoc.

jira-planner guides a free-form problem through research, estimation, structured ticket drafting, user confirmation, creation, and field verification. It reads and writes Jira Cloud through an Atlassian MCP server, with the optional acli tool used for faster read operations. The skill is tenant-agnostic, but it remains inactive until its local site and field configuration has been set up.