Shape agent capabilities into your workflow.

Zenith Audience adapts Elias Mamã's Audience method into a Claude Code plugin that connects trend research, idea development, scripting, pre-publication checks, metrics review, and weekly planning into a daily content workflow. It uses specialized agents and slash commands and includes HTML script templates.

openrouter-image-mcp gives Claude Code, Claude Desktop, Cursor, Codex, and other MCP clients one tool for generating or editing images through OpenRouter. It supports six aliases, aspect-ratio hints, automatic file extensions, multi-image saves, and clearer 401, 402, and 429 errors.

This Claude Code skill curates about 40 Paul Graham essays across high agency, startup ideas, founders, growth, fundraising, product, and mental models. Trigger rules surface the relevant frame during a founder conversation, with short fair-use excerpts and canonical links, but no current news or legal advice.

LaTeX Academic Publisher turns structured research into compilable papers using IEEE, MDPI, Elsevier, Springer, ACM, Nature-style, or plain templates. It scaffolds sections, manages BibTeX, places figures and tables, explains compilation errors, supports focused builds, and packages a clean submission archive.

SNU Library Scholarly Access uses a Seoul National University library account and Playwright to check supported domains, create proxy URLs, discover article PDFs, distinguish full text from supplements, and download files. It offers CLI commands plus an optional MCP server with browser-profile and timeout options.

Crack the Paper turns papers, technical reports, long-form articles, PDFs, and arXiv links into structured reading notes. It follows figures or claim clusters, questions methods and alternative explanations, tracks later work and reception, and connects the material to the reader's research or courses.

img-deck guides Claude Code through content planning, editable white frames, a shared design system, slide prompts, image generation with kie.ai's GPT Image 2, and final PDF assembly. Two confirmation gates precede generation, while helper scripts support local editing, previewing, and packaging.

council-review sends a project, system, document, or plan to three to six blind reviewer lenses in parallel, then has a chair synthesize agreement, tensions, strengths, and prioritized recommendations. It is report-only and never edits the subject under review.

semantic-web-fetch treats a page's declared profile as the authority for meaning: only bound elements count, missing facts remain unfilled, and links are described by their operation and state transition. semantic-web-write creates readable HTML with an ALPS profile, stable bindings, and local checks.

This Claude Code skill reviews AWS spend through the CLI and Cost Explorer, breaking costs down by service, region, and resource while explaining usage and recent activity. It separates reversible savings from larger changes that need confirmation, stays read-only by default, and can create a self-contained HTML dashboard.

mimic helps an agent turn MediaPipe Unity Plugin samples into real-time webcam interactions for pose, hands, face, gestures, objects, or segmentation. It covers intake questions, scene selection, landmark and coordinate references, 2D/3D mapping, and the thread-safe callback-to-Update integration pattern.

goalify researches a repository, locks the few decisions that matter, and writes a self-contained /goal file with absolute paths, commands, progress, and success criteria. A fresh Claude Code session runs it after /clear, and the file cleans itself up only when every check passes.

Obsidian Study Guide Builder turns lecture PDFs, study guides, and notebooks into an interlinked vault of concept notes, formula walkthroughs, lecture teaching notes, visuals, animations, and spaced-repetition cards. It asks about scope and build cadence, shows a sample, then generates and verifies the rest.

Use anneal when several plausible approaches compete and intuition may mislead. It turns the goal into measurable questions, sketches two or three directions, prototypes them cheaply, selects by a direction-fitness score, and only then applies a separate polish rubric. It is a lightweight human decision discipline, not an autonomous engine, and this repository is a legacy mirror.

Define what better means in program.md, then let the agent make one change per experiment and score it against a frozen evaluator. Improved artifacts are committed; regressions and crashes are reverted, with every attempt logged in results.tsv. The workflow covers code, prompts, content, models, and configs, but the evaluation boundary must stay immutable.

Give the skill a claim and public data, and it checks nine common pitfalls including Simpson’s paradox, survivorship bias, relative-risk inflation, base-rate errors, selection bias, and uncorrected multiple comparisons. It produces Markdown, journal-style HTML, and a dashboard PNG while retaining supported positive scenarios. It is a warning tool, not professional medical, statistical, or legal advice.

This adaptive Claude skill supports Brazilian LGPD work for DPOs, privacy engineers, and executives. It covers data-subject requests, 72-hour incident response, DPIAs, ROPA, vendor agreements, international transfers, consent, and retention, with PT-BR templates, PII/cookie/TLS scanners, and tamper-evident evidence logs. It is compliance tooling, not legal advice.

Build a Transfer Impact Assessment using the EDPB six-step method, CNIL’s structured Step 3, essential guarantees, transfer-qualification criteria, and country profiles. The skill can produce Markdown, a formal DOCX, a RoPA JSON delta, and batch risk summaries, including balanced Art. 49 analysis. It provides structured guidance, not legal advice, and current law needs verification.