Start with the job, then find an open-source answer

forex-sentiment-monitor combines GDELT and RSS with optional news APIs to score sentiment for foreign exchange, precious metals, and crypto symbols. VADER supplies a fallback score, while Claude Code can add industry-context review, causal transmission chains, and divergence explanations. Reports are written as Markdown or HTML with source attribution; the default free sources need no API key, and the output is for research rather than investment advice.

paper-ingest resolves a paper URL, title, or DOI into metadata, extracts full text from the PDF, classifies the work, and renders a detailed Obsidian note. It can push references into Zotero, detect duplicates, and collect PDFs for later attachment through WebDAV. The skill expects a local config containing service credentials, so it fits researchers who already use Zotero and Obsidian.

Describe an image or provide a weak existing prompt, and this Claude skill will ask up to three questions only when a critical choice is missing. It then builds one prompt through a ten-part structure covering composition, subject, lighting, palette, camera or typography, finish, and references, with adapters for GPT Image 2 and Nano Banana. It writes prompt text only and does not call an image-generation API.

subtitle-to-study-page converts SRT, VTT, or TXT subtitles plus a video link into a self-contained interactive HTML study page. It organizes chapters with takeaways, analogies, study questions, detailed summaries, cleaned translations, and a jump-to-source link, then adds a searchable timeline and chapter-aware toolbox. The generated page turns long-form video subtitles into structured chapter notes for review.

Point the skill at a React or Next.js codebase to build a guided, theme-matched preview that visitors can click through before creating an account. It reconstructs only the required screens on in-memory mock data, adds a preview route and launch button, and audits the generated code to keep API clients, authentication, secrets, and real backend logic out of the demo.

sgui-stock-analysis helps structure fundamental research on Thai and international stocks, ETFs, REITs, funds, and DCA plans. It separates supplied facts from analysis and assumptions, then frames valuation, risks, bull and bear cases, portfolio fit, and a decision journal. The skill does not fetch live data, read charts, predict prices, or issue trade commands, so users must provide the source material and make the final decision.

pharma-review-skills packages four independent reviews for pharmaceutical work: evidence provenance and usability, depth and interpretation of business analysis, whether key messages lead to a doctor action without compliance traps, and whether an academic event or forum serves strategy and customer experience. In a multi-agent environment, the skills can add blinded panel review, rebuttal, and synthesis.

SnapDeck drives a running web app with headless Chrome, captures real UI states, reads element coordinates, and renders HTML/CSS slide designs to PNG before assembling a full-bleed .pptx. It can reuse a logged-in session, open tabs or modals, force light mode, and place numbered callouts beside the right controls. The resulting slides are crisp picture slides for demos or training, not editable PowerPoint text and shapes.

humanizer-it looks for Italian-specific problems such as English syntactic calques, nominal bureaucratic style, missing discourse markers, and weak use of ci or ne clitics. It supports full editing, diagnosis-only audits, and targeted fixes. A dependency-free Python scanner counts banned constructions, sentence rhythm, and Italian morphosyntactic signals, then reports a cleanliness score.

rsi-loop selects the highest-priority unchecked medium task from BACKLOG.md, implements the smallest correct change, runs the repository’s tests, typecheck, and build, then commits it. When the backlog is empty it can regenerate more work, and .rsi-loop.json controls the commit target, perpetual mode, and blast-radius limit. Because it has no question or checkpoint step, use it only where the task boundaries and checks are already trustworthy.

Use this framework as an agent skill or a manual checklist when reviewing data accounting, asset-backed securitization, property registration, trusted data spaces, and exchange-based transactions. It structures the work around regulatory comparisons, contradiction checks, a risk matrix, and a remediation list. The material is for reference and training rather than legal advice, so current rules and case-specific conclusions still need qualified review.

search-science-literature queries 13 open scholarly sources, including OpenAlex, Crossref, PubMed, Europe PMC, Semantic Scholar, arXiv, and Unpaywall. It normalizes abstracts, removes duplicates, checks for retractions, and exports BibTeX, RIS, or CSV records. Optional APIs add coverage when their keys and quotas are available; the skill explicitly skips Google Scholar scraping and paywalled databases.

color-combo-skill helps an agent choose a palette by product mood rather than picking arbitrary swatches. Its catalog covers premium, futuristic, organic, minimalist, gothic, tropical, gradient, and other directions, with names and usage guidance for each combination. It works as the color stage in a modular design chain and can hand off next steps to typography, effects, and icon skills.

axion-skill routes a forecasting question through research agents that search the web, inspect market data and SEC filings, and run Fermi estimates before returning a probability. Each forecast includes a 0–1 estimate, interval, resolution date, and cited basis. It requires an Axion API key with prepaid credits, so the output is a research forecast rather than a guarantee or a substitute for domain judgment.

LPIM uses a site's sitemap and client materials to build a product-line taxonomy, classify pages, and produce a Product Interest Map plus a findings brief. It is aimed at B2B manufacturers, suppliers, services, and SaaS sites, and deliberately pauses for human review; only the mapper is currently shipped, not visitor qualification or CRM write-back.

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 this Claude skill to reshape AI-assisted drafts around a more natural voice, varied sentence rhythm, and clearer structure without intentionally changing the underlying facts. An optional Python scorer compares statistical detection signals before and after editing, but the project explicitly warns that detector results are unreliable and cannot guarantee passage against every trained classifier.

Frontcraft asks for a clear visual direction, palette, and level of expression before Claude Code writes the interface. It applies deliberate typography, color, layout, motion, and real imagery across common frontend stacks instead of defaulting to generic centered templates. After the build, review agents check issues such as headline collisions, dead links, stale images, and weak hierarchy; a Pexels API key is optional for more targeted photo search.