Recently updated open-source projects

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.

claude-telegram-bridge gives a long or unattended Claude run a Telegram side channel. notify sends non-blocking progress, while ask or listen waits for a reply and exposes clear exit codes for answered, timed out, unconfigured, or stopped states. Replies are accepted only from allow-listed chat IDs, so another person cannot drive the agent through the bot.

open-collider helps Claude move beyond obvious brainstorms by combining distant domains and reference objects into a curated, ranked idea pool. It runs as a single Markdown skill with no server or external state, and asks about token cost before an intentionally large ideation pass.

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.

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.

news-impact-skill fetches Yahoo Finance RSS, deduplicates stories, filters them against a symbol watchlist and aliases, and asks an LLM to rank likely impact per symbol. It emits a compact JSON briefing grounded in headline text; it is advisory only and never places trades, sizes positions, or imports broker data.

Pantheon convenes six isolated reviewers for architecture, security, product fit, implementation truth, accidental misuse, and research claims. They review independently, surface clashes, resolve disagreements in proportion to the project’s stakes, and return a final verdict with a mandatory dissent log. Individual security, QA, or source-truth lenses can also be run without the full council.

Create named teams from ten supported AI command-line backends, then dispatch a task to one member, fan it out for comparison, or run a staged writer-reviewer-synthesizer pipeline. An MCP bridge lets Claude Code call the team tools directly, while team variants and remote members support deeper or cross-host workflows. Setup requires Claude Code, Python 3.9, Node.js 18, and at least one compatible model launcher.

typo3-claude-skills pairs a major-version upgrade playbook with a symptom-indexed TYPO3 development reference. The upgrade side includes Rector and Fractor wrappers, Extension Scanner checks, TCA validation, and page sweeps; the development side points to API removals, event listeners, Fluid, and TypoScript guidance. Shared changelogs and cross-links make the pair useful when an upgrade and day-to-day extension debugging overlap.

naval-self-audit uses structured, deliberately probing questions to turn vague career uncertainty into concrete examples of curiosity, strengths, and repeated patterns. It organizes the answers around specific knowledge, leverage, accountability, and long-term compounding, then narrows them to one or two possible directions and one action for today. It is a structured self-audit for exploring work direction.

Start with a research idea, an existing draft, or source materials and move through scoped literature collection, DOI verification, evidence-matched writing, adversarial review, and prose cleanup. The self-contained Claude Code and Codex skill can export LaTeX, Word, and PDF while keeping an auditable record of writing and review decisions. Word and PDF output require pandoc and, for PDF, a TeX engine.

renxinghua rewrites Chinese AI-generated writing to reduce formulaic openings, buzzword-heavy phrasing, parallel clichés, inflated conclusions, punctuation habits, and other language patterns. It can review articles and organizes about 27 Chinese-specific patterns across several categories. The stated goal is better, more concrete writing rather than trying to fool an AI detector.

Use simple wiki commands to add a URL, file, or note, research a topic, answer from existing pages, apply corrections, and check for broken links or orphaned content. Raw sources remain immutable after creation, while topic pages grow through dated additions instead of deletion. An append-only activity log records each action, giving personal knowledge management a clear history without requiring a separate application or codebase.

berjiwa is a Claude skill for Malaysian Malay marketing and advertising copy. It combines emotion-first storytelling with a humanizer that removes common AI patterns and detects Indonesian intrusions, covering short-video scripts, sales pages, ads, social captions, emails, headlines, and hooks. The workflow is intended for teams that want persuasive copy with a more local, human voice.

handover-navigator reads documents, emails, notes, spreadsheets, and meeting records to create a handover summary, open-task tracker, first-30-day onboarding plan, and questions for missing context. It links each claim to a source, turns unknowns into questions instead of guesses, and normalizes inconsistent task states. Original material stays read-only while results go to a separate directory.

design-styles is a library of 50 named visual directions, from Neoclassical and Japandi to Synthwave and Glassmorphism. Each entry pairs a reference image with core elements, mood, layout and motion notes, starter CSS tokens, and an adaptable image prompt. Use it to compare a few directions, build a moodboard, combine styles, or brief an image, video, carousel, or frontend concept.

gallup-hr-skills packages two complementary views of Gallup’s evidence-based HR framework: one for culture and HR teams designing or interpreting engagement surveys, and one for managers working with their own teams. Both share Q12, CliftonStrengths, the 70% manager lever, and the evidence-oriented framework; the installer lets you choose the culture/HR view, the manager view, or both. It is a methodology advisor rather than a roleplay persona.

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.