Recently updated open-source projects

academic-credentials-skill guides institutions through issuing, verifying, and managing academic diploma SBTs on Solana. It covers Token Extensions, Metaplex metadata, batch issuance, QR or wallet verification, revocation and compliance concerns, plus a migration path from Polygon or other EVM systems.

This Claude Code skill collects the files relevant to a review, writes a structured prompt with specific questions and evidence pointers, and creates a tar.gz bundle for ChatGPT Pro. It supports code, architecture, security, writing, research, and other multi-file reviews while screening common secrets before packaging. The final prompt and archive are pasted and uploaded manually.

Write As Your Mentor analyzes a set of lab or journal papers to extract title patterns, abstract structure, sentence length, verbs, recurring phrases, and closing forms into a reusable style profile. The bundled example targets Chinese engineering and environmental journals, while the same method can produce a custom profile for another group. It can polish sections or draft abstracts and proposals, but research data, results, and citations must come from the user’s real work.

Run a weekly digest over local Claude Code JSONL sessions to measure work patterns such as activity mix, one-shot edit rate, agent usage, model allocation, and project attention. When a diagnostic threshold fires, the plugin appends a concrete rule to CLAUDE.md or adds an investigation item, then measures the same behavior again in later reports. It also sends a one-time anonymous install signal unless the documented opt-out environment variable is set.

Run a morning, afternoon, or evening check-in and let the plugin turn the conversation into a first-person Obsidian note. It can identify an emotional “floor” on a 34-level scale, track selected habits, and add an optional advisory panel below a clear divider so commentary is not mixed with the user’s own voice. Claude Code and an Obsidian vault are required; the anonymous first-load install ping can be disabled.

The skill helps reproduce local React, Next.js, HTML/CSS, or Vue interfaces in Webflow, build from Figma or a blank canvas, and fix styling or responsive issues. It uses the Webflow MCP Bridge and browser automation to manage elements, styles, components, breakpoints, and publishing. The required Chrome extensions must be installed, with Webflow Designer open during use.

gpt-image-2-prompting-skill turns an image request into six blocks covering intent, subject, composition, text, style, and constraints. It selects from 13 templates and 29 scene recipes, with guidance for image-to-image work, series consistency, and troubleshooting, so creators can specify a repeatable visual result instead of relying on one-off prompt examples.

reels-to-site downloads videos from TikTok, Instagram profiles or chats, or loose links, stores media in Cloudflare R2, transcribes audio with Groq Whisper, and builds a Netlify site with playable cards and transcripts. A manifest makes runs resumable. The R2 bucket must be publicly readable for playback. Groq and R2 configuration are required; Netlify credentials are needed only for deployment, and Instagram profile/chat sources additionally need a session cookie.

cross-stake reads CROSS Chain Mainnet network state, validators, wallet delegations, rewards, and unbonding history, then can submit delegate, undelegate, claim, and compound actions behind explicit confirmation gates. Read-only checks do not require a private key; write settings can enforce gas reserves, notional limits, and confirmation thresholds. Managed signing through Vault, KMS, or HSM is supported as an alternative. The skill targets CROSS Mainnet and should be paired with treasury and risk controls before real writes.

wporg-plugin-submit scans a WordPress plugin and builds a clean upload archive before submission to WordPress.org. Its preflight and reference maps cover common rejection points such as prefixes, permissions, sanitization and escaping, internationalization, hidden files, readme and header drift, and plugin policy rules.

sync-fork installs a GitHub Actions workflow that discovers a fork's upstream parent and runs gh repo sync on a recurring schedule, defaulting to every six hours. It performs no commits, rebases, or force-pushes; conflicts fail loudly instead of being hidden. A logged-in GitHub CLI is required, and upstream workflow changes may require a separate token with the workflow scope.

Recite Coach uses an agent workflow to turn PDFs, lecture notes, textbooks, tables, or pasted text into compact recall cards, then converts cards.md into cards.json for a local browser player. The player supports answering, revealing, self-rating, and Leitner-style review on the user’s machine, with no cloud study service required. The skill creates the cards; the player is not a standalone PDF-understanding engine. Python’s standard library is sufficient for the local tool.

content-repurposer analyzes one Instagram Reel or TikTok with audio transcription and frame OCR, identifies its call to action, and rewrites the on-video text and caption for Instagram, TikTok, and YouTube. It can upload and schedule TikTok and YouTube through the user’s Zernio account, while Instagram remains manual by default unless a paid connection is enabled. The original file is never modified; local media tools, a Zernio account, and its key are required.

The skill gathers swim, bike, run, sleep, HRV, and related records from connected fitness MCP servers, normalizes and deduplicates them, then calculates training-load and recovery metrics with a local Python script. It returns a coach-style snapshot, discipline trends, safety flags, and a concrete next-session recommendation. At least one fitness data source is required, and the output is decision support rather than medical advice or a certified coach.

ai-native-review examines a tool, skill, or codebase before implementation. Its four tests ask whether removing the AI call changes the result, whether better models improve it, whether context is sufficient, and whether prompts beat hardcoded rules; it also reviews goal-to-action interaction, visibility, control, and safety.

Amino Deliverability Audit inspects public DNS and related trust signals for an email-sending domain, looking beyond the existence of SPF, DKIM, and DMARC records to alignment gaps, report destinations, MTA-STS coverage, and other silent failures. It combines the signals into an effort-versus-value repair order and drafts the exact records to change. The tool is read-only: it never sends mail, asks for credentials, or edits the domain.

Forge’s magdil-rosh routes a feature or non-code deliverable to a focused checklist, loading only the material needed for that request. It asks up to three scope questions, covers each relevant row or names the deferral, and reports tersely so the agent does not stop at the happy path. Project-specific sections can be adapted to the project’s backends, compliance requirements, locales, and design system; no API key or extra configuration is required.

rust-coding-skill gives coding agents progressive guidance on ownership, errors, data modeling, traits, concurrency, testing, API design, unsafe code, and security tooling. The same reference set is exposed through Claude Code, Codex, Cursor, Copilot, Cline, and other agent instruction formats. Each task ends with cargo fmt, cargo clippy -D warnings, and cargo test, encouraging idiomatic code rather than code that merely compiles. It is a ruleset and verification habit, not a replacement for Rust tooling.