Recently updated open-source projects

polymarket-brier-skill asks Claude Code for a probability and a falsifiable resolution criterion for a Polymarket question, persists the forecast, and computes Brier scores after the market resolves. Source tags let you compare yourself, an influencer, another model, or the market consensus in a calibration ledger and digest. It currently supports Polymarket only, treats disputed resolutions as final, and warns that small samples are noisy.

ELI5 detects who the explanation is for and adjusts vocabulary, analogies, tone, depth, and framing accordingly. It can explain code to a manager, simplify an error for a parent, or describe a technical concept to a child without using the same generic style for every audience. The skill installs in Claude Code and triggers from ordinary requests.

This Claude Code skill teaches agents to charge for APIs, wrap AI inference in an HTTP 402 paywall, search for and hire other agents, and automatically pay 402 quotes through Voidly Pay. It also describes subscription and streaming metering and an optional MCP server with dedicated payment tools. The documented rail uses USDC on Base, with local Ed25519 identity keys.

Anti-Apophenia makes an agent treat an appealing pattern as a hypothesis rather than a finding. It requires a claim, evidence, null model, alternatives, prediction, and disconfirmation loop, while penalizing post-hoc fitting, repeated attempts, cherry-picking, and vague resemblance. Evidence grades and explicit verdicts separate strong, weak, rejected, and unknown results, and tempting branches stay parked instead of steering the investigation. Speculative exploration is allowed only in a clearly marked sandbox.

Memory Road records Claude Code events in SQLite, renders a continuity packet containing current state and open work, and injects it before each prompt through hooks. Hourly rollups, on-demand backfill, and a watchdog extend and protect the history. Installation requires Python 3.10 or later together with a background service, hooks, and scheduled jobs.

YouTube Comment Suite is a cross-platform JavaFX desktop application that aggregates comments from multiple YouTube videos, playlists, and channels for archiving, search, and activity analysis. It filters by video, type, username, keyword, length, or date, summarizes publishing and commenter activity, and saves thumbnails and user profiles for offline reference. Release packages expect Java 8; Java 11 and later require the workaround documented in the project wiki.

VisionCraft lets Claude Code use Agnes AI to create images and videos from text or reference images. It supports multi-image and keyframe workflows, handles polling and timeout recovery, and validates JSON, but requires Windows PowerShell 7+, a valid Agnes API key, and the supported session environment.

Point the skill at a NetIQ or OpenText Identity Manager Designer workspace to document drivers, policies, filters, entitlements, packages, vault schema, and RBPM provisioning. It can compare two exports in terms of actual behavior instead of noisy IDs, ordering, and timestamps. The workflow is intentionally read-only and does not edit Designer files.

mingli packages distilled knowledge for BaZi, Qi Men Dun Jia, Liu Yao, Da Liu Ren, feng shui, Mei Hua Yi Shu, Zi Wei Dou Shu, tarot, and physiognomy into a local Claude Code skill. It uses cards, question-and-answer material, cases, principles, and a teacher persona to structure a reading; a BaZi request needs birth date and time, gender, and birthplace. The package works offline without an external database and is for study and reference, not for life, medical, legal, or major investment decisions.

Give The Board a technical, product, venture, launch, or risk decision, and it selects a panel of contrasting advisory archetypes to review feasibility, economics, user value, compliance, and failure modes. Their independent votes are aggregated into PROCEED, CONCERN, or BLOCK under explicit rules, with reasons and conditions for reconsideration. The panel uses composite roles rather than imitating named real people.

governance-to-automation generates an issue-driven auto-develop.sh workflow from project governance such as SOUL.md, AGENTS.md, CLAUDE.md, and MEMORY.md. The generated loop can implement, check, run dual review, fix, refactor, re-review, commit, and open a pull request, with an optional per-task test gate. Privileged execution and automatic merging remain off unless explicit flags pass a runtime confirmation. A companion repository owns the creation and maintenance of the governance files themselves.

Meeting Todos reads a chosen or recent meeting note, separates tasks assigned to you from other people's commitments, and surfaces unresolved decisions. It shows a preview before writing, preserves the format and order of the existing to-do file, and avoids duplicate entries. The plugin expects Claude Code, Markdown meeting notes, and a to-do file; on first load it also sends an anonymous install signal that can be disabled with an environment variable.

Describe a problem or decision and the skill challenges the framing before optimizing within it. It surfaces load-bearing assumptions, separates foundational truths from convention, rebuilds three approaches around speed, impact, and simplicity, and identifies the action most likely to change the outcome. A fast mode covers assumptions and the leverage point for everyday choices, while the full four-phase process is intended for consequential strategy, pricing, business-model, or career decisions.

Claude Plan reads your task list and Google Calendar, protects sleep, exercise, and meals first, then proposes work that fits the remaining capacity. Weekly calendar changes wait for explicit approval; morning mode sets the day's capacity and priorities, while the Friday review compares scheduled work with what actually shipped. It requires a compatible Google Calendar MCP. On first load, the plugin sends an anonymous name-and-version signal that can be disabled with an environment variable.

claude-insights turns recent Obsidian entries into a structured weekly or monthly reflection. It summarizes emotional-floor trends, habits, recurring themes, commitments versus reality, wins, coach-style pushback, gentler exploratory observations, and optional advisor comments. Any journal format can be analyzed, although entries and indexes created by the companion daily-journal plugin provide richer and faster results.

Run `/patterns` to scan recent sessions, decisions, drafts, and journal entries for themes or working habits that keep returning. It proposes up to five evidence-backed captures—such as CLAUDE.md rules, concept notes, writing seeds, or skill improvements—and writes them only after you confirm. First-time setup requires paths to your notes, and the plugin sends a one-time anonymous install signal unless you opt out.

Use a product requirements document and the actual repository to produce tailored SOUL.md, AGENTS.md, CLAUDE.md, and MEMORY.md files, or compare existing governance against current code and requirements. The skill marks unresolved decisions explicitly and audits before overwriting. This repository is the earlier stage of the workflow; its author recommends a separate successor for issue-driven automation.

wp-plugin-security-checklist guides security checks for WordPress plugins that accept input or render stored content. It covers nonce and capability enforcement for REST, admin, AJAX, and public endpoints, recursive schema-based sanitization, CSS and JavaScript allowlists, safe metadata exposure, prepared statements, file writes, and context-correct escaping at output. A compact grep checklist helps apply the rules while building or reviewing custom plugins.