research
97Skill Claude CodeCodex
Investigate an uncertain question and produce an evidence-backed decision. Use when the user asks to research, compare approaches, validate an assumption, or reduce uncertainty.
811 mods tagged markdown that install into Codex, measured the same four ways as everything else here: what each costs in tokens on every session, what a security scan found and why, whether it is the original, and what changed.
Skill Claude CodeCodex
Investigate an uncertain question and produce an evidence-backed decision. Use when the user asks to research, compare approaches, validate an assumption, or reduce uncertainty.
Skill Claude CodeCodex
Preserve or inspect decision history for Markdown and static HTML knowledge artifacts with Proofpress. Use when creating or accepting a meaningful revision to an ADR, design doc, PRD, README, strategy note, portable .md artifact, or static .html/.htm artifact in a configured repository, or when receiving a file…
Skill Claude CodeCodex
Git-backed ticket management for AI agents.
janrummel/claude-orchestrator-starter
Skill Claude CodeCodex
Adversarial stress-testing of ideas, plans, decisions, and strategies. Finds weak points, simulates stakeholder objections, surfaces hidden assumptions, and runs pre-mortems. Use when the user says 'challenge', 'stress-test', 'red team', 'objections', 'counter-arguments', 'what could go wrong', 'weaknesses', 'devil's…
Skill Claude CodeCodex
Extract clean content from URLs via MCP. Use when the user asks to scrape a URL, read docs/blog/article pages, summarize a link, extract links, search page text, batch-scrape URLs, or get OG/title metadata without Firecrawl.
Skill Claude CodeCodex
Use when operating LINZA MCP as a local-first agent workspace. Guides agents through doctor checks, guidenextsteps, agentworkspace actions, teach/grow review loops, dry-run apply gates, artifact safety, calibr trace review, and context export without exposing raw tool lists to users.
Skill Claude CodeCodex
Search for podcast episodes and fetch their transcripts as clean markdown with speaker names and timestamps. Uses the spoken.md API.
MCP server Claude CodeCodexCursor +2
A validated Markdown memory vault your coding agent can recall, project by project. Runs locally from the @sunsato/vulcanus npm package.
Skill Codex
Publish and manage browser-viewable artifacts with html2link. Use when a user asks an agent to deploy, publish, host, share, update, replace, or delete generated HTML, a static website ZIP, PDF, Markdown, spreadsheet, DOCX, or PPTX as a public link.
Skill Claude CodeCodex
Execute cold outreach campaigns at scale — 500+ emails/day with Instantly, multi-account rotation, automatic warmup, A/B testing, and campaign analytics.
Korner83/ai-development-methodology
Skill Claude CodeCodex
Operating rules for projects using the AI Development Methodology — markdown + git governance for mixed human/AI-agent teams. Load when working in a repo that follows it, or for any process question: sizing and filing backlog items, what counts as Done (Status/Test fields), the file-lock protocol for parallel agents…
MCP server Claude CodeCodexCursor +2
MCP server "wikistrata" as configured in kogarashi86/WikiStrata. Runs locally from the wikistrata Python package.
MCP server Claude CodeCodexCursor +2
Model Context Protocol integration for Claude Context. Runs locally from the @zilliz/claude-context-mcp npm package. Needs 7 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "rowlite" as configured in pipik-roman/rowlite. Launched with https://github.com/pipik-roman/rowlite/releases/download/v0.2.0/rowlite_0.2.0_li.
Skill Claude CodeCodex
Use when asked to read, extract content from, or convert documents — PDF, DOCX, PPTX, XLSX, or HTML files — into Markdown text so an AI agent can process them.
TIKAZI/TIKAZ-Codex-Context-Economy
Skill Claude CodeCodex
Automatically prepare fidelity-first, bounded context when users paste text, attach files or folders, provide webpages or PDFs for Markdown conversion, continue long conversations, or supply documents containing images and complex tables. Route each input through Text, Hybrid, or Source; reduce exact or…
Skill Claude CodeCodex
Use whenever the conversation involves the user's projects, systems, infrastructure, people, past decisions, or recurring problems — even when memory is not explicitly mentioned. Trigger on possessives and project references ("my project", "our server", "remember when we", "last time"), named systems and services in…
MCP server Claude CodeCodexCursor +2
MCP server for high-accuracy scientific PDF OCR using Meta's Nougat. Runs locally from the nougat-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP for managing markdown notes with YAML frontmatter. Runs locally from the notes-mcp Python package.
ThreeFish-AI/negentropy-perceives
MCP server Claude CodeCodexCursor +2
A commercial-grade MCP Server built on FastMCP, offering robust capabilities to read, extract, and localize (into Markdown) content from web pages and PDFs with both text and images. It is purpose-built for long-term deployment in enterprise environments. Runs locally from the negentropy-perceives Python package.
MCP server Claude CodeCodexCursor +2
A robust MCP server for fetching and extracting web content using Trafilatura. Runs locally from the fetchv2-mcp-server Python package.
mohsinkhadim59/youtube-obsidian-mcp
MCP server Claude CodeCodexCursor +2
MCP server "youtube-notes" as configured in mohsinkhadim59/youtube-obsidian-mcp. Runs C:\Users\YourUsername\mcp-servers\youtube-lecture-notes\server.py with python. Needs 1 environment variable to run.
sethdavis512/obsidian-mcp-server
MCP server Claude CodeCodexCursor +2
Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP. Runs locally from the obsidian-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
MCP server "paimon-mcp-fetch" as configured in paimonchan/paimon-mcp-fetch. Launched with https://github.com/paimonchan/paimon-mcp-fetch/releases/download/v0.1.2/paimon-m. Needs 4 environment variables to run.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: