Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 390,084 indexed, measured the same four ways as everything else here.
A bilingual guide for planning research and exploring important scientific questions through Socratic questioning, where questions help clarify ideas and assumptions. It follows the idea that research is a conversation with existing knowledge and other researchers.
Multi-agent legal memo drafting: intake questions, planned legal research, a frozen source pack with verifiable quotes, a counterargument and citation review loop, and a footnoted docx deliverable.
MANDATORY first skill to load when Hermes needs to orchestrate Claude Code on local Windows via SSH+tmux. Covers session lifecycle, monitoring (capture-pane), R1/R2/R3 debate protocol, error recovery, and bulk file transfer. Trigger whenever: (1) user requests local file operations/code modifications/script runs/Git…
A general reverse-engineering toolkit for Windows programs, Android apps, iOS apps, web interfaces, and APIs. Reverse engineering means examining software to understand how it works and, where appropriate, how to modify and rebuild it.
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
Two complementary idea-expansion skills based on Patrick Gunkel's ideonomy — the science of treating ideas as natural phenomena that can be sliced, negated, recombined, and re-instantiated. ideonomy-plain outputs plain-text-portable artifacts (survives SMS/Telegram/Slack). ideonomy-rich outputs performative ASCII art…
Interactive decision planning session to prepare canonical context, classification, rigor, and decision rights for /write-decision. Supports all decision types (ADR/PDR/TDR/BDR/ODR).
Persistent, bitemporal memory for Claude Code: the MCP tool surface, six skills that teach the model to use it, recall injected at session start, and capture before compaction.
★not rated 43
changed 27d agoA
tokens not measured
AGPL-3.0
Use when modifying the Light Dashboard custom/ variant. Covers the custom mini-CMS engine, layout and color customization, adding/removing pages, HTMX navigation, and CMS-level SMQ page scopes.
Condense any input — an idea, brief, PRD, transcript, or mixed notes — into a short spec: one kernel file plus supporting files that downstream skills build from. Also updates and validates existing specs. Use when the user says "create a spec", "distill this into a spec", "validate this spec", or "update the spec".
MCP server for OpenProject Community Edition with guarded read/write support. Runs locally from the openproject-ce-mcp Python package. Needs 4 environment variables to run.
★not rated 43▲
+4 yesterdayASocket: warn
tokens not measured
originalMIT
Move one experiment through RUN → VERIFY → DELIVER with the least control work that safely advances the user's outcome. This is the compute/control layer and owns one compute attempt. When the task spans several runs, nodes, independent side-effect lanes, or paper-wide closeout, route scheduling and state projection…
★not rated 42
changed 3d agoA90 tokens
originalMIT
Official Sent plugin for SMS, WhatsApp, RCS, scheduled template sends, Sender Profiles, SMS compliance, authorized feedback, contacts, analytics, API integration, webhooks, routing, and migration.
MCP server "notebooklm-mcp-structured" as configured in paolodalprato/notebooklm-mcp-structured. Runs locally from the notebooklm-mcp-structured npm package.
★not rated 42 2mo agoA
tokens not measured
originalMITarchived
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: