code-review-graph
21529MCP server Claude CodeCodexCursor +2
MCP server "code-review-graph" as configured in teakzc/backpack-plus. Launched with C:\Python313\python.exe -m code_review_graph serve.
Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 379,527 indexed, measured the same four ways as everything else here.
MCP server Claude CodeCodexCursor +2
MCP server "code-review-graph" as configured in teakzc/backpack-plus. Launched with C:\Python313\python.exe -m code_review_graph serve.
Plugin Claude Code
Bundles 22 skills, 3 hooks · 1,030 tokens together
Disciplined AI Research Assistant for economists: plan-implement-integrate workflow with implementer–reviewer pair, data-analysis discipline, and drift-test-verified integration.
Plugin Claude Code
Bundles 2 commands, 1 agent · 182 tokens together
Project configuration and setup tools including CLAUDE.md creation and maintenance with ground truth validation. The maintain flow preserves existing references and information by default: removal requires cross-verification proving the content false or obsolete (else: keep, extract to docs/, or ask the user). It…
j-shelfwood/obsidian-local-rest-api-mcp
MCP server Claude CodeCodexCursor +2
MCP server "obsidian-vault" as configured in j-shelfwood/obsidian-local-rest-api-mcp. Runs build/index.js with node.
Skill Claude CodeCodex
Writing guidance for meeting and daily, weekly, or monthly reports in Korean. It covers preserving facts, recording follow-up actions, tracking deals, and using a consistent report style.
Skill Claude CodeCodex
A research skill that uses Tavily to find public sources, retrieve their readable text, and pass source identifiers to another research worker. Tavily is a web-search service, and this tool is intended for approved research tasks in BriefLoop.
MCP server Claude CodeCodexCursor +2
MCP server "openwiki" as configured in ishizakahiroshi/many-ai-cli. Launched with openwiki mcp --host claude.
Skill Claude Code
An agent that delegates image, video, and other creative-production tasks to the Gouda service. It also supports continuing, recovering, cancelling, and checking those tasks.
MCP server Claude CodeCodexCursor +2
Governed Obsidian vault access: hybrid retrieval, Markdown-native memory, HITL confirmations. Runs locally from the obsidian-tc npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "gate4agent" as configured in ZENG3LD/gate4agent. Launched with C:/Users/operator/gate4agent/target/release/gate4agent-harness-mcp.exe --session.
Skill Claude CodeCodex
Run the hermeneutic deterministic English drift gate on an assistant draft before sending it when the draft contains numeric claims, completion language, universal quantifiers, or a summary of delegated work.
fore-thought/deepseek-harness-project-collection-starter
Skill Claude CodeCodex
A workflow guide for AI agents working in a project with defined roles, file permissions, and handoff records.
Skill Claude CodeCodex
Trigger: type design, Glyphs, spacing, kerning, stems, color, proportions, masters, interpolation, production QA, typeface voice or DNA, differentiation, and anti-copycat analysis.
Plugin Claude Code
Bundles 4 skills, 2 commands · 364 tokens together
Edit Overleaf projects live alongside human collaborators. Bundles the overleaf-mcp-rt MCP server (self-hosted Overleaf and overleaf.com) with skills for setup, safe co-editing, LaTeX workflow and review comments. Use when asked to read, write, review or compile anything on Overleaf.
fulcradynamics/fulcra-context-mcp
MCP server Claude CodeCodexCursor +2
Fulcra Context MCP Server. Runs locally from the fulcra-context-mcp Python package.
Skill Claude CodeCodex
Autonomous personal decision & shopping copilot for GenPark & OpenClaw. Executes cross-platform product research, review sentiment auditing, MAUT trade-off scoring, cart staging, and tokenized checkout via local sandboxed browsers.
Skill Claude Code
OMP-only feature cycle — frame a GitHub issue, create the worktree from origin/ , hand off /move and /goal, then implement, review, fix and land.
AutoConference/AutoConference-skill
Skill Claude CodeCodex
Turn gate-passed evidence into a submission-shaped LaTeX paper whose layout, tables, equations, citations, and prose are checked mechanically. Use when drafting, revising, compressing, or reviewing a manuscript, or when a paper must be brought to submission quality. Does not run experiments and does not decide what…
narrative-io/narrative-skills-marketplace
Skill Claude Code
Weekly read-only repository audit. Grades one rotating rubric from .claude/audit-rubrics/, files between zero and five GitHub issues for what it finds, and changes no files. Use when the user asks to audit the repo, or when the audit-weekly workflow invokes it. It never edits, commits, branches, or opens pull requests.
Plugin Claude Code
Bundles 4 skills, 1 hook · 158 tokens together
Keep AI project memory small, in git, and shared across tools. Teaches Claude the retrieval-first .ai/ contract, checks bank health at session start, and adds doctor, compact and init commands.
Skill Claude CodeCodex
Connect AgentPlaybooks skills, MCP servers, and federated OpenAPI tools to Hermes. Guide playbook sync, authentication, secret setup, and recovery.
Plugin Claude Code
Bundles 1 skill, 2 commands · 211 tokens together
Livestream to content pipeline in one skill: standard folder layout, transcripts, per-feature clips, chapters, subtitles, summary reels and animated 9:16 shorts (split-screen camera, captions, frame-0 hook, real footage), with YouTube titles and descriptions. Every video is versioned and reproducible.
cubinet-code/paperless-ngx-mcp
MCP server Claude CodeCodexCursor +2
Full Paperless-ngx API for AI assistants: search, tag, edit and upload documents, workflows and more. Runs locally from the paperless-ngx-mcp npm package. Needs 3 environment variables to run.
Skill Claude CodeCodex
Audit and rewrite prose so it reads as human written and is easy to understand. Use when asked to remove AI-isms, clean up AI writing, make something sound less like AI, or make an explanation clearer. Three modes: detect only, rewrite, and edit a file in place. Covers two separate problems, register (does it read as…
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: