🔌
Plugins
Loading...
Showing 30 of 22820 results
Fire-ASAP orchestrator pattern for multi-track autonomous overnight workflows on scheduled triggers — a self-rescheduling poll loop that consolidates the moment all tracks report complete, and survives a 12-20h session end. Companion safety pattern.
Generate semantic context YAML for your data warehouse schema. Connects to Snowflake, BigQuery, Redshift, or Postgres through your existing warehouse connector and produces human-readable table labels, column descriptions, semantic types, and example business questions — ready to import into Jedify or any NL-to-SQL tool.
Convert JSON schemas to other formats (Go structs, TypeScript interfaces, etc.)
LLM command safety validator. Blocks dangerous bash commands and Claude advertising spam.
End-to-end academic research pipeline — 8-phase (Phase 0..7) script-driven workflow across 7 federated sources (OpenAlex, arXiv, Crossref, PubMed, DBLP, bioRxiv, Exa), cross-source dedup, transparent ranking, dual-backend citation chasing (OpenAlex + Semantic Scholar), parallel deep-read fan-out, mandatory self-critique, and cited reports across 5 archetypes
Comptabilite automatisee pour SCI a l'IS. Generation liasse fiscale 2065/2033 via Teledec, consultation balance/grand-livre/journal, ingestion documents. Revue, pre-cloture et cloture interactives dans l'espace abonne FE.
Audit and polish scientific papers: citation/claim verification against Crossref/OpenAlex/Semantic Scholar, guideline-based peer review, rebuttal letters, presubmission checks, arXiv prep, figure critique, prose critique, IMRaD process discipline.
A self-improving suite of skills for rigorous scientific research.
Multi-source scientific literature search and ingestion (EPMC, PubMed, OpenAlex, bioRxiv). The schema base for the deep-research database.
Domain-agnostic scientific method research loop: collaboratively refine problems, then autonomously generate and test hypotheses until solved.
Falsification-first investigation workflow: convert every assertion into a labeled falsifiable hypothesis, predict before measuring, run controlled experiments, verify findings adversarially (REFUTE-first), and persist verdicts in a hypothesis ledger so killed ideas are never re-attacked
Add an external QM program as a SCINE calculator — C++ scine_utilities and Python scine_puffin.
Integrate a new ML model or interatomic potential into scine_parrot.
Pre-code intelligence — define audit scope, gather docs/specs from Notion, run spec-to-code compliance, generate hypotheses for invariants, bug areas, and recommended tools.
Turn raw project inputs (briefs, meeting transcripts, screenshots, voice notes, loose prompts) into a complete, staged scoping package: scope.md as the source of truth, screens.md for design agents, phased task cards for coding agents, and API docs for frontend consumers.
Commitment tracking for LLM agents — a deontic scoreboard of what the agent is entitled to claim and to do; catches drift and overreach. Attaches as Claude Code hooks; the scorer self-resolves via pip/uvx.
Autonomous knowledge management and daily briefing system for Claude Code
Automated tool sweep — entry-point analysis, static analysis dispatch, invariant identification triggers, and tool recommendations.
Apply PrimeRFP SCOUT brand guidelines — official colors, fonts, logo usage, and report structure — to reports and documents generated from SCOUT federal and SLED contracting intelligence.
Token-efficient reading. Claude greps before reading, extracts relevant lines only, synthesizes exploration into compact summaries.
Structure business communication using the SCQA framework — great for memos, exec emails, and strategy docs
Runtime de scraping standardisé (profils + contrat de run) — cadre générique de structuration/validation d'un run de collecte. Fournit profils, contrat de run et générateur de registre de sources ; exécution déportée.
Session scratchpads — organize agent knowledge into a folder + manifest, with a read-only visual viewer. Ships the `scratch` and `planning-with-scratchpad` skills.
Eyes and hands on a Linux Wayland desktop: screenshot any monitor and click, type, scroll, drag, and read any visible app over xdg-desktop-portal (RemoteDesktop + ScreenCast), with optional OCR + OmniParser icon grounding. Pure-Python, CPU-only. GNOME/Wayland only. Ships the MCP server plus a drive-screen skill that encodes the locate-ground-act-confirm loop.
Conduct comprehensive screen reader testing for website features.
Give Claude the ability to see your screen, watch it in real-time with audio, analyze videos, and extract text via OCR.
Capture pages, publish OAuth-authenticated snapshots with the Screenote CLI, and retrieve visual feedback from Claude Code or Codex.
from bennoloeffler/maude-claude-vunds-plugins