Browse all
Capture user feedback and apply prevention rules
This skill facilitates the capture of explicit user thumbs feedback and applies defined prevention rules. It is designed to gather qualitative data and validate assumptions before major implementation phases.
Agent Safety Gates for AI Coding Agents
ThumbGate implements pre-action gates for AI agents, capturing structured feedback (thumbs up/down) to identify failure patterns. It automatically generates prevention rules and blocks known-bad tool calls via the MCP PreToolUse hook, signi…
CAE Simulation Post-Processing Translator
Translates natural language requests from CFD, FEA, and SPH domain experts into precise MCP tool calls for simulation post-processing. It provides domain-specific vocabulary mapping, data-driven visualisation suggestions, and aesthetic guid…
Agent Action Feedback and Prevention Gates
ThumbGate captures agent performance feedback (up/down) and uses adaptive mechanisms to generate hard prevention rules. These rules are enforced via PreToolUse hooks, preventing the agent from executing known-bad actions before they occur.
Viznoir development workflow automation skill
This skill automates the development lifecycle for the viznoir project, guiding developers through the TDD cycle. It enforces best practices for adding new filters, tools, and managing PR quality gates, including benchmarking and registry u…
Agent Feedback and Hard Prevention Gateway
ThumbGate acts as an agentic immune system, capturing thumbs-up/down feedback on actions to automatically generate and enforce prevention rules. These rules are implemented as hard PreToolUse hooks, blocking known-bad patterns before the ag…
CFD Post-Processing Visualization Workflow
This skill guides agents through comprehensive post-processing of CFD data, enabling detailed visualization of fields such as pressure, velocity, and turbulence. It maps domain vocabulary to specific tool calls for analyzing streamlines, bo…
Headlessly analyze Skool communities for revenue signals
This skill allows for the headless reading and analysis of Skool communities, enabling the discovery of customer pain points and potential acquisition leads. It uses direct HTTP reads via the MCP connector, ensuring the user's active browse…
ComfyUI Custom Node Development Assistant
This skill assists developers in creating custom ComfyUI nodes by providing templates and guidance on structuring Python code. It covers mapping Python types to ComfyUI inputs and handling batch dimensions for robust node implementation.
Create DOI-ready Scholarly Book Editions
Automate the creation of versioned, scholarly editions for translated historical texts, including front matter generation and EPUB construction. The workflow integrates with Zenodo to mint permanent DOIs for published editions.
Advanced search of past coding conversations
This skill enables deep retrieval across historical Claude Code and Codex CLI sessions using a hybrid BM25 and semantic index. It guides the user through clarifying intent and formulating structured, multilingual queries to locate specific …
Manage and Index Conversational Lore Data
This skill manages the indexing of conversational sessions from various sources, employing an opt-out blacklist model where all projects are indexed by default. It provides granular control over project inclusion, exclusion, and full databa…
Load UI context and frontend best practices
This skill loads comprehensive context regarding the application's UI structure, navigation patterns, and critical frontend rules. It ensures adherence to established best practices for analytics, linking, and component usage.
MongoDB status check for content pipeline metrics
This skill executes a single MongoDB query to provide a comprehensive, high-level health check of the content pipeline. It reports key metrics including translation coverage, OCR queue depth, job status, and recent throughput rates.
Search and cite historical primary sources
This tool facilitates academic research by querying the Source Library API. It retrieves verbatim quotes and multi-page texts from historical and philosophical works, ensuring accurate citation and source fidelity.
Systematic QA Evaluation for OCR and Translation
This framework provides systematic quality evaluation for OCR and translation outputs across diverse scripts and languages. It calculates metrics such as MCR, CER, BLEU, and detects embedding-space hallucinations to provide corpus readiness…
Record Lessons Learned in Memory
A procedure for documenting bug fixes, incidents, and discovered patterns into domain-specific memory files while checking for contradictions and stale entries.
Source Library quality and metadata auditor
This agent systematically audits historical texts within the Source Library, verifying metadata accuracy against title pages and checking for original language content versus modern translations. It provides structured reporting on quality …
Advanced pipeline progress and diagnostic reporting
This skill provides deep diagnostic reporting on complex data pipelines, moving beyond simple job counters to verify page-level progress across all stages (e.g., OCR, translation, enrichment). It identifies stuck jobs, calculates real throu…
Pipeline Operational Context Loader
This skill loads comprehensive operational context, including architectural rules, model selection guidelines, and critical constraints for complex data pipelines involving OCR, translation, and Lambda workers. It ensures developers are awa…
Comprehensive data repository maintenance skill
This skill provides context and procedures for maintaining a data repository, covering tasks such as correcting page counts, resetting stuck records, and debugging data quality issues. It guides the user through known issues, job management…
Autonomous Curator for Esoteric Historical Texts
This agent autonomously curates and imports primary source material focusing on Western esoteric traditions, including Hermetica, Alchemy, and Kabbalah. It interfaces with major digital libraries (e.g., Gallica, Bodleian) via dedicated APIs…
Extracts and catalogs historical book illustrations
This skill uses advanced AI vision to detect and extract illustrations from historical book scans. It generates a structured gallery, providing rich metadata including type classification, scholarly descriptions, and detailed subject taggin…
Collection Content Curation and Auditing
Automates the generation of editorial content for collection pages, including descriptions, highlighted books, and gallery images. It also includes an auditing mode to detect broken links, missing content, and stale metadata within MongoDB …