Tag: llm
Automated GitHub PR Comment Resolution and Review
This tool automates the resolution of active GitHub Pull Request comments, handling both general conversation and inline code reviews. It uses the GitHub CLI to triage, reply to, and ultimately resolve review threads based on expert judgmen…
Unified AI Image Generation and Design Toolkit
This tool provides a unified interface for professional AI image generation, routing requests across multiple backends including MeiGen Cloud, ComfyUI, and OpenAI-compatible APIs. It supports prompt enhancement, semantic gallery searching, …
Interactive New User Onboarding Flow for Noosphere
Orchestrates a multi-stage, guided onboarding experience for first-time users, moving them from awareness to their first content contribution. It systematically utilizes various platform tools to establish identity, facilitate content uploa…
Shared memory for agent debugging workflows
This skill guides agents to leverage Noosphere as a shared memory layer for debugging complex issues. Agents must consult existing memories before fixing and upload distilled lessons (patterns, warnings, decisions) afterward for future reus…
Structured feedback capture for agentic workflows
This tool allows developers to record structured feedback, including thumbs up/down signals, context, and rubric scores, following task completion or failures. It is designed to distill lessons from chat history and failed tool calls, feedi…
Second pass review using Codex bridge
This skill facilitates an independent second review of the current task or repository state by handing the context to Codex via a dedicated bridge script. It is ideal when the user explicitly requests a secondary agent assessment after an i…
Retrieve last saved Codex bridge result
This skill retrieves the most recently saved raw output from the Claude Code Codex bridge. It allows inspection of the last generated artifact without incurring the cost or latency of re-running the Codex process.
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.
Persist conversation state into long-term memory
This skill persists the current conversation state into a dedicated memory store, ensuring critical facts, decisions, and architectural choices survive context compaction, session boundaries, or model handoffs. It provides structured method…
Deliberative multi-agent code review system
This skill orchestrates a multi-perspective code review by delegating tasks to specialist subagents. It uses gemot to aggregate findings, identify points of disagreement (cruxes), and propose compromises for resolution.
Comprehensive Codebase Technical Debt Auditor
This skill coordinates a comprehensive technical debt audit by scoping the codebase across four vectors: architectural, structural, operational, and hygiene. It executes a dedicated agent to generate a detailed, prioritized audit document s…
Codebase Documentation Drift Auditor
This skill orchestrates a comprehensive documentation drift audit, comparing existing documentation against the live codebase across six phases, including structure, links, and configuration. It generates a detailed audit report and recomme…
Conversational task management for TickTick
This skill integrates with TickTick to allow users to manage their to-do lists entirely through natural language conversation. It intelligently parses dates, infers priorities, and executes full CRUD operations across projects.
Codebase intelligence and dependency mapping tool
This tool indexes an entire codebase, providing deep intelligence through symbol resolution, dependency graph analysis, and semantic search. It allows developers to quickly assess file importance, trace call paths, and understand the potent…
Flaiwheel: Contextual Knowledge Base Workflow
This skill establishes institutional memory by automatically capturing and retrieving project context, architectural decisions, bug fixes, and API changes throughout a coding session. It guides the agent to proactively document learnings an…
Knowledge Base for Project Context and Memory
This skill establishes institutional memory by automatically capturing and retrieving project context, architectural decisions, bug fixes, and API changes across development sessions. It guides the developer through mandatory steps, such as…
Agent Memory Protocol and Context Management
This system provides a complete, protocol-driven memory layer for agents, managing context through structured capture, semantic recall, and consolidation. It uses local SQLite embeddings to ensure persistent, context-aware operation without…
Intelligent content saving to GROWI wiki
This skill intelligently archives content to the GROWI wiki by first suggesting optimal destination paths and then guiding the user through naming, visibility confirmation, and final page creation. It ensures content persistence while adher…
Model-Specific Image Prompt Dialect Generator
This skill translates a normalized asset brief into a highly specific prompt dialect tailored for various text-to-image models. It intelligently handles model quirks, such as token budgets, negative prompt syntax, text-in-image ceilings, an…
Update LLM pricing data from provider websites
This skill researches and updates comprehensive LLM pricing data across major providers (OpenAI, Anthropic, etc.). It ensures accuracy by only including explicitly listed models and running necessary type and unit tests upon completion.
Adversarial Code Review for ML Pipelines
Systematically hardens complex ML pipelines, such as BFCL, through iterative adversarial review rounds using external LLMs. This process tracks cumulative fixes and focuses on identifying subtle bugs that cause data corruption or evaluation…
Immich photo library search and discovery
This skill provides comprehensive photo discovery within an Immich library, supporting natural language queries, structured metadata filtering, and AI-powered visual search. It prioritises presenting results via existing albums or generatin…
Immich photo library people analysis report
This skill analyses Immich's face recognition data to generate a comprehensive report detailing unique individuals, co-occurrence patterns, and recognition quality. It identifies top people, clusters needing naming, and suggests actionable …
Intelligent Photo Album Curation and Suggestion
This skill analyzes new photo imports against existing albums, generating suggestions using a weighted score based on GPS proximity, CLIP visual similarity, and temporal fit. It profiles albums by type (e.g., location, event, theme) and req…