Browse all
MCP Server Builder and Deployment Tool
This utility facilitates the construction and deployment of Model Context Protocol (MCP) servers. It provides the necessary framework for integrating complex, context-aware agentic capabilities.
Persistent Agent Memory via MCP
Provides agents with persistent memory across sessions by allowing them to recall past feedback and follow auto-generated prevention rules. The system uses an MCP server to capture task outcomes and track performance trends locally.
Automated Bluesky Reply Monitoring and Draft Queueing
This skill monitors the AT Protocol for Bluesky notifications (replies, mentions, quotes) by polling the user's PDS endpoint. It queues actionable draft replies into a local file, ensuring that no content is ever auto-posted without explici…
Agent Memory Migration Bridge for Enforcement
This CLI utility parses structured, per-role markdown memory files from the Agent Architect Kit and transforms them into actionable feedback entries for the ThumbGate runtime enforcement layer. It facilitates the migration of agent learning…
Contextual Recall for Coding Tasks
Retrieve historical context, including prevention rules, past failures, and context packs, to avoid repeating errors during coding tasks.
Search promoted lessons for corrective actions
This tool queries the promoted lessons database to retrieve comprehensive guidance on failure patterns. It searches for corrective actions, linked prevention rules, gates, and the current lifecycle state of lessons.
Governing Programmatic Agent Coding Runs
This skill governs the execution of automated coding agents across various environments (local, cloud, self-hosted). It ensures compliance by enforcing pre-run checks, bounding agent scope, and persisting comprehensive metadata before any d…
Capturing User Feedback into Structured Memories
Captures explicit user feedback into structured memories and prevention rules to optimise agentic performance. It processes quality signals like thumbs up or down to record repeatable patterns and failure prevention actions.
Manage and review automated prevention rules
This tool manages prevention rules, which are automatically generated from recurring failure patterns observed during execution. Developers can list active rules, check if a specific action is blocked, or review the history of rule promotio…
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…
Check Claude Codex bridge execution status
This skill retrieves the latest metadata regarding the Claude Codex bridge execution. It provides details such as the run timestamp, operational mode, exit status, and saved artifact paths.
DualSPHysics Particle Post-Processing Workflow
This skill automates the post-processing of DualSPHysics particle data by mapping domain-specific vocabulary to MCP tool calls. It enables automated fluid filtering, isosurface mesh extraction, and time-series animations for SPH simulations…
Codex Bridge Plugin Setup and Validation
This skill validates the operational readiness of the Codex bridge plugin within the Claude Code environment. It checks for necessary installations, verifies the availability of the `codex exec review` command, and confirms the presence of …
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…
Run Claude Codex code review
Executes a code review using a Claude Codex bridge against specified targets, including uncommitted work, base branches, or specific commits. The skill summarizes findings and provides access to the raw review artifact.
automated simulation report generation skill
This skill generates structured, comprehensive reports from raw simulation post-processing results. It supports both single-case overviews and detailed comparative analyses, compiling visualizations, quantitative data, and physical observat…
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.
Comprehensive Mesh Geometry Analysis and Inspection
This skill provides comprehensive analysis of various mesh formats (STL, OBJ, PLY, etc.), checking for manifold integrity, normal consistency, and geometric degeneracies. It also facilitates format conversion and calculates detailed mesh st…
Adversarial code review using Claude Codex
This skill executes a skeptical, adversarial review of a codebase using Claude Codex, identifying potential regressions, unsafe assumptions, and release risks. Users can scope the review by specifying a base branch, commit SHA, or focusing …
Automated CFD Simulation Visualization and Analysis
This skill automates the post-processing of Computational Fluid Dynamics (CFD) data, enabling advanced visualization of simulation outputs like pressure fields, velocity contours, and streamlines from various formats (e.g., OpenFOAM, VTK). …
Dual-write skill for capturing user feedback
This skill captures user feedback via a dual-write mechanism, storing data both in Amp's native MCP memory for immediate recall and in ThumbGate for cross-platform analytics and DPO training pairs.
Pre-Action Gates for Preventing AI Mistakes
ThumbGate intercepts agent tool calls via PreToolUse hooks, capturing negative feedback to synthesize prevention rules. This mechanism physically blocks known bad actions or repeat hallucinations before they consume tokens or execute destru…
FEA Post-Processing Workflow Skill
Automates finite element analysis post-processing by mapping structural engineering terminology to specific MCP tool calls for stress, deformation, and mode shape visualisation.
Automated Open Source Project Management Workflow
This skill codifies the entire open-source project lifecycle, automating contributor onboarding, issue triage, and structured release management. It handles version bumping, PyPI publishing, and the curation of project showcase assets.