MCP App StoreMCP App Store
from nexus-agents12
A disciplined, test-first workflow for reproducing, triaging, and fixing software bugs while preventing regressions.
This skill provides a clear, disciplined workflow for diagnosing and fixing bugs in a codebase. It emphasizes reproducing failures reliably, localizing the causal layer, reducing to minimal repros, and implementing minimal root-cause fixes. The skill enforces a stop-the-line protocol to prevent compounding failures and mandates adding a regression test so the defect cannot reappear unnoticed. Practical commands and checklists guide issue creation, writing failing tests, running lint/type/test checks, and creating a focused PR.
Use this skill whenever a test, build, or lint fails, or when investigating reported defects and runtime errors. It is intended for reproduceable failures, flaky tests investigation, CI pipeline breakages, and any situation where a minimal, provable fix plus a regression test is required.
This skill is suitable for code-focused agents with Read/Edit/Write and Bash capabilities (tools that can run tests, edit files, and create commits/PRs).
Pure documentation skill providing a disciplined, test-first bug-fix workflow with triage sequence, stop-the-line protocol, and anti-rationalization guidance. No bundled scripts to execute. Well-written with clear steps, quality checklist, and practical counter-arguments for common debugging shortcuts. Assumes pnpm/Node.js ecosystem.
No scripts present — static analysis only. Clean skill with no security concerns. The anti-rationalization table and stop-the-line protocol are standout features.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Run Execute
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
Alpha Forge Pre-Ship Quality Gates
Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.
OpenTestAI
Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.
Blender Build-Go (bgo)
Automate build → remove → install → enable → launch cycle for Blender extensions or add-ons to speed up iteration and CI workflows.
Overnight — Autonomous Long-Running Coding
Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges
EventKit Integration (iOS/macOS)
Expert EventKit patterns for iOS/macOS: permissions, bidirectional sync, zero-width identity signatures, batch operations, and zombie-task handling.
Evolve — Goal-Driven Improvement Loop
Autonomous improvement loop that selects high-value work, runs a full research-plan-implement (/rpi) cycle, validates changes, and repeats to compound repo impr