arbisoft

arbisoft/ai-skillforge

Plugin Claude Code

End-to-end development workflow: researcher, planner, and implementer agents orchestrated into a single test-driven research-plan-implement pipeline.

arbisoft/ai-skillforge

Skill Claude CodeCodex

Skill that instructs an agent to execute a plan.md task list using strict test-driven development — Red, Yellow, Green phases — one task at a time, verifying tests pass before moving on.

arbisoft/ai-skillforge

Skill Claude CodeCodex

Skill that instructs an agent to turn a research.md file into a test-driven, task-by-task implementation plan — structured so any downstream LLM agent can pick up individual tasks and execute them independently.

arbisoft/ai-skillforge

Skill Claude CodeCodex

Skill that instructs an agent to deeply explore a codebase in response to a user query — mapping current implementation, identifying impacted areas, and gathering everything needed for a downstream implementation agent.

arbisoft/ai-skillforge

Skill Claude CodeCodex

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics.

arbisoft/ai-skillforge

Skill Claude CodeCodex

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

arbisoft/ai-skillforge

Skill Claude CodeCodex

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

arbisoft/ai-skillforge

Skill Claude CodeCodex

Add x402 payment execution to AI agents — per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents need to pay for APIs, services, or other agents.

arbisoft/ai-skillforge

Skill Claude CodeCodex

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

arbisoft/ai-skillforge

Skill Claude CodeCodex

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

arbisoft/ai-skillforge

Skill Claude CodeCodex

Engineering operating model for teams where AI agents generate a large share of implementation output.

arbisoft/ai-skillforge

Skill Claude CodeCodex

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.