whole codebase refactor manager
by nowrich
Orchestrate and verify large-scale, cross-module codebase refactors with automated planning and testing.
New: UPI payments are live. Buyers in India can now pay for skills with UPI in INR -> Browse skills
THE AGENSI STORE
118 skills found
by nowrich
Orchestrate and verify large-scale, cross-module codebase refactors with automated planning and testing.
by YK
An evidence-based, checklist-driven workflow for auditing and verifying AI-generated code before deployment.
Takes software work from coding and debugging through testing, release readiness, deployment verification, and production recovery.
Repair feature-flag lifecycle drift in a repository using Cursor.
Repair GraphQL nullability drift across schemas, resolvers, loaders, ORM models, generated types, clients, caches, tests, and docs.
by Johnny Gu
Detect unfinished code, empty tests, and swallowed errors in AI-generated diffs using structural analysis.
Transform vague coding requests into production-ready AI coding prompts with context, constraints, architecture, tests, acceptance criteria, and verification gates.
Repair webhook-signature contract drift in a repository using Cursor.
Organize supplied accessibility feedback into a traceable evidence map with Claude.
by GarphenGate
A methodical debugging specialist that enforces reproduction and isolation before fixing code.
by nowrich
Architect production-ready system prompts, evidence policies, and failure-handling logic for AI agents.
Stress-test AI agents for security, reliability, tool abuse, data leakage, failure modes, and production readiness before deployment.
by monna
Test ChatGPT workspace skill routing across direct triggers, exclusions, collisions, Memory conditions, and conversation carryover.
by blockie710
Verify and benchmark DSP audio plugins by identifying harness bugs, measuring real THD, and auditing CPU load.
AI Agent Reliability Architect is a production-grade reliability engineering system for AI agents. It systematically discovers capabilities, maps failure modes, generates golden-path, boundary, recovery, and adversarial tests, evaluates tool use and state behavior, and produces an evidence-based Agent Reliability Score™. It includes a deliberate human review checkpoint, remediation planning, regression testing, and final QA—helping teams identify hidden failures and harden AI agents before deployment.