AI Agent Workflow Collection

Draft or revise an academic paper from a reviewed evidence set with a coherent contribution story, explicit section contracts, and claim-evidence alignment.

Adversarially review an academic paper for reject-level defects, material weaknesses, and advisory improvements without silently rewriting it.

WCAG 2.1 AA accessibility mandates for the frontend. Use when implementing or reviewing user interface components, form inputs, modals, or motion effects.

Roleplay the most difficult, tech-resistant user for your product. Find every UX pain point, filter complaints pragmatically, and create actionable tickets.

Transition from a hands-on "bricklayer" to a high-level "architect" by managing a fleet of autonomous AI agents. Use this when you need to scale engineering output with a small team, handle repetitive migrations/bug fixes, or onboard engineers to complex legacy codebases.

Design or change backend APIs and service boundaries with explicit contracts, validation, compatibility, idempotency, and failure semantics.

Mandatory middleware, validation boilerplate, error safe-listing, and performance rules for fast, consistent, and secure endpoints.

Identity, JWT rules, session management, and security logic for authentication. Use when building or modifying login, registration, password resets, token generation, or authentication middlewares.

Implement or review backend authentication, authorization, tenancy, secret, and untrusted-input boundaries without trusting caller-supplied identity or scope.

Verify backend changes at contract and integration boundaries with deterministic success, denial, concurrency, retry, migration, and dependency-failure evidence.

Build or change queues, jobs, workers, schedulers, retries, leases, and distributed workflows with bounded concurrency and idempotent recovery.

Initializes a new project from the template. Use when starting a fresh repository, defining a new project vision, or setting up the initial codebase structure.

Get reliable output from weak or local models by tightening the harness instead of the prompt. Use when running a small/quantized/local model, when an agent loops, drifts, stalls before acting, or emits malformed tool calls, or when designing a background executor that must finish unattended. Use to pick a bounded profile — tool allowlist, turn/retry caps, forced structured output, verify loop, micro-task decomposition.

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser.

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines.

Verify that every material citation resolves, supports its adjacent claim, preserves scope, and is not stale or misleading.

Normalize collected observations into auditable claims with support, contradiction, provenance, limitations, and confidence.

Guides a service-layer extraction pass after an AI-built feature ships. Use when feature code works but contains duplicated mechanics, repeated API calls, or copy-pasted logic across multiple callers. Use when deciding what belongs in shared services vs. domain-specific actions.

Framework for surfacing and tracking tech debt, known bugs, and security gaps in software codebases.

Naming patterns, formatting rules, import order, and module design standards for modern software codebases.

Change backend domain models, persistence, schemas, and migrations while preserving invariants, tenant scope, rollback safety, and operational compatibility.

Design, implement, and verify decision-useful charts, dashboards, figures, and interactive data stories without distorting the underlying evidence.

Diagnoses and recovers from complex REST and GraphQL API failures. Enforces reproduction before fixing and verifies via runtime inspection.

Containerize applications using Docker. Enforce production-grade security, multi-stage builds, and optimized resource allocation.