Marketplace

Use when a retrieval corpus has exact or near-duplicate docs/chunks inflating embedding cost or polluting top-k results, and you must detect and prune them.

Invoke when a downstream system must consume LLM output as JSON matching a fixed schema and malformed or missing fields would break the pipeline.

Use to scan agent transcripts, traces, and telemetry for leaked secrets or PII before they are stored or shared, and to fix the root cause.

Invoke when building or tuning a RAG/semantic-search pipeline's chunking: pick strategy, chunk size, and overlap validated against retrieval metrics.

Use before running untrusted or model-generated code, installs, or binaries: stand up a disposable, network-restricted sandbox, run it, then tear it down.

Invoke when an autonomous task may outlast one context window—persist resumable checkpoints to a state file so work survives resets and interruptions.

Audit UIs against WCAG 2.2 AA and deliver prioritized, code-level fixes. Use when asked for an accessibility review, a11y compliance, or AT bug reports.

Design multi-layer caching strategies: browser, CDN, application, and database caching with invalidation patterns.

Manage Drupal in all popular forms: drush CLI, REST/JSON:API, module management, content types, Views, performance caching, and security hardening.

Design feature flag strategies: flag types, rollout percentages, kill switches, technical debt management, and cleanup schedules.

Audit codebases for i18n readiness: hardcoded strings, locale formatting, RTL support, pluralization rules, and translation workflow.

Design micro-frontend architectures: module federation, route splitting, shared dependencies, and team boundaries.

Manage AI agent products: capability roadmaps, eval-driven development, safety reviews, user trust, and launch criteria.

Design cohesive animation systems: motion principles, timing curves, choreography rules, and accessible motion.

Generate and run contract tests for REST and GraphQL APIs from OpenAPI specs or schema definitions.

Use when API reference docs must be generated or updated from source code, with verified schemas, runnable examples, and complete error catalogs.

Design API products: endpoint design for developer experience, versioning strategy, rate tiers, and ecosystem growth.

Design rate limiting strategies for APIs: token bucket, sliding window, per-user limits, and 429 response patterns.

Design WebSocket and real-time communication systems: connection management, reconnection, message protocols, and scaling.

Analyze customer churn: cohort analysis, churn signals, at-risk scoring, retention experiments, and win-back strategies.

Use when reviewing a diff, PR, or staged changes: a five-pass protocol that yields severity-ranked findings with concrete failure cases.

Create comprehensive onboarding documentation for any codebase: architecture maps, data flow diagrams, and gotchas for new developers.

Conduct systematic competitor analysis: feature matrices, positioning maps, moat assessment, and strategic gap identification.

Design ergonomic component APIs: prop design, composition patterns, accessibility defaults, and forward compatibility.