engineering

Capture full browser observability for a URL — network requests, DOM snapshots, screenshots, and console logs dumped to a searchable filesystem. Use for reverse engineering, autoresearch loops, flaky test diagnosis, and pre-QA reconnaissance.

Cancel an active agentic development loop by removing its state file.

Run a full repo compatibility pass — scanner score, docs reliability, startup path, and validation efficiency — and produce a P0/P1/P2 finding list before extending agent autonomy.

Start an agentic development loop in the current session — re-injects your task prompt each iteration until the completion promise is output or max iterations is reached.

Update or create the right technical documentation for a code change, service, or workflow using the code-documentation skill.

Runs a comprehensive multi-lens PR review. Use when the user wants a thorough pre-merge review covering code quality, silent failures, test coverage, and comment accuracy. By default reviews the current git diff; can be scoped to specific files, a PR number, or a branch. Returns findings grouped by severity with file:line references and concrete fix suggestions. Should be invoked proactively before creating a PR or after completing a significant feature.

Intent-first PR triage agent. Processes a list of PRs, issues, or issue descriptions by recovering the plain-language intent behind each, judging whether the implementation actually solves the underlying problem, and routing each item to: close, escalate to a human (needs judgment / ready for landing), or continue autonomously through validation, review, and CI. Use when managing a PR queue, doing a queue health pass, or deciding which PRs should keep moving. Handles each item independently.

Leads architecture, implementation strategy, code quality, and technical delivery across the engineering surface.

Use for end-to-end software execution in an unfamiliar or complex repo: orienting the codebase, choosing an execution model, planning and verifying changes, reviewing architecture or PRs, improving agent-first harnesses, and coordinating work across the specialized `frontend` and `backend` engineering skills.

Use for AI and agent engineering work: system prompt design, tool call architecture, context engineering, memory and learning systems, multi-agent coordination, evals and regression gates, fine-tuning pipelines, RAG, vector stores (TurboPuffer/Pinecone/Azure), agent governance and safety, run steering, skill packages, prompt engineering patterns, constrained generation, ML pipelines, data engineering, and production AI infrastructure.

Use for backend engineering work such as APIs, services, data models, persistence, queues, caching, auth, background jobs, and server-side debugging or refactors.

Cross-cloud CLI-first cloud operations for AWS, Azure, and GCP. Use when the assistant needs to identify which cloud provider or multi-cloud estate a repo uses, deploy new resources or services, wire automatic deployments, inventory and optimize infrastructure, or diagnose and repair cloud failures entirely from the terminal, with explicit approval gates for high-cost, destructive, identity-sensitive, or hard-to-reverse changes. Covers AWS Amplify full-stack projects, serverless workloads (Lambda, API Gateway, Step Functions, SAM, CDK), and the full AWS database portfolio (RDS, Aurora, Aurora DSQL, DynamoDB, ElastiCache), as well as deep Azure references for diagnostics, storage, compute, compliance, identity, Foundry, and cross-cloud migrations.

This skill should be used when the user asks to write, update, review, scaffold, move, remove, or continuously improve documentation for code, folders, services, repos, workflows, architectural decisions, or operational processes. Trigger for inline docs, `README.md`, `ARCHITECTURE.md`, `TESTS.md`, `SETUP.md`, `RUNBOOK.md`, `CHANGELOG.md`, `SECURITY.md`, `OVERVIEW.md`, `FAQ.md`, `DECISIONS.md`, `DEPENDENCIES.md`, `AGENTS.md`, `PLAN.md`, `SPEC.md`, `SOUL.md`, `PRINCIPLES.md`, `DESIGN.md`, `logs/`, `lessons/`, `items/`, `fixes/`, `audits/`, `raw/`, `plans/`, `specs/`, `sources/`, `lib/`, `references/`, `cookbook/`, `knowledge/`, `runbooks/`, `research/`, `official-documentation/`, `context/`, MDX docs, JSDoc/TSDoc, docstrings, ADRs, post-mortems, migration guides, documentation cleanups, and documentation-impact reviews.