Engineering
Agentic Development
General software-engineering orchestration skill for unfamiliar or complex repositories.
→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, and coordinating work across the specialized `frontend` and `backend` engineering skills.
ai engineeringbackendcloud management
engineering/skills/agentic-development
How it works
- • Run the repo scan helper if available, or manually map the repo from the root.
- • Read repo-local instructions before proposing architecture or touching code.
Engineering
AI Engineering
AI and data engineering skill for ML systems, pipelines, prompt workflows, evaluation, and production AI architecture.
→Use for ML, data, and AI engineering work: data pipelines, ETL and ELT, DataOps, warehouses and lakehouses, streaming systems, prompt and agent design, RAG, constrained generation, experiment design, model evaluation, feature engineering, and computer vision systems from dataset prep through production deployment.
agentic developmentbackendcloud management
engineering/skills/ai-engineering
How it works
- • Load only the reference files relevant to the current task (see Workflow Router below).
- • For data engineering: choose the processing model first — batch vs. streaming, Lambda vs. Kappa, warehouse vs. lakehouse.
Engineering
Backend
Backend engineering skill for APIs, services, schemas, persistence, and server-side operational work.
→Use for backend engineering work such as APIs, services, data models, persistence, queues, caching, auth, background jobs, and server-side debugging or refactors.
agentic developmentai engineeringcloud management
engineering/skills/backend
How it works
- • Pair with [`../agentic-development/SKILL.md`](../agentic-development/SKILL.md) for repo orientation, proof planning, and execution-mode selection.
- • Map the authoritative backend path before editing: endpoint, serializer/validator, service, job, model, schema, queue consumer, or migration owner.
Engineering
Cloud Management
CLI-first cloud operations skill for AWS, Azure, and GCP.
→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.
agentic developmentai engineeringbackend
engineering/skills/cloud-management
How it works
- • CLI-first cloud operations skill for AWS, Azure, and GCP.
Engineering
Code Documentation
Documentation skill for READMEs, architecture notes, runbooks, ADRs, changelogs, and code-adjacent technical writing.
→This skill should be used when the user asks to write, update, review, scaffold, or reorganize documentation for code, folders, services, repos, workflows, architectural decisions, or operational processes. Trigger for `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`, `runbooks/**/*.md`, `docs/**/*.md`, MDX docs, JSDoc/TSDoc, docstrings, ADRs, post-mortems, migration guides, and PR documentation-impact reviews.
agentic developmentai engineeringbackend
engineering/skills/code-documentation
How it works
- • Documentation skill for READMEs, architecture notes, runbooks, ADRs, changelogs, and code-adjacent technical writing.
Engineering
Frontend
Frontend engineering skill for browser-facing implementation, UI systems, and design-quality work.
→Use for frontend engineering work such as components, routes, state management, accessibility, performance, design-system integration, and browser-facing debugging or refactors.
agentic developmentai engineeringbackend
engineering/skills/frontend
How it works
- • Pair with [`../agentic-development/SKILL.md`](../agentic-development/SKILL.md) for repo orientation and proof planning.
- • Map framework boundaries, route ownership, state owners, design-system sources, analytics seams, and error-reporting seams before editing.
Engineering
Pentest
Authorized offensive-security skill for validating exploitability against approved targets.
→Use for authorized hands-on offensive security work against staging, sandbox, or lab targets. Covers pentest planning, finding validation, exploitability proof, raw HTTP replay, browser and API testing, network and cloud assessment, secrets and misconfiguration discovery, bounded post-exploitation, and evidence-driven pentest reporting. Do not use for passive code review or compliance audits.
agentic developmentai engineeringbackend
engineering/skills/pentest
How it works
- • Authorized offensive-security skill for validating exploitability against approved targets.
Engineering
PR Management
Pull request management skill for designing or improving review systems, merge policies, SLAs, and workflow health at team scale.
→Pull request management skill for teams from 1 to 1000+ engineers. Use when the user needs to design or improve PR workflow, review queues, merge policy, ownership rules, branch strategy, review SLAs, CI gating, metrics, or operating rituals for getting code reviewed and merged safely at scale.
agentic developmentai engineeringbackend
engineering/skills/pr-management
How it works
- • Pull request management skill for designing or improving review systems, merge policies, SLAs, and workflow health at team scale.
Engineering
Quality Assurance
End-to-end QA skill for testing, debugging, secure engineering, code review, and release confidence.
→End-to-end quality assurance and secure engineering for any software repo: code review, test strategy, bug triage, debugging, flaky-test repair, coverage analysis and improvement, suite architecture, CI quality gates, secure coding reviews, security audits, threat modeling, compliance validation, and dependency or vulnerability management for frontend, backend, full-stack, and AI systems. Use when reviewing PRs, writing or repairing tests, debugging failing suites, improving release confidence, creating test plans, running passive security reviews, or translating threats into requirements. For authorized active penetration testing, exploit validation against a running target, or pentest reporting, use `pentest`.
agentic developmentai engineeringbackend
engineering/skills/quality-assurance
How it works
- • Run `python <skill-dir>/scripts/qa-scan.py <repo-root>` when the bundled scanner is available; otherwise perform the same stack and CI inventory manually.
- • Preserve and read the full failure artifact set before changing code: stack traces, failing assertions, screenshots, traces, query logs, retry logs, seeds, and the first bad CI step.