Skills

Implements secure OAuth 2.0 and OpenID Connect flows including authorization code with PKCE, client credentials, and device code grants. Generates token exchange logic, refresh handling, state/nonce validation, and secure token storage. Flags common pitfalls like implicit flow usage, missing PKCE, and insecure redirect URI handling.

Curates high-quality datasets for supervised fine-tuning (SFT) and preference optimization (DPO/RLHF). Covers deduplication, quality filtering, formatting into chat/instruction templates, train/validation splits, label balancing, contamination checks against eval sets, and PII scrubbing. Produces clean, well-documented datasets ready for training.

Designs evaluation harnesses for LLM applications, covering dataset construction, task-specific metrics, LLM-as-judge rubrics with bias controls, and regression gates. Helps teams measure quality, catch regressions across model or prompt changes, and report results with confidence intervals rather than vibes.

Reviews cloud IAM policies for least-privilege violations, overly broad wildcards, privilege escalation paths, and risky trust relationships across AWS, GCP, and Azure. Explains the risk of each finding and rewrites policies to grant only the permissions actually needed.

Turns reliability goals into concrete SLIs, SLOs, and error budgets. Helps choose the right service level indicators, set realistic targets from historical data, compute burn rates, and design multi-window multi-burn-rate alerting so teams get paged before the budget is exhausted.

Drafts clear product requirements documents from rough ideas or stakeholder notes. Structures the problem statement, goals and non-goals, user stories, acceptance criteria, success metrics, and open questions, and surfaces ambiguities and edge cases that need decisions before engineering starts.

Sets up and interprets mutation testing to measure real test-suite effectiveness beyond line coverage. Configures tools like Stryker, PIT, or mutmut, explains surviving mutants, recommends targeted tests to kill them, and tunes performance for CI. Helps teams find tests that assert nothing and coverage that lies.

Designs and implements real-time services using WebSockets and Server-Sent Events. Covers connection lifecycle, heartbeats, reconnection with backoff, room/channel fan-out, backpressure, authentication on upgrade, and horizontal scaling with a pub/sub backplane. Produces production patterns for chat, live dashboards, collaborative editing, and streaming updates.

Configures HTTP security headers to harden web applications. Covers Content-Security-Policy (including nonces and strict-dynamic), HSTS, X-Content-Type-Options, Referrer-Policy, Permissions-Policy, COOP/COEP/CORP, and cookie flags. Produces server/CDN configuration, explains tradeoffs, and provides a rollout plan using report-only mode to avoid breakage.

Analyzes cloud spend and produces a FinOps optimization plan. Covers rightsizing, autoscaling, spot/reserved/savings plans, storage tiering, idle resource cleanup, data transfer reduction, and tagging for cost allocation. Prioritizes actions by savings and risk, and defines guardrails and budgets to prevent regressions.

Analyzes LLM usage and reduces inference cost without sacrificing quality. Covers prompt compression, context trimming, caching (prompt and semantic), model routing by task difficulty, batching, structured output to cut retries, and token accounting. Produces a concrete plan with estimated savings and quality guardrails.

Adds production-grade observability to a codebase by instrumenting it with structured logs, metrics, and distributed traces. Recommends span boundaries, cardinality-safe labels, and OpenTelemetry conventions, then generates the wiring code and dashboards needed to make a service debuggable in production.

Helps design and implement features for machine learning models from raw tabular, time-series, or text data. Suggests transformations, encodings, aggregations, and leakage-safe splits, explains the rationale, and generates reproducible feature pipeline code with validation.

Designs and scaffolds ergonomic command-line tools with subcommands, flags, config files, shell completions, and helpful error output. Covers argument parsing conventions, exit codes, stdin/stdout piping, colored output, progress indicators, and cross-platform packaging. Produces maintainable CLIs that follow POSIX conventions and feel great to use.

Diagnoses and fixes flaky tests by analyzing test code and CI failure history for common sources of nondeterminism such as time and timezone dependence, order dependence, shared mutable state, race conditions, and unmocked network calls. Proposes targeted fixes and quarantine strategies to keep the suite trustworthy.

Helps researchers and nonprofits draft compelling grant proposals. Structures the significance, aims, methodology, timeline, and budget justification to match a funder's priorities and review criteria, tightens the narrative, and flags gaps a reviewer would penalize before submission.

Writes end-to-end UI tests with Playwright or Cypress that mirror real user journeys. Covers resilient selectors (roles/test-ids), network stubbing, auth setup, fixtures, waiting strategies that avoid flakiness, visual and accessibility assertions, and CI integration. Produces maintainable specs and a page-object structure.

Generates consumer-driven contract tests between services so that API providers and consumers stay compatible as they evolve independently. Produces Pact-style contracts, provider verification stubs, and CI wiring, and flags breaking changes before they reach production.

Generates property-based tests that assert invariants across randomly generated inputs using frameworks like Hypothesis, fast-check, or jqwik. Identifies properties (round-trip, idempotence, invariants, oracle comparison), defines generators and shrinking, and sets up stateful testing for complex APIs. Surfaces edge cases that example-based tests miss.

Designs routing layers that dispatch requests across multiple LLMs based on task type, difficulty, latency, cost, and reliability. Covers classifier-based and heuristic routing, fallbacks and retries across providers, quality scoring, and A/B evaluation of routing policies. Helps teams get frontier quality where it matters and cheap models everywhere else.

Scans code, configuration, and git history for leaked credentials such as API keys, tokens, private keys, and connection strings. Classifies findings by severity and false-positive likelihood, and provides safe remediation steps including rotation, history scrubbing, and pre-commit prevention.