Skills

Reviews claims in a document for accuracy and verifiability. Extracts discrete factual statements, rates each as supported, unsupported, or needs-verification, flags logical inconsistencies and unsourced numbers, and suggests what evidence would confirm or refute each claim. Designed to reduce hallucinated or outdated facts before publishing.

Drafts email newsletters that get opened and read. Writes subject lines and preview text, structures the issue with a clear lead, scannable sections, and a single primary call to action, and adapts tone to the audience. Can turn a list of updates or links into a cohesive issue and suggest send-time and segmentation tips.

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.

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.

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.

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.

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.

Turns strategy into well-formed Objectives and Key Results. Coaches on ambitious yet measurable objectives, outcome-based (not output-based) key results, leading vs lagging indicators, alignment across teams, and quarterly cadence with check-ins and scoring. Flags common anti-patterns like task lists disguised as OKRs.

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.

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.

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.

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 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.

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.

Facilitates agile retrospectives that produce action, not just venting. Suggests a format suited to the team's mood, synthesizes raw notes into themes, distinguishes signal from one-off complaints, and turns discussion into specific, owned, time-boxed action items with follow-up on prior ones.

Designs data quality checks for tables, pipelines, and warehouses. Generates expectation suites covering schema conformance, null and uniqueness constraints, referential integrity, freshness, and statistical drift, then wires them into pipelines so bad data is caught before it reaches dashboards or models.

Builds robust webhook producers and consumers. Covers signature verification, idempotency keys, retry with exponential backoff, dead-letter handling, event ordering, and replay endpoints, and generates handler code plus tests so integrations survive duplicates and outages.

Builds cross-browser extensions on Manifest V3 with background service workers, content scripts, popup and options UIs, and message passing. Covers permissions scoping, storage sync, context menus, and store submission requirements for Chrome, Edge, and Firefox. Emphasizes least-privilege permissions and secure content-script isolation.

Designs recommendation systems end to end: candidate generation, ranking, and re-ranking. Covers collaborative filtering, content-based and embedding retrieval, two-tower models, cold-start strategies, feature stores, offline/online evaluation (NDCG, recall@k), and feedback loops. Produces an architecture and evaluation plan tailored to the product.