Desenvolvimento

Audit shipping costs and identify savings across carriers, zones, and modes. Use when you need to compare UPS/FedEx/USPS/DHL rates, analyze zone-skip and zone-reduction opportunities, find parcel-to-LTL and LTL-to-FTL modal break points, audit accessorial surcharges (fuel, residential, DAS, DIM weight), evaluate carrier contract negotiation leverage, benchmark lane rates against market, optimize m

Audit a job matching platform for relevance, fairness, and candidate experience. Evaluates matching algorithm precision and recall, skill taxonomy and NLP extraction, culture fit modeling risks, algorithmic bias detection (EEOC, NYC Local Law 144, EU AI Act), geographic and remote work handling, salary range accuracy, and feedback loop quality. Use when building or reviewing job boards, ATS matchi

Delegate coding tasks to OpenCode CLI agent for feature implementation, refactoring, PR review, and long-running autonomous sessions. Requires the opencode CLI installed and authenticated.

Scan codebase for Martin Fowler's catalog of code smells: god classes, long methods, feature envy, data clumps, primitive obsession, shotgun surgery, message chains, and more. Reports each smell with file location, severity, and specific refactoring recommendation. Ranks worst files and builds a prioritized refactoring queue. Use when code feels messy, before a major refactor, to find maintainabil

Chains /mvp → /spec — analyzes an app from video/screenshots/description, then generates implementation stories. Triggers: analyze and spec, product analysis to stories, app teardown to specs, full analysis pipeline, mvp to spec.

Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file stagin

Generate an institutional-grade commercial real estate underwriting model — input schema (T-12 income, T-3 trailing, rent roll, debt terms, exit assumptions), calc engine (Cap Rate, NOI, Cash-on-Cash, IRR, DSCR, Debt Yield, ROI, Equity Multiple, levered & unlevered returns), 10-year proforma, sensitivity tables (cap rate × growth × exit cap), partner waterfall (pref + carry tiers), and PDF/Markdow

Audit a media production studio or post-production facility. Analyzes facility scheduling and utilization, equipment lifecycle tracking, editorial and VFX pipelines, color grading and finishing workflows, digital asset management (MAM/DAM), IMF/MXF format compliance, SMPTE standards adherence, content security posture (TPN readiness), and talent/crew coordination systems.

Ensure that new complex models actually outperform simple, naive baselines.

Audit my project's third-party integrations or set up multiple at once — scans for payments, auth, email, push, analytics, storage, search, and realtime, calculates a production-readiness health score, identifies gaps, and chains sub-skills to fill them

Stress-test your product through 6 adversarial decision-maker personas -- skeptical board member, activist investor, power user, churned customer, competitor CEO, and enterprise procurement officer. Each persona attacks from a different strategic angle with findings grounded in actual code references. Use when you need to red-team a product, challenge business viability, find competitive weaknesse

Analyze game design documents and implementations for core gameplay loop clarity and depth, XP leveling curves and unlock pacing, difficulty curve spikes and plateaus, skill tree viability, player motivation via Self-Determination Theory, feedback loop quality across immediate-short-medium-long timescales, session design and retention hooks, and MoSCoW/RICE feature prioritization scoring.