I turn recurring decisions into contracts agents can execute, verify, and improve. Some skills are public; others expose the method without publishing internal assets.
Connect over MCP so an agent can evaluate evidence, inspect services and availability, or submit a brief — without having to interpret the visual interface.
/api/mcp ↗ /game · 6 authored + 39 upstream /game2 · 6 repository-specific + 39 upstream 48 unique skills found across both codebases. The catalogue below highlights only authored or evidence-backed operating methods; third-party dependencies are not presented as my work.
Showing 25 skills
Delivery harness for running one or many coding agents through bounded specs, isolated git worktrees, feedback loops, and explicit completion gates.
Autonomous research method where every agent proposal must survive a reproducible benchmark before it enters the frontier.
Technical AEO workflow that treats crawler policy, canonical identity, entities, structured data, and machine-readable surfaces as one tested system.
Reverse-engineers every accepted frontier move to separate the transferable structural lever from nonce luck and search artifacts.
Source-anchored gate that turns papers, diffs, and hypotheses into bounded route packets before code or compute is spent.
Role factory for dispatching circuit engineers with the exact field, group, phase, ancilla, and cost constraints of a route.
Structural optimization method for point-addition circuits across qubit width, Toffoli count, live ranges, arithmetic, and score.
Correctness protocol that isolates classical output, phase behavior, and ancilla cleanup before an optimization is trusted.
Timeline-based method for finding the tallest live-qubit moment and creating safe holes through earlier uncompute or later recompute.
Gate-cost method for cutting Toffoli and non-Clifford work through algebraic fusion, measured replay, and cheaper uncomputation.
Spend-gated search protocol for estimating clean-island density, validating candidates, and deciding whether a GPU nonce hunt is economical.
Scientific collaboration contract for splitting orthogonal investigations, exchanging exact evidence, and reconciling agent disagreement.
Six-gate creation pipeline for Brazilian characters, teams, real-world maps, and 3D assets, from sourced research to in-engine validation.
Vertical-slice pipeline for shipping a playable faction as one system: roster, crest, cover, character, thumbnail, selection video, voice, and UI integration.
Clean-context critic for every new character, map, model, and texture; the builder's explanation is deliberately excluded from the review.
Method for writing invariants, probes, and thresholds that must prove they can fail before they are allowed to protect the game.
Risk classifier for deciding whether a pull request is mergeable, needs staging, or requires human gameplay or backend review.
Playable-journey gate covering menu, ranking, nickname, team and character selection, initial boot, and first HUD.
Adversarial visual-improvement loop for a browser FPS: independent critics, measured screenshots, conflict-aware builders, and regression gates.
Measurement-first debugging protocol that requires a failing ruler, a falsifiable hypothesis, and a mutation proving the fix can regress.
Editorial voice contract for technical writing grounded in shipped systems, concrete tradeoffs, and verifiable claims.
End-to-end publishing contract for paired English and Portuguese articles, localized slugs, metadata, internal links, RSS, and covers.
Visual-system skill for generating consistent bilingual article covers and social thumbnails in the portfolio's phosphor language.
Repository-aware frontend workflow combining specs, browser evidence, responsive checks, accessibility, tests, and diff review.
Agent-facing discovery skill for evaluating experience, services, availability, and starting an introduction through MCP.
Want this level of operating method in your product or team?
Start a project