robertoatila
- 168 skills
- 0 followers
- 4 hours ago last updated
- ▌ Agentic Coding Heuristics · robertoatilaOperational heuristics, startup tips, and working patterns for agentic coding engines.
- ▌ Autonomous Execution Loop · robertoatilaExecutes structured work plans with evidence ledgers, worktrees, and task validation.
- ▌ Comprehensive Code Review · robertoatilaSystematic code review across security, correctness, architecture, maintainability, and test coverage.
- ▌ Headless Browser Research · robertoatilaEscalation browsing for Cloudflare/WAF-protected, login-gated, or JS-rendered pages.
- ▌ Image To Code Synthesizer · robertoatilaTranslates UI designs and mockups into pixel-perfect, accessible frontend code.
- ▌ Package Pre Publish Audit · robertoatilaAudits packages and tarballs before publishing to npm, PyPI, or Crates.io.
- ▌
- ▌ Systematic Code Debugging · robertoatilaTraces root causes of bugs, memory leaks, and regressions using systematic diagnostics.
- ▌ Skypilot Multi Cloud Compute Orchestration · robertoatilaMulti-cloud compute orchestration and automatic cost optimization for distributed ML workloads.
- ▌ Arbor Computational Neuroscience Simulation · robertoatilaSimulates morphologically detailed spiking neural networks with GPU-accelerated multicompartment models.
- ▌ Nextflow Scalable Scientific Data Pipelines · robertoatilaBuilds reproducible, containerized scientific data pipelines with Nextflow and workflow orchestrators.
- ▌ Openpi Physical Intelligence Robotics Policy · robertoatilaFine-tunes and serves OpenPI physical intelligence models for robot policy inference.
- ▌ Pennylane Quantum Differentiable Programming · robertoatilaDifferentiable quantum machine learning and hybrid quantum-classical circuit training with PennyLane.
- ▌ Simpo Reference Free Preference Optimization · robertoatilaReference-free preference optimization for efficient LLM alignment without a reference model.
- ▌ Git Bugfix Contribution 2 · robertoatila> CRITICAL POLICY: git push --force / git push -f is STRICTLY PROHIBITED.
- ▌ Openrlhf Ray Distributed Reinforcement Learning · robertoatilaDistributed RLHF training (PPO, GRPO, DPO) for large models using Ray.
- ▌
- ▌
- ▌ Pre Publish Review · robertoatilaNuclear-grade 16-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (5 agents) for holistic review, and 1 oracle for overall release synthesis. Runs ONLY when the user explicitly asks for a pre-publish review — a plain publish/release request MUST NOT trigger this; /publish ships directly. Triggers: 'pre-publish review', 'review before publish', 'release review', 'pre-release review', 'ready to publish?', 'can I publish?', 'pre-publish', 'safe to publish', 'publishing review', 'pre-publish check'.
- ▌ Tech Debt Audit 2 · robertoatilaThorough, file-cited technical debt audit across 9 dimensions using AST-grep (tree-sitter), grep, language-native tooling, and optionally CodeGraph knowledge graph. Produces TECH_DEBT_AUDIT.md with severity, effort estimates, and prioritized fixes. Use when asked for codebase health check, tech debt audit, architecture review, code quality assessment, or cleanup planning. Triggers: 'tech debt', 'technical debt', 'debt audit', 'code health', 'technical debt audit', 'codebase health check', 'find tech debt', 'debt analysis', 'audit code quality'.
- ▌ Data Scientist · robertoatilaExpert data processing with a hybrid engine strategy: resident-kernel engines first - DuckDB plus a resident Python stack (Polars/numpy/matplotlib) in persistent js/py eval kernels where the harness has them, bun/uv one-shots elsewhere - and per-action placement judgment (in-memory vs streaming vs remote-in-place). Triggers: 'analyze the data', 'what is in this CSV/parquet/json', 'summarize this', 'group by', 'filter rows', 'sort by', 'join these files', 'merge datasets', 'time series trend', 'compare yesterday and today', 'distribution/histogram', 'correlation', 'clean duplicates', 'handle missing values', 'dataset larger than RAM', 'SQL query on files', 'DataFrame operations', 'chart/plot this data', DuckDB vs Polars selection, quick data exploration CLI. NOT for plain text/code inspection, configs, or tiny inline math.
- ▌ Debugging · robertoatilaMUST USE for any real runtime debugging across ANY language or binary — crashes, silent failures, wrong responses, stuck processes, memory leaks, async misbehavior, unexplained timing, reverse engineering. Runs a hypothesis-driven loop: form ≥3 hypotheses, investigate in parallel, after 2 failed rounds spawn Oracles from orthogonal angles, confirm root cause, lock with a failing test, fix minimally, QA by actually USING the system, scrub artifacts. The actual HOW lives in `references/` — READ THEM. Triggers: 'debug this', 'why is X not working', 'hanging', 'attach a debugger', 'reverse engineer', 'pwndbg', 'gdb', 'lldb', 'node inspect', 'pdb', 'dlv', 'delve', 'rust-gdb', 'set a breakpoint', 'context window exploded', 'why is the response empty', 'why is this happening', 'trace this bug', 'reproduce and fix', 'silent failure', 'HTTP 200 but empty', 'why did it stop', 'inspect the binary', 'playwright', 'flaky test', 'fails intermittently', 'passes in isolation', 'only fails in CI'.
- ▌ Data Science Toolkit · robertoatilaStatistical analysis, feature engineering, exploratory data science, and visualization workflows in Python.
- ▌ Deadcode Elimination · robertoatilaDetects and prunes dead code, unused functions, orphan modules, and obsolete dependencies.
- ▌
- ▌ Lsp Diagnostic Setup · robertoatilaConfigures Language Server Protocol diagnostics, linters, and type checkers across codebases.
- ▌ Multi Agent Teammode · robertoatilaCoordinates teams of cooperating Codex agents with script-managed persistent state.
- ▌ Payloadsallthethings · robertoatilaCurated OWASP attack dictionaries and bypass payloads for authorized web security audits.
- ▌ Pr Review Resolution · robertoatilaAnalyzes and systematically resolves pull request review comments and automated checks.
- ▌ Visual Regression QA · robertoatilaAutomates visual regression testing across browsers, responsive viewports, and themes.
- ▌ Blackbird Osint Recon · robertoatilaFast asynchronous OSINT reconnaissance and identity verification engine across 500+ platforms.
- ▌ Coding Agent Sessions · robertoatilaInspects, searches, exports, and reconstructs coding-agent session logs across platforms.
- ▌ Parallel Task Batcher · robertoatilaBatches and dispatches parallel agent jobs with dependency resolution.
- ▌ Task Dag Orchestrator · robertoatilaDefines and executes directed acyclic graphs of interdependent agent tasks.
- ▌ Brandkit Design System · robertoatilaGenerates brand guideline boards, visual identity systems, and design tokens.
- ▌ Github Issue Pr Triage · robertoatilaTriages GitHub issues and pull requests, prioritizing bugs and mapping duplicates.
- ▌ Hyperplan Orchestrator · robertoatilaStructures multi-phase technical projects into deterministic implementation plans with verification criteria.
- ▌ Benchling Lims Laboratory Tracking · robertoatilaIntegrates Benchling API for registry entities, inventory, ELN entries, and laboratory workflows.
- ▌ Bitsandbytes 8bit Nf4 Quantization · robertoatilaQuantizes LLMs to 8-bit or 4-bit NormalFloat for memory-efficient GPU inference.
- ▌ Fsm Grammar Constrained Generation · robertoatilaConstrains LLM generation to valid JSON, XML, or Pydantic schemas using FSMs.
- ▌ Knowledge Distillation Compression · robertoatilaCompresses large language models via teacher-to-student knowledge distillation.
- ▌ Neural Audiocraft Sound Generation · robertoatilaGenerates music, audio effects, and soundscapes from text descriptions using AudioCraft.
- ▌ Requirements Interview Elicitation · robertoatilaConducts structured requirements elicitation interviews to resolve ambiguity before implementation.
- ▌
- ▌ Adaptyv Cloud Biolab Protein Assays · robertoatilaSubmits and monitors automated protein assays via Adaptyv Bio Foundry API.
- ▌
- ▌ Dspy Declarative Prompt Compilation · robertoatilaBuilds declarative LM programs, modular RAG systems, and automated prompt optimizers.
- ▌ Flash Attention Kernel Optimization · robertoatilaAccelerates transformer attention computation with IO-aware memory access and tiling.
- ▌ Hqq Fast Kernel Weight Quantization · robertoatilaHalf-Quadratic Quantization for fast 2/3/4-bit LLM compression without calibration data.
- ▌ Crewai Hierarchical Multiagent Teams · robertoatilaOrchestrates autonomous multi-agent teams with role-based collaboration and hierarchical execution.
- ▌ Llamaindex Hierarchical Query Engine · robertoatilaIngests, indexes, and queries heterogeneous documents for advanced RAG architectures.
- ▌ Megatron Tensor Pipeline Parallelism · robertoatilaTrains massive LLMs using Megatron tensor, pipeline, and sequence parallelism strategies.
- ▌ JSON Canvas Visualizer · robertoatilaCreates and edits JSON Canvas visual diagrams, flowcharts, and mind maps.
- ▌ Systematic Refactoring · robertoatilaPerforms safe, incremental code refactoring without altering existing external behavior.
- ▌
- ▌ Agentic Idea Refinement · robertoatilaRefines, stress-tests, and expands agentic ideas into concrete technical roadmaps.
- ▌ Agentic Loop Controller · robertoatilaGoal-like loop that uses ultrawork mode to decompose work into systematic,.
- ▌ Deep Project Scaffolder · robertoatilaScaffolds deep project architectures with hierarchical AGENTS.md documentation.
- ▌ Deep Technical Research · robertoatilaConducts deep technical research, literature synthesis, paper analysis, and citation verification.
- ▌ Git Bugfix Contribution · robertoatila> CRITICAL POLICY: git push --force / git push -f is STRICTLY PROHIBITED.
- ▌
- ▌ Obsidian Database Bases · robertoatilaDesigns Obsidian database base files (.base) with tabular views and filters.
- ▌
- ▌ Security Research Audit · robertoatilaAudits software components for CVEs, exposed secrets, insecure configurations, and dependency risks.
- ▌
- ▌ Agent Environment Doctor · robertoatilaDiagnoses agent installation health, environment variables, and CLI tooling dependencies.
- ▌ AI Boilerplate Sanitizer · robertoatilaSanitizes and strips AI boilerplate, conversational filler, and redundant outputs.
- ▌ Browser Devtools Testing · robertoatilaAutomated end-to-end browser testing and console/network inspection via DevTools.