convez.ai
SkillDados & AnalyticsAvançado
OlixIgnacious

Agent Skills — Kaggle Grandmaster (Machine Learning Competitivo)

OlixIgnacious/agent-skills

12 skills Kaggle GM: EDA → features → ensemble → submissão

Ver no GitHub
InicialPluginScore · de 0 a 100

Biblioteca de skills e agents para Claude Code com 12 comandos especializados em competições Kaggle. Cobre todo o fluxo de trabalho: validação adversarial, EDA, baselines diversificados, otimização com Optuna, engenharia de features, hill climbing, stacking, pseudo-labeling e ensemble com seed. Instalável em macOS, Linux e Windows via PowerShell.

Instalação

$npx convez-ai OlixIgnacious/agent-skills

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
5
Forks
0
Acompanhando
0
Saúde
28%
Último commit
há 5 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Otimizar modelos em competições Kaggle com orquestração automática
  • Implementar validação cruzada segura e detecção de data drift
  • Engenharia de features acelerada com GPU e rastreamento de delta de CV
  • Busca bayesiana de hiperparâmetros e otimização de pesos de ensemble

Veredito

Ferramenta muito especializada para competidores Kaggle serious. Implementação sólida com agents bem estruturados, mas requer expertise em ML competitivo para máximo proveito. Excelente para acelerar fluxo de validação e ensemble.

README

A tradução para o português deste README ainda está na fila.

Agent Skills

A multi-domain Claude Code skill library — agents and skills organized by use case. Install once, use what's relevant.

macOS / Linux

bash <(curl -fsSL https://raw.githubusercontent.com/OlixIgnacious/agent-skills/main/install.sh)

Windows (PowerShell)

irm https://raw.githubusercontent.com/OlixIgnacious/agent-skills/main/install.ps1 | iex

The installer asks which domain (Kaggle / SDLC / Research / All) and which tool (Claude Code / Antigravity / Copilot / All), then downloads only the files you need.

By default, Claude Code skills are installed into ~/.claude/skills/ so they work in every project. Pass --local to install into the current project's .claude/skills/ instead:

bash <(curl -fsSL https://raw.githubusercontent.com/OlixIgnacious/agent-skills/main/install.sh) --local

How It Works

Agents are role-based AI workers Claude delegates to automatically based on your task. They have a specific persona, judgment filters, and tool access.

Skills are slash commands you invoke explicitly for step-by-step procedures with code templates.

/kaggle-grandmaster          ← you invoke a skill
"help me engineer features"  ← Claude delegates to an agent

Domains

Kaggle — Competitive Machine Learning

3 agents · 12 skills · Full GM workflow from EDA to final submission

Agents

AgentRole
kaggle-grandmasterCompetition orchestrator — decides phase, invokes skills, delegates to sub-agents
kaggle-feature-engineerFeature engineering specialist — CV-delta tracked batches, GPU-accelerated
kaggle-ensemble-builderEnsemble specialist — hill climbing, stacking, Optuna weight search, final blend

Skills

CommandPhaseWhat it does
/kaggle-grandmasterAlwaysPersona, shake-up avoidance, problem reformulation heuristics
/kaggle-adversarial-validationDay 1Detect train/test distribution shift before locking folds
/kaggle-validationDay 1Lock fold strategy — KFold / TimeSeriesSplit / GroupKFold / Multilabel
/kaggle-edaDay 1–2Distribution analysis, leakage scan, temporal pattern detection
/kaggle-baselinesDay 2–3Ridge + XGBoost + LightGBM + CatBoost with GPU backends
/kaggle-target-transformDay 2–3Log/sqrt transforms, winsorization, isotonic calibration
/kaggle-optunaDay 3+Bayesian hyperparameter search (TPE) + ensemble weight optimization
/kaggle-feature-engineeringDay 3→N-5Groupby aggs, interactions, CV-safe target encoding, lag/rolling
/kaggle-hill-climbingFinal weekGreedy ensemble selection + scipy/Optuna weight optimization
/kaggle-stackingFinal weekStage 1 OOF → Stage 2 meta-learner + residual stacking
/kaggle-pseudo-labelingFinal 3 daysFold-aware soft labels on unlabeled test data
/kaggle-extra-trainingFinal 24hSeed ensemble + full-data retrain + submission checklist

→ Domain guide · Orchestration


SDLC Workbench — Software Development Lifecycle

17 agents · 4 skills · Requirements → Architecture → Implementation → Review

Skills

CommandPhaseWhat it does
/sdlc-biz-to-techPhase 1Business requirement → TRD grounded in the codebase
/sdlc-architectural-reviewPhase 2Stress-test a TRD — scalability, security, data, ops
/sdlc-feature-devPhase 3Implement from approved TRD — TDD, full test coverage
/sdlc-code-reviewPhase 4Multi-dimensional PR review → APPROVE / REQUEST CHANGES / BLOCK

A drop-in workflow template for any codebase. Works across Claude Code, Antigravity, and GitHub Copilot.

FileTool
CLAUDE.mdClaude Code
AGENTS.mdUniversal — Antigravity + Cursor + Claude Code
GEMINI.mdAntigravity (agy)
.github/copilot-instructions.mdGitHub Copilot

→ SDLC domain guide


Research Paper Writing

2 agents · 1 skill · Venue selection → Literature review → Writing → Submission

Agentic research assistant that searches the web for top papers, fetches live journal/publisher formatting guidelines, and guides writing from abstract to references. Adapts to any venue.

Agents

AgentRole
literature-reviewerDeep literature search — arXiv, Semantic Scholar, venue proceedings. Annotated bibliography + gap analysis
venue-advisorIdentifies and ranks target journals/conferences. Fetches live guidelines, impact factors, acceptance rates

Skills

CommandWhat it does
/research-paperEnd-to-end paper writing — venue selection, literature search, section-by-section writing, publisher formatting, submission checklist

Supported publishers: IEEE, ACM, Nature, Springer (LNCS), Elsevier, NeurIPS, ICML, ICLR, ACL, CVPR, arXiv and more — guidelines fetched live.

→ Domain guide


Finance Research (coming soon)

1 agent · skills planned · Quant research, factor analysis, backtesting, portfolio construction

Agents

AgentRole
finance-researcherQuantitative research — factor IC analysis, walk-forward backtesting, risk

→ Domain guide


Meta

1 skill · Build new skills and agents for this library

CommandWhat it does
/skill-creatorGuided creation of a new skill or agent — gathers requirements, writes correctly structured files, places them in the right directories, updates the README

Repository Structure

agents/                  ← role-based AI workers (auto-delegated)
  kaggle/
    kaggle-grandmaster.md
    kaggle-feature-engineer.md
    kaggle-ensemble-builder.md
  sdlc/
    biz-to-tech-orchestrator.md
    architectural-review-orchestrator.md
    feature-dev-orchestrator.md
    code-review-orchestrator.md
    requirements-analyst.md
    code-archaeologist.md
    api-designer.md
    test-engineer.md
    technical-writer.md
    software-engineer.md
    database-internals.md
    devops-sre.md
    cybersecurity.md
    linux-debugging.md
    system-design.md
    competitive-programming.md
    ml-research.md
  research/
    literature-reviewer.md
    venue-advisor.md
  finance/
    finance-researcher.md

skills/                  ← slash-command skills, domain-prefixed
  kaggle-grandmaster/
  kaggle-adversarial-validation/
  kaggle-validation/
  kaggle-eda/
  kaggle-baselines/
  kaggle-target-transform/
  kaggle-optuna/
  kaggle-feature-engineering/
  kaggle-hill-climbing/
  kaggle-stacking/
  kaggle-pseudo-labeling/
  kaggle-extra-training/
  sdlc-biz-to-tech/
  sdlc-architectural-review/
  sdlc-feature-dev/
  sdlc-code-review/
  research-paper/
  skill-creator/

domains/                 ← per-domain workflow guides and orchestration
  kaggle/
  sdlc/
  research/
  finance/

.claude-plugin/          ← plugin manifest
  plugin.json

Contributing a Domain

  1. agents/<domain>/<domain>-<role>.md — agent with name, description, model, tools frontmatter
  2. skills/<domain>-<name>/SKILL.md — skill with description, disable-model-invocation, allowed-tools frontmatter (omit disable-model-invocation for persona/orchestrator skills)
  3. domains/<domain>/README.md — use case overview, file list, and skill chain
  4. domains/<domain>/ORCHESTRATION.md — phase-by-phase workflow (optional — see Kaggle for an example)

See the Kaggle domain as the reference implementation for skills; the SDLC domain for agents.

Ver o original no GitHub

Bom para

Relacionados