Annuaire de skills

Découvrez des skills réutilisables pour les AI agents.

Recherchez de vrais skills GitHub par tâche et vérifiez Stars, confiance, audit, catégorie et chemin d’installation avant de les utiliser.

Chaque recommandation reste clairement reliée à son dépôt, son audit et son chemin d’installation.

Résultats de recherche: executor

Annuaire en anglais

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.

34K
Stars
77/100
Confiance
Catégorie: researchAudit

Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux.

339
Stars
67/100
Confiance
Catégorie: coding-agentsAudit

A compiler, optimizer and executor for financial expressions and factors

292
Stars
69/100
Confiance
Catégorie: financeAudit

A cross-host prompt library and agent skill for managing long-horizon multi-task workflows in coding agents like Claude Code, Cursor, Codex, and Grok Build.

55
Stars
66/100
Confiance
Catégorie: coding-agentsAudit

A Codex Skill for coordinating four specialized subagents to handle development, research, analysis, and review tasks.

70
Stars
69/100
Confiance
Catégorie: coding-agentsAudit

A Python framework for managing positions and trades in DeFi

148
Stars
65/100
Confiance
Catégorie: web3-analyticsAudit

Claude Code skills: codex-sprint, review-loop (iterative simplify-review-fix), rust-dev (FAIL FAST standards)

42
Stars
69/100
Confiance
Catégorie: utilityAudit

A skill collection that separates planning from execution via verifiable goals and fresh-session handoffs for AI coding agents.

20
Stars
63/100
Confiance
Catégorie: coding-agentsAudit

A Claude Code skill that structures long coding tasks as a graph with executor and supervisor nodes to prevent drift.

26
Stars
64/100
Confiance
Catégorie: coding-agentsAudit

Curated library of battle-tested prompts for long-horizon agent tasks adapted to multiple AI agent hosts like Claude Code, Cursor, and Codex.

30
Stars
66/100
Confiance
Catégorie: coding-agentsAudit

Design, implement, and review Kotlin and Android APIs. Use when working on .kt files, Kotlin nullability, sealed classes/interfaces, coroutines, Android threading, Java interop, or Kotlin-backed React Native Nitro Module implementations.

161
Stars
59/100
Confiance
Catégorie: design-creativeAudit