Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

codebase-onboarding

Estrellas2

Forks0

Actualizado13 de marzo de 2026 a las 17:19

Rapidly map an unfamiliar research or engineering codebase, identify entry points, execution paths, configuration layers, tests, and risky modules. Use when inheriting a project, preparing a reproduction, reviewing a repo for collaboration, or locating where to modify a model, runtime, compiler, or hardware flow.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

ceasonen

ceasonen/research-skills

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Desarrolladores de softwareOcupaciones informáticas y matemáticas·SOC 15-1252

Explorador de archivos

2 archivos

SKILL.md

readonly

Más de este repositorio

mismo repositorio

accelerator-kernel-optimization

ceasonen/research-skills

Review and optimize kernels and data movement for CUDA, Triton, Metal, OpenCL, SIMD, and accelerator-style workloads. Use when diagnosing throughput gaps, memory bandwidth limits, launch overhead, occupancy issues, kernel fusion tradeoffs, or host-device transfer bottlenecks in ML and systems research.

2026-03-132

benchmark-error-analysis

ceasonen/research-skills

Build evaluation plans and error-analysis workflows for ML, retrieval, generation, systems benchmarks, and embedded or perception pipelines. Use when adding metrics, checking regressions, designing ablations, interpreting leaderboard changes, or debugging why a model improved on one slice and failed on another.

2026-03-132

compiler-runtime-analysis

ceasonen/research-skills

Analyze compiler, runtime, and code generation systems including IR lowering, scheduling, memory layout, graph compilation, autotuning, and runtime overhead. Use when profiling a compiler stack, comparing generated code, debugging performance cliffs, or evaluating compiler research claims.

2026-03-132

control-systems-state-estimation

ceasonen/research-skills

Design and debug state estimation, filtering, system identification, and control-oriented models for robotics, autonomous systems, and embedded control. Use when choosing observers, Kalman variants, sensor fusion structure, stability assumptions, or diagnosing drift, lag, and closed-loop estimation failures.

2026-03-132

dataset-curation

ceasonen/research-skills

Create and audit datasets for CS and EE research, including schema design, collection pipelines, deduplication, split strategy, leakage prevention, labeling QA, licensing, and provenance tracking. Use when building a dataset, merging corpora, preparing train, validation, and test splits, or validating a benchmark before publication.

2026-03-132

distributed-systems-debugging

ceasonen/research-skills

Debug distributed systems behavior including consistency issues, queue backlogs, retries, partitions, replica divergence, tail latency, and backpressure. Use when a service mesh, stream processor, storage system, scheduler, or multi-node research system behaves differently under scale than in local tests.

2026-03-132

name	codebase-onboarding
description	Rapidly map an unfamiliar research or engineering codebase, identify entry points, execution paths, configuration layers, tests, and risky modules. Use when inheriting a project, preparing a reproduction, reviewing a repo for collaboration, or locating where to modify a model, runtime, compiler, or hardware flow.

Codebase Onboarding

Use this skill to compress the first day of repo reading into a structured map.

Core Workflow

Identify build system, runtime entry points, and test commands.
Map the top-level architecture and the config surface.
Trace one representative execution path end to end.
Separate generated code, vendor code, and owned code.
Produce the minimal file list needed for the user's task.

Execution Rules

Prefer concrete paths and functions over vague architecture prose.
Distinguish authoritative config from defaults and examples.
Call out dead ends, stale docs, and scripts that appear unused.
End with the smallest safe edit surface.

Output Contract

Return:

Architecture map.
Entry points.
Config and dependency map.
Highest-risk modules.
Recommended reading or edit order.