Gonglitian

58 mods across 1 repository, 2 stars between them.

audio-transcribe

01

Gonglitian/agent-skills

Skill Claude CodeCodex

Transcribe audio files to text using faster-whisper with smart parallel GPU processing. Trigger when user says '转录', '音频转文字', 'transcribe', '语音识别', '听写', '把这个音频转成文字', '帮我转录一下', 'speech to text', or provides audio/video files (mp3, m4a, wav, mp4) and wants text output. Also trigger when user mentions extracting text…

2 1mo ago B 111 tokens

auto_experiment

02

Gonglitian/agent-skills

Skill Claude CodeCodex

Automated experiment workflow for code + data experiments with structured planning, execution, and reporting. Trigger when user wants to run a full experiment cycle, says "开始实验", "跑一下验证", "实验流程", "setup experiment", "run experiment", "验证一下", "搭建实验", or needs workspace creation + iterative experiment loop + final…

2 1mo ago A 76 tokens

checkGPUStatus

03

Gonglitian/agent-skills

Skill Claude CodeCodex

A Chinese-language tool for checking GPU availability on five named remote servers and their Slurm computing-cluster status.

2 1mo ago A 148 tokens

Gonglitian/agent-skills

Skill Claude CodeCodex

Automated full-spectrum research survey. Uses litian-academic-search (7-source) for academic papers + WebSearch site: filters for social media. Ingests all found papers via paper-read --light. Produces structured FINALREPORT.md per topic + concept glossary with pseudocode. Use when user wants "全面调研", "综合调研", "survey…

2 1mo ago A 0 tokens

data-pipeline-check

06

Gonglitian/agent-skills

Skill Claude CodeCodex

Validate data pipeline integrity, check dataset format compatibility, verify data quality, and diagnose data loading issues. Trigger when user mentions data problems, format conversion, dataset validation, or says "检查数据", "数据格式", "data check", "数据质量", "数据对不对", "格式兼容吗", "数据结构", "数据长什么样", "action space对得上吗", "验证数据".

2 1mo ago A 90 tokens

domain-wiki

07

Gonglitian/agent-skills

Skill Claude CodeCodex

Build and query a structured, provenance-tracked, freshness-aware knowledge base for any specialized domain, so an agent can pull real, citeable engineering knowledge into a long task instead of relying on parametric memory. Use this when work depends on hard-won domain details that the model is likely to get subtly…

2 1mo ago A 184 tokens

engineering-loop

08

Gonglitian/agent-skills

Skill Claude CodeCodex

Run a long-horizon, evidence-driven engineering loop for any task that is an experiment system, not a one-shot generation — repeatedly proposing, implementing, validating, and promoting candidates against a fixed baseline until a measurable target is met. Use this whenever a task will span many iterations and hours…

2 1mo ago A 187 tokens

evidence-report

09

Gonglitian/agent-skills

Skill Claude CodeCodex

Turn objective measurements into a ranked, evidence-backed diagnosis and a next-step plan — instead of guessing at what's slow/wrong and changing things hopefully. Use this whenever you need to understand why something underperforms (a slow kernel/query/endpoint/job, a regression, a model that's underperforming, high…

2 1mo ago A 184 tokens

experiment-plan

10

Gonglitian/agent-skills

Skill Claude CodeCodex

Turn a refined research proposal into a claim-driven experiment roadmap with progressive 4-stage execution order. Reads from research-refine output (FINALPROPOSAL.md). Produces EXPERIMENTPLAN.md + EXPERIMENTTRACKER.md. Use after research-refine, or when user says "实验计划", "experiment plan", "设计实验", "ablation matrix"…

2 1mo ago A 85 tokens

experiment-run

11

Gonglitian/agent-skills

Skill Claude CodeCodex

Execute experiments from EXPERIMENTTRACKER.md produced by experiment-plan. For each TODO run: launch training/eval, monitor via gpu-train-monitor, auto-diagnose failures via train-debug, collect results, update tracker. Bridges the gap between planning (experiment-plan) and reporting (experimentreport). Use when user…

2 1mo ago A 0 tokens

experiment-report

12

Gonglitian/agent-skills

Skill Claude CodeCodex

Write structured experiment reports from experiment-run output. Consumes results/ / + EXPERIMENTTRACKER.md. Reports are scannable: TL;DR + summary table first. Trigger when user says "写个报告", "总结实验结果", "实验报告", "experiment report", or after experiment-run completes.

2 1mo ago A 0 tokens

find-skills

13

Gonglitian/agent-skills

Skill Claude CodeCodex

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

2 1mo ago A 67 tokens

gap-to-method

14

Gonglitian/agent-skills

Skill Claude CodeCodex

A research workflow that maps published work across several design dimensions, finds gaps, and suggests methods for addressing them. It uses semantic database and web searches to gather papers and evidence.

2 1mo ago A 191 tokens

Gonglitian/agent-skills

Skill Claude CodeCodex

Diagnose and fix Chinese / Japanese / Korean (CJK) input method (IME) issues in Ghostty terminal on Linux — specifically the snap-distributed Ghostty + fcitx5 + GTK4 + X11 / Wayland combination. Trigger this skill whenever the user reports: 'ghostty 输入不了中文 / 中文打不了 / 输入法不工作 / fcitx 在 ghostty 里失灵', 'ghostty 装好了但输入法没反应'…

2 1mo ago B 291 tokens

gpu-train-monitor

16

Gonglitian/agent-skills

Skill Claude CodeCodex

Monitor multi-GPU training jobs, check GPU utilization, parse training logs, track loss curves, and provide real-time status reports. Trigger when user asks about training progress, GPU status, loss monitoring, or says "现在怎么样了", "训练进度", "GPU状态", "check training".

2 1mo ago A 65 tokens

image-gen

17

Gonglitian/agent-skills

Skill Claude CodeCodex

An image-generation and image-editing tool for creating pictures from text, modifying existing images, combining several images, and making diagrams for papers or public explanations. It supports the nano and gpt image backends and named visual styles.

2 1mo ago A 360 tokens

Gonglitian/agent-skills

Skill Claude CodeCodex

A development guide for Isaac Lab, a robotics simulation framework, focused on generating and collecting movement data asynchronously across parallel simulations.

2 1mo ago A 76 tokens

isaaclab-dev

19

Gonglitian/agent-skills

Skill Claude CodeCodex

A reference guide for Isaac Lab, a robotics simulation framework for building and testing robot environments in software.

2 1mo ago A 82 tokens

kda

20

Gonglitian/agent-skills

Skill Claude CodeCodex

The orchestration entry point for running a Kernel-Design-Agents-style engineering loop on any domain — it ties together three sibling skills (engineering-loop for control, domain-wiki for knowledge, evidence-report for measurement) into one long-horizon, auditable, evidence-driven workflow. Use this when a task is an…

2 1mo ago A 168 tokens

Gonglitian/agent-skills

Skill Claude CodeCodex

Multi-source academic literature search across 7 data sources (OmniBox local KB, arXiv, Semantic Scholar, OpenAlex, DeepXiv, WebSearch, WebFetch). Use whenever the user asks about research topics, wants literature review, searches for papers, asks "what's the state of X", "find papers about Y", "文献检索", "学术搜索", "找论文"…

2 1mo ago A 123 tokens

long-horizon-spec

22

Gonglitian/agent-skills

Skill Claude CodeCodex

A planning skill for defining the scope, goals, and checkable acceptance criteria of a long or complex coding task in a SPEC.md file before implementation begins. It uses a collaborative planning process to clarify unclear requirements.

2 1mo ago A 248 tokens

marp-slide

23

Gonglitian/agent-skills

Skill Claude CodeCodex

Create professional Marp presentation slides with 7 beautiful themes (default, minimal, colorful, dark, gradient, tech, business). Use when users request slide creation, presentations, or Marp documents. Supports custom themes, image layouts, and "make it look good" requests with automatic quality improvements.

2 1mo ago A 64 tokens

Gonglitian/agent-skills

Skill Claude CodeCodex

Cross-platform information gathering from Xiaohongshu, Bilibili, Zhihu, and X/Twitter. Trigger when user wants to search, collect, or gather information across social platforms, says '全网搜索', '多平台搜索', '从各个平台搜', '搜集信息', 'search all platforms', '帮我搜一下', '调研一下社交媒体上的讨论', or mentions wanting opinions/discussions from…

2 1mo ago B 112 tokens