Image Visual Check
jjjkkkjjj/Matft
Procedure for adding tests for Matft's image processing (Matft.image., indexing or channel swapping on images, etc.), generating comparison images that put the result next to an OpenCV reference…
用 MaaCore 本体对本地图片（用户日志反馈包截图、自己截的图）离线验证识别结果：pipeline 任务为什么没命中、模板匹配得分多少、OCR 认出了什么、物品模板匹配情况。用户提到 ｢验证识别｣｢为什么没识别/没命中｣｢模板分数/得分｣｢OCR 结果对不对｣｢排查反馈包截图｣或给了截图要复现 core 行为时使用。与外部脚本（python 直调 ppocr/OpenCV）的区别：本工具走…
Install Core Image Eval
$ npx skills add MaaAssistantArknights/MaaAssistantArknights --skill core-image-eval -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install MaaAssistantArknights/MaaAssistantArknights core-image-eval --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/MaaAssistantArknights/MaaAssistantArknights.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/core-image-eval .claude/skills/core-image-eval && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "core-image-eval" agent skill from https://github.com/MaaAssistantArknights/MaaAssistantArknights/tree/dev-v2/.agents/skills/core-image-eval into .claude/skills/core-image-eval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "core-image-eval", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/MaaAssistantArknights/MaaAssistantArknights/tree/dev-v2/.agents/skills/core-image-evalType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add MaaAssistantArknights/MaaAssistantArknights --skill core-image-eval -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install MaaAssistantArknights/MaaAssistantArknights core-image-eval --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MaaAssistantArknights/MaaAssistantArknights.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/core-image-eval .agents/skills/core-image-eval && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "core-image-eval" agent skill from https://github.com/MaaAssistantArknights/MaaAssistantArknights/tree/dev-v2/.agents/skills/core-image-eval into .agents/skills/core-image-eval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "core-image-eval", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MaaAssistantArknights/MaaAssistantArknights --skill core-image-eval -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install MaaAssistantArknights/MaaAssistantArknights core-image-eval --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MaaAssistantArknights/MaaAssistantArknights.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/core-image-eval .cursor/skills/core-image-eval && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "core-image-eval" agent skill from https://github.com/MaaAssistantArknights/MaaAssistantArknights/tree/dev-v2/.agents/skills/core-image-eval into .cursor/skills/core-image-eval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "core-image-eval", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/MaaAssistantArknights/MaaAssistantArknights.git --path .agents/skills/core-image-eval--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add MaaAssistantArknights/MaaAssistantArknights --skill core-image-eval -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install MaaAssistantArknights/MaaAssistantArknights core-image-eval --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MaaAssistantArknights/MaaAssistantArknights.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/core-image-eval .gemini/skills/core-image-eval && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "core-image-eval" agent skill from https://github.com/MaaAssistantArknights/MaaAssistantArknights/tree/dev-v2/.agents/skills/core-image-eval into .gemini/skills/core-image-eval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "core-image-eval", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install MaaAssistantArknights/MaaAssistantArknights core-image-evalInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add MaaAssistantArknights/MaaAssistantArknights --skill core-image-eval -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/MaaAssistantArknights/MaaAssistantArknights.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/core-image-eval .github/skills/core-image-eval && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "core-image-eval" agent skill from https://github.com/MaaAssistantArknights/MaaAssistantArknights/tree/dev-v2/.agents/skills/core-image-eval into .github/skills/core-image-eval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "core-image-eval", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MaaAssistantArknights/MaaAssistantArknights --skill core-image-eval -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install MaaAssistantArknights/MaaAssistantArknights core-image-eval --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MaaAssistantArknights/MaaAssistantArknights.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/core-image-eval .opencode/skills/core-image-eval && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "core-image-eval" agent skill from https://github.com/MaaAssistantArknights/MaaAssistantArknights/tree/dev-v2/.agents/skills/core-image-eval into .opencode/skills/core-image-eval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "core-image-eval", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
core-image-eval- GitHub stars
- 24k
- Token cost
- ~899 tokens
- SKILL.md length
- 189 words
- Files
- 1
- Skills in repo
- 8
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
用 MaaCore 本体对本地图片（用户日志反馈包截图、自己截的图）离线验证识别结果：pipeline 任务为什么没命中、模板匹配得分多少、OCR 认出了什么、物品模板匹配情况。用户提到 ｢验证识别｣｢为什么没识别/没命中｣｢模板分数/得分｣｢OCR 结果对不对｣｢排查反馈包截图｣或给了截图要复现 core 行为时使用。与外部脚本（python 直调 ppocr/OpenCV）的区别：本工具走…
- Works in 3 steps: ｢任务为什么没命中｣：report 该任务 → miss 时看 asst.log… → ｢OCR 为什么没匹配 expected｣：ocr 看引擎原文，report… → ｢物品图标认成别的｣：depot（或 templ…
- Development work in your project
- SKILL.md covers 前置条件, CLI 用法（人工快速验证）, Agent 编程用法（写脚本组合调用） and 关键语义, plus 1 more section
- Calls python, cmake and pip
What it does
Core Image Eval is an agent skill from MaaAssistantArknights/MaaAssistantArknights. 用 MaaCore 本体对本地图片（用户日志反馈包截图、自己截的图）离线验证识别结果：pipeline 任务为什么没命中、模板匹配得分多少、OCR 认出了什么、物品模板匹配情况。用户提到 ｢验证识别｣｢为什么没识别/没命中｣｢模板分数/得分｣｢OCR 结果对不对｣｢排查反馈包截图｣或给了截图要复现 core 行为时使用。与外部脚本（python 直调 ppocr/OpenCV）的区别：本工具走 core 完整链路（前处理、ocrReplace、mask、各服 OCR 模型），结果与运行时一致。
Its SKILL.md is about 900 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development. It works with Python and OpenCV. The repository describes itself as: 《明日方舟》小助手，全日常一键长草！| A one-click tool for the daily tasks of Arknights, supporting all clients. The licence is AGPL-3.0.
When your agent uses it
- Development work in your project
Example prompts
- “/core-image-eval”
Requirements
- Python 3
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- ｢任务为什么没命中｣：report 该任务 → miss 时看 asst.log 里该模板的 match_templ 行（score 距阈值差多少）。
- ｢OCR 为什么没匹配 expected｣：ocr 看引擎原文，report 看经过 ocrReplace/expected 过滤后的结果，两者对比定位是识别问题还是替换表问题。
- ｢物品图标认成别的｣：depot（或 templ 指定多个候选物品）看各候选的分数差。
What it can do on your machine
Read from SKILL.md and the folder at commit 2ab53cc. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pythoncmakepip
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Core Image Eval loads about 899 tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 189 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from MaaAssistantArknights/MaaAssistantArknights at commit 2ab53cc, republished under its AGPL-3.0 licence (© MaaAssistantArknights). 189 words, ~899 tokens.
Download SKILL.mdSave it as
.claude/skills/core-image-eval/SKILL.md (or your agent's skills folder).- name
- core-image-eval
- description
- 用 MaaCore 本体对本地图片（用户日志反馈包截图、自己截的图）离线验证识别结果：pipeline 任务为什么没命中、模板匹配得分多少、OCR 认出了什么、物品模板匹配情况。用户提到 ｢验证识别｣｢为什么没识别/没命中｣｢模板分数/得分｣｢OCR 结果对不对｣｢排查反馈包截图｣或给了截图要复现 core 行为时使用。与外部脚本（python 直调 ppocr/OpenCV）的区别：本工具走 core 完整链路（前处理、ocrReplace、mask、各服 OCR 模型），结果与运行时一致。
MaaCore 本地图片离线评估
工具是 tools/maa_core_eval.py（自包含 ctypes 模块，可 import 也可 CLI）。core 侧入口为 DebugTask 参数化（AsstAppendTask(handle, "Debug", params)），仅 Debug 构建 的 MaaCore.dll 可用。
前置条件
- MaaCore Debug 构建：默认取
build/bin/Debug/MaaCore.dll，没有则cmake --build build --target MaaCore --config Debug。 - 资源根默认仓库根（
AsstLoadResource语义：其下找resource/）；外服加--global YoStarJP/YoStarEN/YoStarKR/txwy—— 分服的 OCR 模型、模板与任务定义随资源叠加切换，识别即切到对应服。 depot模式的模板涂黑处理依赖 Pillow（pip install pillow）。- Debug 构建日志会镜像 stdout，过滤干扰行用
grep -v '^\[[0-9]\{4\}-'；完整日志在 user_dir 的debug/asst.log。
CLI 用法（人工快速验证）
# 任务命中评估（hit/score/box/OCR 文本）
python tools/maa_core_eval.py --mode report --tasks "TaskA,TaskB" 图.png
# OCR 原始识别文本（不套 ocrReplace/expected）
python tools/maa_core_eval.py --mode ocr [--roi x,y,w,h] 图.png
# 首命中 + next 列表（线上 find_first 同款）
python tools/maa_core_eval.py --mode pipeline --tasks "TaskA" 图.png
# 图片序列按 next 链推进（纯识别，不执行 action）
python tools/maa_core_eval.py --mode replay --tasks "TaskA" 1.png 2.png 3.png
# 裸模板匹配（物品图标等非任务模板；支持目录全量）
python tools/maa_core_eval.py --mode templ [--task 任务名] [--resize w,h] --templates "2001,items/xxx.png,items" 图.png
# 仓库物品匹配（复刻线上 DepotImageAnalyzer 预处理）
python tools/maa_core_eval.py --mode depot [--templates "2001,..."] 图.pngAgent 编程用法（写脚本组合调用）
import sys; sys.path.insert(0, "tools")
from maa_core_eval import CoreEval
ev = CoreEval(global_client="YoStarJP") # 默认国服用 CoreEval()，本例为日服
ev.report(images=["1.png"], tasks=["TaskA"])
ev.pipeline(images=["1.png"], tasks=["A", "B"]) # 返回含 next，可自行驱动链
ev.ocr(images=["1.png"], roi=[100, 200, 300, 50])
ev.templ(images=["1.png"], templates=["2001"], task="DepotMatchData", resize=[1066, 599])
ev.replay(images=["1.png", "2.png"], tasks=["A"])
ev.close()返回均为 list[dict]，字段见各方法 docstring。
关键语义
- report：JustReturn 任务恒命中，结果的
algorithm字段标注了任务算法（JustReturn 时 score=0、rect=[0,0,0,0]，不是 bug）；未命中的任务只报 miss，最高分等细节看asst.log的match_templtrace。 - pipeline：命中详情在
result字段（task为完整任务名含@前缀），next为命中任务的 next 列表；replay 即靠next逐图推进。 - templ：内部阈值放开，恒报最佳得分，hit 由
threshold判定（缺省取task任务的阈值，无task时 0.8）；task参数让 Matcher 的 maskRange/colorScales/method 取自该任务，任务的 roi 同样生效（不传roi时识别区域即任务 roi；复刻线上自定义识别器的关键），resize在 core 侧先归一 1280x720 再 INTER_AREA 缩放（两级与线上截图缩放链一致，数值敏感预处理别在 python 做）；返回 error 表示输入问题（模板缺失/模板大于 roi 等），不存在正常的 ｢无结果｣。 - depot：
depot_items复刻的是｢单个模板的匹配行为｣，不是线上完整的选物逻辑 —— 线上 DepotImageAnalyzer 逐格匹配、按颜色筛候选并受材料顺序约束，本工具是整张图对全部 MATERIAL 候选各取全图最佳；所以它适合验证 ｢某模板在某图上的分数｣，不能直接等同线上会认出的物品清单。复刻要点：模板右下 80x50 涂黑 +resize到DepotMatchData的 roi +task="DepotMatchData"（其 maskRange 排除数量角标）；数量识别不在复刻内。 - 评估不带实例，
cache: true的任务不会命中 rect 缓存，结果相当于线上 ｢第一次识别｣；线上后续识别被限制在缓存 rect 内，若怀疑缓存导致的线上偏差，注意这一差异。 - 图片自动 INTER_AREA 归一到 1280x720（与线上截图缩放一致；非 16:9 的图会被拉伸并打 warn，结果与该分辨率的线上行为不可比），识别不受历史 rect 缓存污染。
- 连着模拟器要在线验证任务流（含点击 action）用 Custom 任务，本工具只做离线图片评估。
- 仅支持 Windows（
ctypes.WinDLL+MaaCore.dll）；AsstLoadResource是进程级的 —— 同一进程先建日服CoreEval再建国服的，日服资源叠加不会撤掉，需要分服独立评估请分开进程跑。
排查套路
- ｢任务为什么没命中｣：report 该任务 → miss 时看
asst.log里该模板的match_templ行（score 距阈值差多少）。 - ｢OCR 为什么没匹配 expected｣：
ocr看引擎原文，report看经过 ocrReplace/expected 过滤后的结果，两者对比定位是识别问题还是替换表问题。 - ｢物品图标认成别的｣：
depot（或 templ 指定多个候选物品）看各候选的分数差。
© MaaAssistantArknights, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/core-image-eval of MaaAssistantArknights/MaaAssistantArknights.
Open the folder on GitHubat commit 2ab53cc
Compare with similar skills
Core Image Eval next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Core Image Eval this skillMaaAssistantArknights/MaaAssistantArknights | 24k | — | ~899 | Automated safety check: Pass | AGPL-3.0 | |
| Image Visual Checkjjjkkkjjj/Matft | 147 | — | ~2.3k | Automated safety check: Pass | BSD-3-Clause | |
| Torch Performance Optimizationalbumentations-team/albucore | 123 | — | ~895 | Automated safety check: Pass | MIT | |
| Srt Whiteboard Animationgeeklee/srt-whiteboard-animation | 4.1k | — | ~1.8k | Automated safety check: Pass | MIT | |
| ComfyUI Custom Node BuilderConstantineB6/comfy-pilot | 230 | — | ~897 | Automated safety check: Pass | MIT | |
| Env Setupwwwzhouhui/skills_collection | 282 | — | ~3.5k | Automated safety check: Notes | None |
Similar skills
Torch Performance Optimization
albumentations-team/albucore
Optimize or review eager CPU-only Albucore PyTorch runtime paths with benchmark-backed decisions.
Srt Whiteboard Animation
geeklee/srt-whiteboard-animation
将 SRT 字幕做成暖米黄纸张底的白板手绘动画：读字幕→输出配图策略→确认后生成统一风格线稿→按叙事语义标注分区→预览台调整→渲染 MP4。编排沿用分区遮罩揭示（annotation.json / sequence / startMs / protectedRegions），但每个区域内的落墨换成 stream 的连续笔迹（骨架/网格 ink→color）。当用户提供 SRT…
ComfyUI Custom Node Builder
ConstantineB6/comfy-pilot
Helps an agent write ComfyUI custom nodes in Python, including wrapping an existing script, mapping data types and handling image batches.
Env Setup
wwwzhouhui/skills_collection
Checking and provisioning the machine's environment for the video-agent-kit plugin — probing for ffmpeg/ffprobe that actually carry the encoders and filters we render with (libx264/aac/libmp3lame…
Generating Python Installer
affaan-m/ECC
Commercial-grade Python installer expert for Windows: Nuitka extreme compilation, dist slimming, DLL footprint analysis, and Inno Setup packaging to ship the smallest, fastest installers.
More from MaaAssistantArknights/MaaAssistantArknights
All 8 skills in this repoChangelog
MaaAssistantArknights/MaaAssistantArknights
依据 git 提交、diff、现有 CHANGELOG 与 tag，生成符合 MAA 规范、可直接写入 CHANGELOG.md 的最终 Markdown。用户提到发版、整理/生成 changelog、写更新日志、发布正式版或 beta 时均应使用本 skill，即使用户没有明确说出 "changelog" 一词。
Maa Cyber Fortune Master
MaaAssistantArknights/MaaAssistantArknights
用“赛博道士 + 故障玄学 + 半懂不懂技术分析”的风格回复 MAA 用户的简略求助。用于用户只给一句模糊问题、没有日志、没有截图、没有报错时，做一段短小离谱但认真的玄学诊断。触发词可包括“赛博算卦”“玄学回复”“评论区整活”“帮我写一段离谱但正经的故障分析”
Maa Issue Log Analysis
MaaAssistantArknights/MaaAssistantArknights
分析 MaaAssistantArknights 上游仓库公开 Issue（https://github.com/MaaAssistantArknights/MaaAssistantArknights/issues/...
Pallas Style Reply
MaaAssistantArknights/MaaAssistantArknights
以《明日方舟》帕拉斯的人设与语气生成强角色扮演式回复。用于用户明确要求“帕拉斯风格”“帕拉斯口吻”“像帕拉斯一样说话”“Pallas roleplay”时，输出带有米诺斯祭司、英雄叙事、荣誉与信念色彩的中文回复，同时保持内容可理解、可执行。
Readme Shot Demo
MaaAssistantArknights/MaaAssistantArknights
用 MAA GUI 内置演示模式（tools/ReadmeShotDemo）重新生成仓库 README 界面截图。用户提到更新/换 README 截图、README 里的画面过期、UI 大改后要更新 README 展示图、跑 ReadmeShotDemo 或 demo 截图时使用，即使用户没有明确说出 ｢ReadmeShotDemo｣ 一词。
Side Story Navigation
MaaAssistantArknights/MaaAssistantArknights
新增/更新 SideStory（别传）活动关卡导航。涵盖 tasks/Stages 导航任务、StageActivityV2.json 活动配置、MaaRelease 仓库同步三个文件的联动修改。用户要求添加新活动导航、更新活动关卡、活动开放或复刻时调整导航，以及提到同步 MaaRelease 时均应使用本 skill。
Related
Categories
Questions about Core Image Eval
What does Core Image Eval do?
用 MaaCore 本体对本地图片（用户日志反馈包截图、自己截的图）离线验证识别结果：pipeline 任务为什么没命中、模板匹配得分多少、OCR 认出了什么、物品模板匹配情况。用户提到 ｢验证识别｣｢为什么没识别/没命中｣｢模板分数/得分｣｢OCR 结果对不对｣｢排查反馈包截图｣或给了截图要复现 core 行为时使用。与外部脚本（python 直调 ppocr/OpenCV）的区别：本工具走…. Core Image Eval is an agent skill from MaaAssistantArknights/MaaAssistantArknights.
When should I use Core Image Eval?
Core Image Eval fits situations like: development work in your project.
How do I install Core Image Eval in Claude Code?
Run `npx skills add MaaAssistantArknights/MaaAssistantArknights --skill core-image-eval -a claude-code`. Or copy the skill folder (.agents/skills/core-image-eval in MaaAssistantArknights/MaaAssistantArknights) into .claude/skills/core-image-eval in your project. Claude Code loads it when a task matches its description.
How do I install Core Image Eval in Codex?
Run `npx skills add MaaAssistantArknights/MaaAssistantArknights --skill core-image-eval -a codex`. Or copy the skill folder (.agents/skills/core-image-eval in MaaAssistantArknights/MaaAssistantArknights) into .agents/skills/core-image-eval in your project. Codex loads it when a task matches its description.
Can I use Core Image Eval in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MaaAssistantArknights/MaaAssistantArknights --skill core-image-eval -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/core-image-eval, .gemini/skills/core-image-eval, .github/skills/core-image-eval and .opencode/skills/core-image-eval in your project.
What does Core Image Eval need to run?
Going by SKILL.md and its folder, Core Image Eval needs the command-line tools its instructions call (python, cmake and pip). Our summary lists: Python 3.
Does Core Image Eval access the network?
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Core Image Eval safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Core Image Eval use?
Core Image Eval is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Core Image Eval use?
About 899 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Core Image Eval?
Skills that share tags, products or a category with Core Image Eval: Image Visual Check (jjjkkkjjj/Matft, 147 stars), Torch Performance Optimization (albumentations-team/albucore, 123 stars), Srt Whiteboard Animation (geeklee/srt-whiteboard-animation, 4.1k stars) and ComfyUI Custom Node Builder (ConstantineB6/comfy-pilot, 230 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Core Image Eval?
MaaAssistantArknights (a GitHub organization) maintains it in MaaAssistantArknights/MaaAssistantArknights, which has 23,606 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 7, 2026.
Source: MaaAssistantArknights/MaaAssistantArknights on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.