Screenshot
nexu-io/open-design
Capture desktop, app windows, or pixel regions across OS platforms.
スクリーンショットに赤枠・矢印・吹き出し等の注釈を自動追加するスキル. An agent skill from minicoohei/ai-agent-camp.
No licenceAuto-check passed
Install Screenshot Annotator
$ npx skills add minicoohei/ai-agent-camp --skill screenshot-annotator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install minicoohei/ai-agent-camp screenshot-annotator --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/minicoohei/ai-agent-camp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/screenshot-annotator .claude/skills/screenshot-annotator && 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 "screenshot-annotator" agent skill from https://github.com/minicoohei/ai-agent-camp/tree/main/skills/screenshot-annotator into .claude/skills/screenshot-annotator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "screenshot-annotator", 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/minicoohei/ai-agent-camp/tree/main/skills/screenshot-annotatorType 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 minicoohei/ai-agent-camp --skill screenshot-annotator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install minicoohei/ai-agent-camp screenshot-annotator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/minicoohei/ai-agent-camp.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/screenshot-annotator .agents/skills/screenshot-annotator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "screenshot-annotator" agent skill from https://github.com/minicoohei/ai-agent-camp/tree/main/skills/screenshot-annotator into .agents/skills/screenshot-annotator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "screenshot-annotator", 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 minicoohei/ai-agent-camp --skill screenshot-annotator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install minicoohei/ai-agent-camp screenshot-annotator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/minicoohei/ai-agent-camp.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/screenshot-annotator .cursor/skills/screenshot-annotator && 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 "screenshot-annotator" agent skill from https://github.com/minicoohei/ai-agent-camp/tree/main/skills/screenshot-annotator into .cursor/skills/screenshot-annotator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "screenshot-annotator", 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/minicoohei/ai-agent-camp.git --path skills/screenshot-annotator--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 minicoohei/ai-agent-camp --skill screenshot-annotator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install minicoohei/ai-agent-camp screenshot-annotator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/minicoohei/ai-agent-camp.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/screenshot-annotator .gemini/skills/screenshot-annotator && 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 "screenshot-annotator" agent skill from https://github.com/minicoohei/ai-agent-camp/tree/main/skills/screenshot-annotator into .gemini/skills/screenshot-annotator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "screenshot-annotator", 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 minicoohei/ai-agent-camp screenshot-annotatorInstalls 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 minicoohei/ai-agent-camp --skill screenshot-annotator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/minicoohei/ai-agent-camp.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/screenshot-annotator .github/skills/screenshot-annotator && 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 "screenshot-annotator" agent skill from https://github.com/minicoohei/ai-agent-camp/tree/main/skills/screenshot-annotator into .github/skills/screenshot-annotator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "screenshot-annotator", 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 minicoohei/ai-agent-camp --skill screenshot-annotator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install minicoohei/ai-agent-camp screenshot-annotator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/minicoohei/ai-agent-camp.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/screenshot-annotator .opencode/skills/screenshot-annotator && 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 "screenshot-annotator" agent skill from https://github.com/minicoohei/ai-agent-camp/tree/main/skills/screenshot-annotator into .opencode/skills/screenshot-annotator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "screenshot-annotator", 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
screenshot-annotator- GitHub stars
- 347
- Token cost
- ~550 tokens
- SKILL.md length
- 149 words
- Files
- 5 (incl. scripts)
- Skills in repo
- 37
- Repo updated
- First seen
- Licence
- None found
At a glance
スクリーンショットに赤枠・矢印・吹き出し等の注釈を自動追加するスキル. An agent skill from minicoohei/ai-agent-camp.
- Works in 3 steps: Analyze the screenshot to identify the… → Generate annotation overlay using Gemini… → Output annotated image as a separate file
- SKILL.md covers Workflow, Usage, Parameters and Styles, plus 5 more sections
- Runs Python scripts from its folder; calls python; needs GEMINI_API_KEY and GOOGLE_API_KEY
What it does
Screenshot Annotator is an agent skill from minicoohei/ai-agent-camp. スクリーンショットに赤枠・矢印・吹き出し等の注釈を自動追加するスキル。 「スクショに注釈を付けて」「画面に矢印を追加」「マニュアル用の注釈」等のリクエストで発動。
Its SKILL.md is about 550 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts (for example `SKILL.en.md`, `SKILL.es.md` and `agents/openai.yaml`).
The repository describes itself as: AI Agent Camp — non-engineer-friendly AI agent training curriculum. Lessons, skills, commands, and hooks for Claude Code, Cursor, and Codex.
Example prompts
- “/screenshot-annotator”
Requirements
- Python 3
- A credential in GEMINI_API_KEY
- A credential in GOOGLE_API_KEY
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Analyze the screenshot to identify the target element
- Generate annotation overlay using Gemini Vision API
- Output annotated image as a separate file
What it can do on your machine
Read from SKILL.md and the folder at commit 048ba4c. 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
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
GEMINI_API_KEYGOOGLE_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Screenshot Annotator loads about 550 tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 149 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); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 149 words (~550 tokens).
“Add annotations to screenshots without modifying the original image. Annotations are overlaid on top.”
- name
- screenshot-annotator
- triggers
- スクショに注釈を付けて, 画面に矢印を追加, マニュアル用の注釈, 赤枠を付けて, 吹き出しを追加, screenshot-annotator, annotate screenshot
Files
SKILL.md and 4 other files (scripts) in skills/screenshot-annotator of minicoohei/ai-agent-camp.
- SKILL.md
- SKILL.en.md
- SKILL.es.md
- agents/openai.yaml
- scripts/annotate.py
Open the folder on GitHubat commit 048ba4c
Compare with similar skills
Screenshot Annotator 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 |
|---|---|---|---|---|---|---|
| Screenshot Annotator this skillminicoohei/ai-agent-camp | 347 | — | ~550 | Automated safety check: Pass | None | |
| Screenshotnexu-io/open-design | 100k | — | ~291 | Automated safety check: Pass | Apache-2.0 | |
| Wireframe Annotatednexu-io/open-design | 100k | — | ~960 | Automated safety check: Pass | Apache-2.0 | |
| Tabler Screenshot Makertabler/tabler | 42k | — | ~1.3k | Automated safety check: Pass | MIT | |
| PR Screenshotsgithub/awesome-copilot | 40k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Image Annotationsgithub/awesome-copilot | 40k | — | ~6k | Automated safety check: Pass | MIT |
Similar skills
Wireframe Annotated
nexu-io/open-design
An annotated / redline lo-fi wireframe — a desktop landing/marketing page drawn as flat greyboxes inside a browser chrome frame, overlaid with numbered annotation pins (①②③④⑤) in a single accent…
Tabler Screenshot Maker
tabler/tabler
Makes reproducible screenshots of Tabler components and screens for release notes, the website and social posts, using the repository's screenshots app.
- Official
PR Screenshots
github/awesome-copilot
Embed before/after screenshots and annotated images in pull request descriptions.
- Official
Image Annotations
github/awesome-copilot
Annotate screenshots, diagrams, and images with callout rectangles, arrows, labels, and color-coded highlights using PIL.
Screenshots Marketing
nexu-io/open-design
Generate marketing screenshots with Playwright. An agent skill from nexu-io/open-design.
More from minicoohei/ai-agent-camp
All 37 skills in this repoExploratory Data Analysis
minicoohei/ai-agent-camp
200以上のファイル形式に対応した探索的データ分析（EDA）スキル. An agent skill from minicoohei/ai-agent-camp.
Content Optimizer
minicoohei/ai-agent-camp
コンテンツのA/Bテスト・自己改善ループを支援するプランナースキル. An agent skill from minicoohei/ai-agent-camp.
Video Editor
minicoohei/ai-agent-camp
TikTok/YouTube向け動画編集スキル。ffmpegでキャプション焼き込み、 Ken Burnsエフェクト、シーン結合、音声合成を行う。
Article Writer
minicoohei/ai-agent-camp
テーマからアウトライン生成→文体プロファイル適用→Markdown記事出力を行う記事執筆スキル. An agent skill from minicoohei/ai-agent-camp.
Banner Creator
minicoohei/ai-agent-camp
各種SNS・広告プラットフォーム向けのバナー/クリエイティブを生成するスキル. An agent skill from minicoohei/ai-agent-camp.
Check Inbox
minicoohei/ai-agent-camp
メールとSlackから返信すべき項目・タスクを抽出する統合型スキル. An agent skill from minicoohei/ai-agent-camp.
Questions about Screenshot Annotator
What does Screenshot Annotator do?
スクリーンショットに赤枠・矢印・吹き出し等の注釈を自動追加するスキル. An agent skill from minicoohei/ai-agent-camp. Screenshot Annotator is an agent skill from minicoohei/ai-agent-camp.
How do I install Screenshot Annotator in Claude Code?
Run `npx skills add minicoohei/ai-agent-camp --skill screenshot-annotator -a claude-code`. Or copy the skill folder (skills/screenshot-annotator in minicoohei/ai-agent-camp) into .claude/skills/screenshot-annotator in your project. Claude Code loads it when a task matches its description.
How do I install Screenshot Annotator in Codex?
Run `npx skills add minicoohei/ai-agent-camp --skill screenshot-annotator -a codex`. Or copy the skill folder (skills/screenshot-annotator in minicoohei/ai-agent-camp) into .agents/skills/screenshot-annotator in your project. Codex loads it when a task matches its description.
Can I use Screenshot Annotator 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 minicoohei/ai-agent-camp --skill screenshot-annotator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/screenshot-annotator, .gemini/skills/screenshot-annotator, .github/skills/screenshot-annotator and .opencode/skills/screenshot-annotator in your project.
What does Screenshot Annotator need to run?
Going by SKILL.md and its folder, Screenshot Annotator needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named GEMINI_API_KEY and GOOGLE_API_KEY. Our summary lists: Python 3; A credential in GEMINI_API_KEY; A credential in GOOGLE_API_KEY.
Does Screenshot Annotator access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Screenshot Annotator 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Screenshot Annotator use?
No licence was found for Screenshot Annotator or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Screenshot Annotator use?
About 550 tokens (SKILL.md is roughly 2.2k 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 Screenshot Annotator?
Skills that share tags, products or a category with Screenshot Annotator: Screenshot (nexu-io/open-design, 100k stars), Wireframe Annotated (nexu-io/open-design, 100k stars), Tabler Screenshot Maker (tabler/tabler, 42k stars) and PR Screenshots (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Screenshot Annotator?
minicoohei (a GitHub user) maintains it in minicoohei/ai-agent-camp, which has 347 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 7, 2026.
Source: minicoohei/ai-agent-camp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.