Octopus Research
nyldn/claude-octopus
Thorough research across multiple sources — use for complex topics needing broad synthesis
Nudge the user with time-based reminders (stopping times, meetings, break suggestions).
Install Nudge
$ npx skills add ravila4/claude-adhd-skills --skill nudge -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ravila4/claude-adhd-skills nudge --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/ravila4/claude-adhd-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/nudge .claude/skills/nudge && 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 "nudge" agent skill from https://github.com/ravila4/claude-adhd-skills/tree/main/skills/nudge into .claude/skills/nudge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nudge", 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/ravila4/claude-adhd-skills/tree/main/skills/nudgeType 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 ravila4/claude-adhd-skills --skill nudge -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ravila4/claude-adhd-skills nudge --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ravila4/claude-adhd-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/nudge .agents/skills/nudge && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "nudge" agent skill from https://github.com/ravila4/claude-adhd-skills/tree/main/skills/nudge into .agents/skills/nudge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nudge", 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 ravila4/claude-adhd-skills --skill nudge -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ravila4/claude-adhd-skills nudge --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ravila4/claude-adhd-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/nudge .cursor/skills/nudge && 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 "nudge" agent skill from https://github.com/ravila4/claude-adhd-skills/tree/main/skills/nudge into .cursor/skills/nudge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nudge", 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/ravila4/claude-adhd-skills.git --path skills/nudge--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 ravila4/claude-adhd-skills --skill nudge -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ravila4/claude-adhd-skills nudge --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ravila4/claude-adhd-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/nudge .gemini/skills/nudge && 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 "nudge" agent skill from https://github.com/ravila4/claude-adhd-skills/tree/main/skills/nudge into .gemini/skills/nudge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nudge", 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 ravila4/claude-adhd-skills nudgeInstalls 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 ravila4/claude-adhd-skills --skill nudge -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ravila4/claude-adhd-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/nudge .github/skills/nudge && 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 "nudge" agent skill from https://github.com/ravila4/claude-adhd-skills/tree/main/skills/nudge into .github/skills/nudge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nudge", 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 ravila4/claude-adhd-skills --skill nudge -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ravila4/claude-adhd-skills nudge --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ravila4/claude-adhd-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/nudge .opencode/skills/nudge && 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 "nudge" agent skill from https://github.com/ravila4/claude-adhd-skills/tree/main/skills/nudge into .opencode/skills/nudge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nudge", 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
nudge- GitHub stars
- 157
- Token cost
- ~680 tokens
- SKILL.md length
- 254 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Nudge the user with time-based reminders (stopping times, meetings, break suggestions).
- Works in 2 steps: Reason - Why this nudge was set → Action - What to do when it fires
- Productivity & Automation work in your project
- SKILL.md covers When to Use, Tools, Message Format and When Nudges Fire, plus 1 more section
- Calls python3 and sqlite3
What it does
Nudge is an agent skill from ravila4/claude-adhd-skills. Nudge the user with time-based reminders (stopping times, meetings, break suggestions). Surfaces via hook on prompt submission -- requires human interaction to fire. NOT for process monitoring or job polling -- use sleep in Bash instead.
Its SKILL.md is about 680 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 Productivity & Automation. It works with Bash. The repository describes itself as: Claude Code skills and hooks for staying organized with AI agents. The licence is MIT.
When your agent uses it
- Productivity & Automation work in your project
Example prompts
- “/nudge”
Requirements
- Python 3
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- Reason - Why this nudge was set
- Action - What to do when it fires
What it can do on your machine
Read from SKILL.md and the folder at commit f99e0a3. 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:
python3sqlite3
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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Nudge loads about 680 tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 254 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 ravila4/claude-adhd-skills at commit f99e0a3, republished under its MIT licence (© ravila4). 254 words, ~680 tokens.
Download SKILL.mdSave it as
.claude/skills/nudge/SKILL.md (or your agent's skills folder).- name
- nudge
- description
- Nudge the user with time-based reminders (stopping times, meetings, break suggestions). Surfaces via hook on prompt submission -- requires human interaction to fire. NOT for process monitoring or job polling -- use `sleep` in Bash instead.
Nudge
Human-facing reminder system for managing focus and pacing. Nudges are stored in SQLite and surface via hook when due.
When to Use
Proactively set nudges when:
- User mentions a stopping time ("stop me at 11", "I need to wrap up by 5")
- User mentions a deadline or meeting ("standup in 30 minutes")
- A long focus session (2+ hours) is underway without breaks
- User asks for a reminder explicitly
Do NOT use nudge for:
- Tasks Claude will complete in the current turn
- Information that should go in memory instead
- Process monitoring (e.g., "check if the build finished", "see if the pipeline completed"). Nudges require user input (prompt submission) to fire, so they cannot check on running processes. Use
sleep <seconds>in Bash instead -- it blocks inline and resumes without requiring user interaction.
Tools
Scripts are located at hooks/:
Adding a Nudge
python3 hooks/add_alert.py "<time>" "<message>"Time formats:
HH:MM- Today at that time (e.g.,23:00)YYYY-MM-DD HH:MM- Specific datetime+30m- 30 minutes from now+2h- 2 hours from now
Acknowledging a Nudge
When a nudge has been addressed, dismiss it:
python3 hooks/ack_alert.py <id>Viewing Nudges
sqlite3 hooks/alerts.db "SELECT id, due_at, message FROM alerts WHERE acknowledged = 0"Message Format
Messages are notes-to-self for Claude. Include:
- Reason - Why this nudge was set
- Action - What to do when it fires
Format: reason - action to take
Examples
User asked to stop at 11 PM - wrap up current work and suggest break
User mentioned standup in 30m - remind to prep notes
2 hours on debugging session - check if stuck, suggest break
Deployment window opens at 14:00 - remind user to run deploy scriptWhen Nudges Fire
Due nudges appear in the system-reminder on each prompt submission. When a nudge fires:
- Read the message to understand context and action
- Take the specified action (remind user, suggest break, etc.)
- Acknowledge the nudge so it doesn't repeat
Database Schema
CREATE TABLE alerts (
id INTEGER PRIMARY KEY AUTOINCREMENT,
due_at TEXT NOT NULL, -- "YYYY-MM-DD HH:MM"
message TEXT NOT NULL, -- reason - action
created_at TEXT DEFAULT CURRENT_TIMESTAMP,
acknowledged INTEGER DEFAULT 0 -- 0=pending, 1=done
)Location: hooks/alerts.db
© ravila4, MIT. 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 skills/nudge of ravila4/claude-adhd-skills.
Open the folder on GitHubat commit f99e0a3
Compare with similar skills
Nudge 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 |
|---|---|---|---|---|---|---|
| Nudge this skillravila4/claude-adhd-skills | 157 | — | ~680 | Automated safety check: Pass | MIT | |
| Octopus Researchnyldn/claude-octopus | 4.2k | 1 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Cua Driverdavidondrej/skills | 4.1k | — | ~821 | Automated safety check: Pass | MIT | |
| Textmemajiayu000/claude-skill-registry | 666 | 2 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Lark Basemajiayu000/claude-skill-registry | 666 | 1 repos | ~3.9k | Automated safety check: Pass | MIT | |
| Lark Calendarmajiayu000/claude-skill-registry | 666 | 1 repos | ~2.8k | Automated safety check: Pass | MIT |
Similar skills
Cua Driver
davidondrej/skills
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling…
Textme
majiayu000/claude-skill-registry
Text Claude from your phone — set up the njerschow/textme daemon so inbound iMessages drive a Claude Code session on your laptop, with voice notes, image input, code execution, and a phone-number…
Lark Base
majiayu000/claude-skill-registry
飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走…
Lark Calendar
majiayu000/claude-skill-registry
飞书日历：管理日历日程和会议室。查看/搜索日程、创建/更新日程、管理参会人、查询忙闲和推荐时段、预定会议室。当用户需要查看日程安排、创建/修改会议、查询/预定会议室时使用。不负责：查询过去的视频会议记录（走 lark-meeting）、待办任务（走 lark-task）。
Remind Me
majiayu000/claude-skill-registry
Set reminders using natural language. An agent skill from majiayu000/claude-skill-registry.
More from ravila4/claude-adhd-skills
Daily Journal
ravila4/claude-adhd-skills
Draft, organize, or update development journal entries. An agent skill from ravila4/claude-adhd-skills.
Obsidian Vault
ravila4/claude-adhd-skills
Manage Obsidian vault operations. An agent skill from ravila4/claude-adhd-skills.
Test Driven Development
ravila4/claude-adhd-skills
(TDD) Use when implementing any feature or bugfix. An agent skill from ravila4/claude-adhd-skills.
Related
Works with
Categories
Questions about Nudge
What does Nudge do?
Nudge the user with time-based reminders (stopping times, meetings, break suggestions). Nudge is an agent skill from ravila4/claude-adhd-skills. Nudge the user with time-based reminders (stopping times, meetings, break suggestions).
When should I use Nudge?
Nudge fits situations like: productivity & Automation work in your project.
How do I install Nudge in Claude Code?
Run `npx skills add ravila4/claude-adhd-skills --skill nudge -a claude-code`. Or copy the skill folder (skills/nudge in ravila4/claude-adhd-skills) into .claude/skills/nudge in your project. Claude Code loads it when a task matches its description.
How do I install Nudge in Codex?
Run `npx skills add ravila4/claude-adhd-skills --skill nudge -a codex`. Or copy the skill folder (skills/nudge in ravila4/claude-adhd-skills) into .agents/skills/nudge in your project. Codex loads it when a task matches its description.
Can I use Nudge 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 ravila4/claude-adhd-skills --skill nudge -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nudge, .gemini/skills/nudge, .github/skills/nudge and .opencode/skills/nudge in your project.
What does Nudge need to run?
Going by SKILL.md and its folder, Nudge needs the command-line tools its instructions call (python3 and sqlite3). Our summary lists: Python 3.
Does Nudge 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 Nudge 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 Nudge use?
Nudge is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Nudge use?
About 680 tokens (SKILL.md is roughly 2.7k 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 Nudge?
Skills that share tags, products or a category with Nudge: Octopus Research (nyldn/claude-octopus, 4.2k stars), Cua Driver (davidondrej/skills, 4.1k stars), Textme (majiayu000/claude-skill-registry, 666 stars) and Lark Base (majiayu000/claude-skill-registry, 666 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Nudge?
ravila4 (a GitHub user) maintains it in ravila4/claude-adhd-skills, which has 157 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on March 1, 2026.
Source: ravila4/claude-adhd-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.