cli-jaw 0.1.6 → 0.1.8

package/skills_ref/apple-reminders/SKILL.md

@@ -1,118 +0,0 @@
----
-name: apple-reminders
-description: Manage Apple Reminders via remindctl CLI (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.
-homepage: https://github.com/steipete/remindctl
-metadata:
-  {
-    "openclaw":
-      {
-        "emoji": "⏰",
-        "os": ["darwin"],
-        "requires": { "bins": ["remindctl"] },
-        "install":
-          [
-            {
-              "id": "brew",
-              "kind": "brew",
-              "formula": "steipete/tap/remindctl",
-              "bins": ["remindctl"],
-              "label": "Install remindctl via Homebrew",
-            },
-          ],
-      },
-  }
----
-
-# Apple Reminders CLI (remindctl)
-
-Use `remindctl` to manage Apple Reminders directly from the terminal.
-
-## When to Use
-
-✅ **USE this skill when:**
-
-- User explicitly mentions "reminder" or "Reminders app"
-- Creating personal to-dos with due dates that sync to iOS
-- Managing Apple Reminders lists
-- User wants tasks to appear in their iPhone/iPad Reminders app
-
-## When NOT to Use
-
-❌ **DON'T use this skill when:**
-
-- Scheduling Clawdbot tasks or alerts → use `cron` tool with systemEvent instead
-- Calendar events or appointments → use Apple Calendar
-- Project/work task management → use Notion, GitHub Issues, or task queue
-- One-time notifications → use `cron` tool for timed alerts
-- User says "remind me" but means a Clawdbot alert → clarify first
-
-## Setup
-
-- Install: `brew install steipete/tap/remindctl`
-- macOS-only; grant Reminders permission when prompted
-- Check status: `remindctl status`
-- Request access: `remindctl authorize`
-
-## Common Commands
-
-### View Reminders
-
-```bash
-remindctl                    # Today's reminders
-remindctl today              # Today
-remindctl tomorrow           # Tomorrow
-remindctl week               # This week
-remindctl overdue            # Past due
-remindctl all                # Everything
-remindctl 2026-01-04         # Specific date
-```
-
-### Manage Lists
-
-```bash
-remindctl list               # List all lists
-remindctl list Work          # Show specific list
-remindctl list Projects --create    # Create list
-remindctl list Work --delete        # Delete list
-```
-
-### Create Reminders
-
-```bash
-remindctl add "Buy milk"
-remindctl add --title "Call mom" --list Personal --due tomorrow
-remindctl add --title "Meeting prep" --due "2026-02-15 09:00"
-```
-
-### Complete/Delete
-
-```bash
-remindctl complete 1 2 3     # Complete by ID
-remindctl delete 4A83 --force  # Delete by ID
-```
-
-### Output Formats
-
-```bash
-remindctl today --json       # JSON for scripting
-remindctl today --plain      # TSV format
-remindctl today --quiet      # Counts only
-```
-
-## Date Formats
-
-Accepted by `--due` and date filters:
-
-- `today`, `tomorrow`, `yesterday`
-- `YYYY-MM-DD`
-- `YYYY-MM-DD HH:mm`
-- ISO 8601 (`2026-01-04T12:34:56Z`)
-
-## Example: Clarifying User Intent
-
-User: "Remind me to check on the deploy in 2 hours"
-
-**Ask:** "Do you want this in Apple Reminders (syncs to your phone) or as a Clawdbot alert (I'll message you here)?"
-
-- Apple Reminders → use this skill
-- Clawdbot alert → use `cron` tool with systemEvent

package/skills_ref/atlas/SKILL.md

@@ -1,99 +0,0 @@
----
-name: "atlas"
-description: "macOS-only AppleScript control for the ChatGPT Atlas desktop app. Use only when the user explicitly asks to control Atlas tabs/bookmarks/history on macOS and the \"ChatGPT Atlas\" app is installed; do not trigger for general browser tasks or non-macOS environments."
----
-
-
-# Atlas Control (macOS)
-
-Use the bundled CLI to control Atlas and inspect local browser data.
-
-## Quick Start
-
-Set a stable path to the CLI:
-
-```bash
-export CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"
-export ATLAS_CLI="$CODEX_HOME/skills/atlas/scripts/atlas_cli.py"
-```
-
-User-scoped skills install under `$CODEX_HOME/skills` (default: `~/.codex/skills`).
-
-Then run:
-
-```bash
-uv run --python 3.12 python "$ATLAS_CLI" app-name
-uv run --python 3.12 python "$ATLAS_CLI" tabs --json
-```
-
-The CLI requires the Atlas app bundle in `/Applications` or `~/Applications`:
-
-- `ChatGPT Atlas`
-
-If AppleScript fails with a permissions error, grant Automation permission in System Settings > Privacy & Security > Automation, allowing your terminal to control ChatGPT Atlas.
-
-## Tabs Workflow
-
-1. List tabs to get `window_id` and `tab_index`:
-
-```bash
-uv run --python 3.12 python "$ATLAS_CLI" tabs
-```
-
-2. Focus a tab using the `window_id` and `tab_index` from the listing:
-
-```bash
-uv run --python 3.12 python "$ATLAS_CLI" focus-tab <window_id> <tab_index>
-```
-
-3. Open a new tab:
-
-```bash
-uv run --python 3.12 python "$ATLAS_CLI" open-tab "https://chatgpt.com/"
-```
-
-Optional maintenance commands:
-
-```bash
-uv run --python 3.12 python "$ATLAS_CLI" reload-tab <window_id> <tab_index>
-uv run --python 3.12 python "$ATLAS_CLI" close-tab <window_id> <tab_index>
-```
-
-## Bookmarks and History
-
-Atlas stores Chromium-style profile data under `~/Library/Application Support/com.openai.atlas/browser-data/host/`.
-
-List bookmarks:
-
-```bash
-uv run --python 3.12 python "$ATLAS_CLI" bookmarks --limit 100
-```
-
-Search bookmarks:
-
-```bash
-uv run --python 3.12 python "$ATLAS_CLI" bookmarks --search "docs"
-```
-
-Search history:
-
-```bash
-uv run --python 3.12 python "$ATLAS_CLI" history --search "openai docs" --limit 50
-```
-
-History for today (local time):
-
-```bash
-uv run --python 3.12 python "$ATLAS_CLI" history --today --limit 200 --json
-```
-
-The history command copies the SQLite database to a temporary location to avoid lock errors.
-
-If history looks stale or empty, ask the user which Atlas install they are using, then check both Atlas data roots and inspect the one with the most recent `History` file:
-
-- `~/Library/Application Support/com.openai.atlas/browser-data/host/`
-- `~/Library/Application Support/com.openai.atlas.beta/browser-data/host/`
-
-## References
-
-Read `references/atlas-data.md` in the skill folder (for example, `$CODEX_HOME/skills/atlas/references/atlas-data.md`) when adjusting data paths or timestamps.

package/skills_ref/brainstorming/SKILL.md

@@ -1,96 +0,0 @@
----
-name: brainstorming
-description: "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation."
----
-
-# Brainstorming Ideas Into Designs
-
-## Overview
-
-Help turn ideas into fully formed designs and specs through natural collaborative dialogue.
-
-Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval.
-
-<HARD-GATE>
-Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it. This applies to EVERY project regardless of perceived simplicity.
-</HARD-GATE>
-
-## Anti-Pattern: "This Is Too Simple To Need A Design"
-
-Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval.
-
-## Checklist
-
-You MUST create a task for each of these items and complete them in order:
-
-1. **Explore project context** — check files, docs, recent commits
-2. **Ask clarifying questions** — one at a time, understand purpose/constraints/success criteria
-3. **Propose 2-3 approaches** — with trade-offs and your recommendation
-4. **Present design** — in sections scaled to their complexity, get user approval after each section
-5. **Write design doc** — save to `docs/plans/YYYY-MM-DD-<topic>-design.md` and commit
-6. **Transition to implementation** — invoke writing-plans skill to create implementation plan
-
-## Process Flow
-
-```dot
-digraph brainstorming {
-    "Explore project context" [shape=box];
-    "Ask clarifying questions" [shape=box];
-    "Propose 2-3 approaches" [shape=box];
-    "Present design sections" [shape=box];
-    "User approves design?" [shape=diamond];
-    "Write design doc" [shape=box];
-    "Invoke writing-plans skill" [shape=doublecircle];
-
-    "Explore project context" -> "Ask clarifying questions";
-    "Ask clarifying questions" -> "Propose 2-3 approaches";
-    "Propose 2-3 approaches" -> "Present design sections";
-    "Present design sections" -> "User approves design?";
-    "User approves design?" -> "Present design sections" [label="no, revise"];
-    "User approves design?" -> "Write design doc" [label="yes"];
-    "Write design doc" -> "Invoke writing-plans skill";
-}
-```
-
-**The terminal state is invoking writing-plans.** Do NOT invoke frontend-design, mcp-builder, or any other implementation skill. The ONLY skill you invoke after brainstorming is writing-plans.
-
-## The Process
-
-**Understanding the idea:**
-- Check out the current project state first (files, docs, recent commits)
-- Ask questions one at a time to refine the idea
-- Prefer multiple choice questions when possible, but open-ended is fine too
-- Only one question per message - if a topic needs more exploration, break it into multiple questions
-- Focus on understanding: purpose, constraints, success criteria
-
-**Exploring approaches:**
-- Propose 2-3 different approaches with trade-offs
-- Present options conversationally with your recommendation and reasoning
-- Lead with your recommended option and explain why
-
-**Presenting the design:**
-- Once you believe you understand what you're building, present the design
-- Scale each section to its complexity: a few sentences if straightforward, up to 200-300 words if nuanced
-- Ask after each section whether it looks right so far
-- Cover: architecture, components, data flow, error handling, testing
-- Be ready to go back and clarify if something doesn't make sense
-
-## After the Design
-
-**Documentation:**
-- Write the validated design to `docs/plans/YYYY-MM-DD-<topic>-design.md`
-- Use elements-of-style:writing-clearly-and-concisely skill if available
-- Commit the design document to git
-
-**Implementation:**
-- Invoke the writing-plans skill to create a detailed implementation plan
-- Do NOT invoke any other skill. writing-plans is the next step.
-
-## Key Principles
-
-- **One question at a time** - Don't overwhelm with multiple questions
-- **Multiple choice preferred** - Easier to answer than open-ended when possible
-- **YAGNI ruthlessly** - Remove unnecessary features from all designs
-- **Explore alternatives** - Always propose 2-3 approaches before settling
-- **Incremental validation** - Present design, get approval before moving on
-- **Be flexible** - Go back and clarify when something doesn't make sense

package/skills_ref/browser/SKILL.md

@@ -1,179 +0,0 @@
----
-name: browser
-description: "Chrome browser control: open pages, take ref snapshots, click, type, screenshot. Requires cli-jaw server running."
-metadata:
-  {
-    "openclaw":
-      {
-        "emoji": "🌐",
-        "requires": { "bins": ["cli-jaw"], "system": ["Google Chrome"] },
-        "install":
-          [
-            {
-              "id": "brew-cliclick",
-              "kind": "brew",
-              "formula": "cliclick",
-              "bins": ["cliclick"],
-              "label": "Install cliclick (optional, for coordinate-based clicks)",
-            },
-          ],
-      },
-  }
----
-
-# Browser Control
-
-Control Chrome browser via `cli-jaw browser` commands.
-Uses ref-based snapshots to identify page elements, then click/type by ref ID.
-
-## Prerequisites
-
-- cli-jaw server must be running (`cli-jaw serve`)
-- Google Chrome must be installed
-- playwright-core must be installed (`npm i playwright-core`)
-
-## Quick Start
-
-```bash
-cli-jaw browser start                          # Start Chrome (CDP port 9240)
-cli-jaw browser navigate "https://example.com" # Go to URL
-cli-jaw browser snapshot                        # Get page structure with ref IDs
-cli-jaw browser click e3                        # Click ref e3
-cli-jaw browser type e5 "hello"                 # Type into ref e5
-cli-jaw browser screenshot                      # Save screenshot
-```
-
-## Core Workflow
-
-> **Always follow this pattern:**
-> 1. `snapshot` → See page structure + ref IDs
-> 2. `click`/`type`/`press` → Interact using ref
-> 3. `snapshot` → Verify result → Repeat
-
-## Commands
-
-### Browser Management
-
-```bash
-cli-jaw browser start [--port 9240]  # Start Chrome (default CDP port: 9240)
-cli-jaw browser stop                 # Stop Chrome
-cli-jaw browser status               # Connection status
-```
-
-### Observe
-
-```bash
-cli-jaw browser snapshot                # Ref snapshot (all elements)
-cli-jaw browser snapshot --interactive  # Interactive elements only (buttons, links, inputs)
-cli-jaw browser screenshot              # Current viewport
-cli-jaw browser screenshot --full-page  # Full page
-cli-jaw browser screenshot --ref e5     # Specific ref element only
-cli-jaw browser text                    # Page text content
-cli-jaw browser text --format html      # HTML source
-```
-
-### Snapshot Output Example
-
-```
-e1   link       "Gmail"
-e2   link       "Images"
-e3   textbox    "Search"           ← To type here: type e3 "query"
-e4   button     "Google Search"    ← To click: click e4
-e5   button     "I'm Feeling Lucky"
-```
-
-### Act
-
-```bash
-cli-jaw browser click e3              # Click element
-cli-jaw browser type e3 "hello"       # Type text
-cli-jaw browser type e3 "hello" --submit  # Type + press Enter
-cli-jaw browser press Enter           # Press key
-cli-jaw browser press Escape
-cli-jaw browser press Tab
-cli-jaw browser hover e5              # Mouse hover
-```
-
-### Navigate
-
-```bash
-cli-jaw browser navigate "https://example.com"  # Go to URL
-cli-jaw browser open "https://example.com"       # Open in new tab
-cli-jaw browser tabs                             # List tabs
-cli-jaw browser evaluate "document.title"        # Execute JS
-```
-
-## Common Workflows
-
-### Web Search
-
-```bash
-cli-jaw browser start
-cli-jaw browser navigate "https://www.google.com"
-cli-jaw browser snapshot --interactive
-# → e3 textbox "Search"
-cli-jaw browser type e3 "search query" --submit
-cli-jaw browser snapshot --interactive
-# Click desired result link
-cli-jaw browser click e7
-```
-
-### Form Filling
-
-```bash
-cli-jaw browser snapshot --interactive
-# → e1 textbox "Name", e2 textbox "Email", e3 button "Submit"
-cli-jaw browser type e1 "John Doe"
-cli-jaw browser type e2 "john@example.com"
-cli-jaw browser click e3
-cli-jaw browser snapshot  # Verify result
-```
-
-### Read Page Content
-
-```bash
-cli-jaw browser navigate "https://news.ycombinator.com"
-cli-jaw browser text | head -100  # First 100 lines
-# Or structured:
-cli-jaw browser snapshot  # Element list with roles
-```
-
-## macOS Alternatives (No Server Required)
-
-These work without cli-jaw server using native macOS tools:
-
-```bash
-# Screenshot
-screencapture -x ~/screenshot.png
-screencapture -R 0,0,1280,720 ~/region.png
-
-# Open URL
-open "https://example.com"
-open -a "Google Chrome" "https://example.com"
-
-# Current tab URL
-osascript -e 'tell app "Chrome" to URL of active tab of front window'
-
-# Tab list
-osascript -e 'tell app "Chrome" to get {title, URL} of every tab of front window'
-
-# Execute JavaScript
-osascript -e 'tell app "Chrome" to execute front window'\''s active tab javascript "document.title"'
-
-# Coordinate-based clicks (requires: brew install cliclick)
-cliclick c:500,300
-cliclick t:"text input"
-```
-
-## Notes
-
-- Ref IDs **reset on navigation**. Always re-run `snapshot` after `navigate`.
-- Use `--interactive` to show only clickable/typeable elements (shorter list).
-- Screenshots are saved to `~/.cli-jaw/screenshots/`.
-- Default CDP port is 9240 (change via `browser.cdpPort` in settings.json).
-- If Chrome is already running, `start` connects to the existing instance.
-
-## Non-DOM Elements
-
-If `snapshot` returns **no ref** for your target (Canvas, iframe, Shadow DOM, etc.),
-use the **vision-click** skill (Codex only). See `skills_ref/vision-click/SKILL.md`.