← Back to Skills Marketplace
ClawList — AI-Powered Task Management for OpenClaw
by
tenlifejosh
· GitHub ↗
· v1.0.0
· MIT-0
114
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install clawlist-tlc
Description
Manage tasks with natural language commands to add, list, complete, prioritize, categorize, and get briefings using a JSON-based CLI tool.
README (SKILL.md)
ClawList Skill
Trigger phrases: task management, to-do list, my list, add task, mark done, focus today, what should I work on, clawlist, what's on my list, show my tasks, finished this week
What This Skill Does
ClawList is a persistent, intelligent task management system for OpenClaw. It reads and writes a JSON task file and provides natural language task management with a beautiful CLI interface.
Data file: /Users/oliverhutchins1/.openclaw/workspace-main/clawlist/tasks.json
Script: /Users/oliverhutchins1/.openclaw/workspace-main/clawlist/clawlist.py
Natural Language Routing
When the user says something matching these patterns, translate to the appropriate command and run it using exec:
"Add [X] to my list"
→ Extract the task title, and any mentioned category/priority
cd /Users/oliverhutchins1/.openclaw/workspace-main/clawlist
python3 clawlist.py add "Task title" --category \x3Ccategory> --priority \x3Cpriority>
- If no category mentioned → default:
personal - If no priority mentioned → default:
normal - If urgency implied ("ASAP", "urgent", "today") →
--priority urgent - Categories:
personal | business | product | ops | social
"What's on my list?" / "Show my tasks"
cd /Users/oliverhutchins1/.openclaw/workspace-main/clawlist
python3 clawlist.py list
"Mark [X] done" / "I finished [X]" / "Complete [X]"
→ Extract the task reference (partial title or ID)
cd /Users/oliverhutchins1/.openclaw/workspace-main/clawlist
python3 clawlist.py done "partial title or id"
"What should I focus on today?" / "Today's priorities"
cd /Users/oliverhutchins1/.openclaw/workspace-main/clawlist
python3 clawlist.py list --today
"Show me product tasks" / "What's in [category]?"
→ Map to the closest category: personal | business | product | ops | social
cd /Users/oliverhutchins1/.openclaw/workspace-main/clawlist
python3 clawlist.py list --category product
"Morning briefing" / "What's my brief?" / "ClawList brief"
cd /Users/oliverhutchins1/.openclaw/workspace-main/clawlist
python3 clawlist.py brief
"Show me what I finished this week" / "My stats" / "Progress report"
cd /Users/oliverhutchins1/.openclaw/workspace-main/clawlist
python3 clawlist.py stats
"Archive done tasks" / "Clean up done"
cd /Users/oliverhutchins1/.openclaw/workspace-main/clawlist
python3 clawlist.py archive
"Start working on [X]" / "I'm working on [X]"
cd /Users/oliverhutchins1/.openclaw/workspace-main/clawlist
python3 clawlist.py start "partial title"
Agent Routing
Hutch (main session)
- Handle all real-time task requests from J
- Translate natural language → clawlist.py commands
- Show Rich output directly in the chat reply
- After
addordone, confirm with a brief 1-line acknowledgment - Don't pad the response — output from the script is the reply
Steward (daily briefing cron)
- Always include
python3 clawlist.py briefin the morning briefing - Embed the output block in the briefing message
- Run after calendar and weather, before the day's recommendations
Execution Pattern
- Parse the user's intent
- Map to the closest command
- Run via
execin the clawlist directory - Capture and display stdout as the response
- Add a brief 1-line confirmation only if the output doesn't already confirm
Always run from the clawlist directory (or use the full path) so the script finds tasks.json correctly.
Priority Mapping (natural language → CLI flag)
| User says | --priority |
|---|---|
| urgent, ASAP, critical, today, immediately | urgent |
| high, important, soon | high |
| normal, eventually, sometime | normal |
| low, someday, maybe, nice-to-have | low |
Category Mapping
| User says | --category |
|---|---|
| personal, life, self, me | personal |
| business, GND, client, revenue, sales | business |
| product, KDP, Prayful, build, ship | product |
| ops, system, setup, config, fix | ops |
| social, post, TikTok, Twitter, content | social |
Error Handling
- If
python3 clawlist.pyfails → check if Rich is installed:pip3 install rich - If tasks.json not found → the script creates a fresh one automatically
- If no match for
done→ inform J and show the list so they can pick the right one
Example Session
J: Add "Review GND proposal for Parker HVAC" to my list as business, high
→ python3 clawlist.py add "Review GND proposal for Parker HVAC" --category business --priority high
J: What's on my list?
→ python3 clawlist.py list
J: Mark the KDP task done
→ python3 clawlist.py done "KDP"
J: What should I focus on today?
→ python3 clawlist.py list --today
Usage Guidance
This skill is suspicious because it contains only instructions and no code or install steps, yet tells the agent to run a Python script and read/write a JSON file at a hard-coded user path that is not included with the skill. Before installing or enabling it: (1) verify the exact file /Users/oliverhutchins1/.openclaw/workspace-main/clawlist/clawlist.py exists and inspect its source to ensure it does only the expected task operations; (2) prefer a version of the skill that includes its code or an install step from a trusted release (GitHub release, official domain); (3) remove or adapt hard-coded user paths to your environment; (4) be aware that the agent will execute that local code (including as part of scheduled briefings), so do not enable the skill if you cannot audit the script. If you cannot locate and review the referenced files, do not install or enable this skill.
Capability Analysis
Type: OpenClaw Skill
Name: clawlist-tlc
Version: 1.0.0
The skill bundle contains hardcoded absolute paths to a specific user's home directory (/Users/oliverhutchins1/) in SKILL.md, which is highly unusual for a portable skill and suggests a targeted script or a leak of personal environment data. Additionally, the primary logic file (clawlist.py) referenced in the instructions is missing from the provided files, and the execution patterns described lack input sanitization, posing a significant risk of shell injection if the agent processes malicious user input into the 'exec' commands.
Capability Assessment
Purpose & Capability
Name/description (task management) aligns with the actions in SKILL.md (run a local Python CLI that reads/writes a JSON task file). However the skill bundle contains no code or install steps yet the instructions expect a local script (/Users/oliverhutchins1/.openclaw/.../clawlist.py) and data file. That mismatch (instruction-only but dependent on an external, absent script) is inconsistent and unusual.
Instruction Scope
Instructions tell the agent to cd into a specific user's home path and run python3 on a local script via exec, capturing stdout and returning it to the user. While this is coherent for a local CLI-based task manager, it also means the agent will execute whatever code exists at that path — potentially arbitrary — and the SKILL.md gives the agent discretion to run these commands for scheduled briefings. The instructions do not include safeguards or checks on the script's content.
Install Mechanism
No install spec (instruction-only) — lower installer risk in itself. But because the skill references an external script that is not included or installed, the skill assumes the environment already contains unverified code. The lack of an included/official install or source increases the chance of misconfiguration or hidden behavior.
Credentials
The skill requests no credentials or env vars (appropriate). However it hard-codes an absolute path containing a specific username (/Users/oliverhutchins1/...), which is not generic and suggests the skill was packaged for a particular user or environment. That hard-coded path is disproportionate to a generic task manager skill and could cause the agent to access that user's files if present.
Persistence & Privilege
always is false (normal). The SKILL.md instructs a daily briefing agent ('Steward') to always run the brief command, meaning recurring execution of the local script. Autonomous invocation plus scheduled use increases the impact if the local script is malicious, but the skill does not request additional system-wide privileges or modify other skills.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install clawlist-tlc - After installation, invoke the skill by name or use
/clawlist-tlc - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
World-class persistent to-do system. Natural language task management, morning briefing integration, priority scoring, completion tracking, and beautiful Rich CLI output.
Metadata
Frequently Asked Questions
What is ClawList — AI-Powered Task Management for OpenClaw?
Manage tasks with natural language commands to add, list, complete, prioritize, categorize, and get briefings using a JSON-based CLI tool. It is an AI Agent Skill for Claude Code / OpenClaw, with 114 downloads so far.
How do I install ClawList — AI-Powered Task Management for OpenClaw?
Run "/install clawlist-tlc" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is ClawList — AI-Powered Task Management for OpenClaw free?
Yes, ClawList — AI-Powered Task Management for OpenClaw is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does ClawList — AI-Powered Task Management for OpenClaw support?
ClawList — AI-Powered Task Management for OpenClaw is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created ClawList — AI-Powered Task Management for OpenClaw?
It is built and maintained by tenlifejosh (@tenlifejosh); the current version is v1.0.0.
More Skills