← Back to Skills Marketplace
Screenshot To Task
by
vx：17605205782
· GitHub ↗
· v1.0.0
· MIT-0
163
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install screenshot-to-task
Description
把截图里的待办或灵感整理成任务、备注和优先级。；use for screenshots, tasks, capture workflows；do not use for 伪造截图内容, 替代 OCR 系统.
Usage Guidance
This skill appears to do what it says: generate structured task drafts from screenshot text. Before running the included script, ensure you only pass the intended input (e.g., the example .md or a single text file); avoid pointing the script at large directories (like your home folder) because it can read many file types and could include sensitive content in output. No network downloads or credentials are required. If you plan to modify the spec to enable 'directory_audit' or 'pattern_audit' modes, review the code paths and limit the directories scanned to avoid accidental disclosure of secrets.
Capability Assessment
Purpose & Capability
Name/description match what is provided: an instruction-only skill plus a local Python script that produces structured task summaries from text input. Declared requirement (python3) is appropriate and no unrelated credentials or binaries are requested.
Instruction Scope
SKILL.md instructs the agent to prefer local resources (spec.json, template.md) and only run the script when shell/exec is available. The bundled script supports only the needed structured_brief mode by default (resources/spec.json sets mode to structured_brief). However the script also contains directory_audit/pattern_audit/csv_audit capabilities (it can recursively list and read many text file types), so if someone changes the spec or runs the script in other modes it can read arbitrary files from provided directories — exercise caution and only point it at intended input files.
Install Mechanism
No install spec — instruction-only model with a local Python script. Nothing is downloaded or written to non-standard locations by default.
Credentials
No environment variables or external credentials are requested. The script does not attempt network calls or require API keys.
Persistence & Privilege
always is false and the skill does not request persistent or elevated platform privileges. It does not modify other skills or global agent settings according to included files.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install screenshot-to-task - After installation, invoke the skill by name or use
/screenshot-to-task - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of screenshot-to-task skill.
- Organizes tasks, notes, and priorities from screenshot content.
- Provides workflow for reviewing and structuring tasks based on screenshot summaries and user context.
- Enforces clear boundaries: does not generate false screenshot content or replace OCR functions.
- Outputs tasks, notes, priority, required info, archiving advice, and next steps in a structured format.
- Includes explicit handling of incomplete inputs and risk/compliance warnings.
- Supports execution via python3 if environment allows, or outputs structured drafts directly.
Metadata
Frequently Asked Questions
What is Screenshot To Task?
把截图里的待办或灵感整理成任务、备注和优先级。；use for screenshots, tasks, capture workflows；do not use for 伪造截图内容, 替代 OCR 系统. It is an AI Agent Skill for Claude Code / OpenClaw, with 163 downloads so far.
How do I install Screenshot To Task?
Run "/install screenshot-to-task" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Screenshot To Task free?
Yes, Screenshot To Task is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Screenshot To Task support?
Screenshot To Task is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux, win32).
Who created Screenshot To Task?
It is built and maintained by vx：17605205782 (@52yuanchangxing); the current version is v1.0.0.
More Skills