Screenshot Capture

v1.0.0

Process screenshots Enzo shares with comments. Save to reference library, extract content, categorize, set reminders, and log patterns. Use when Enzo sends an image with context like "save this", shares a screenshot of content (LinkedIn posts, tweets, articles), or sends ideas/frameworks to remember.

1· 2.8k·15 current·15 all-time
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The name/description (capture, save, extract, categorize, remind, log) matches the SKILL.md steps. All required actions (copy image, append to notes files, summarize, add a reminder, and log a pattern) are consistent with processing screenshots.
Instruction Scope
The instructions operate on local files (cp [inbound image] notes/screenshots/..., write to notes/*.md) and ask the agent to 'extract key content' and 'set a 1-week reminder'. This is within scope, but two behaviors are underspecified: how extraction/OCR is performed (which tool or capability), and where/how reminders are created (calendar, task system, internal state, external service). The cp command also assumes the agent has a defined 'inbound image' path and write permission to the notes directory.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest risk for supply-chain or disk-write install behavior.
Credentials
The skill requests no environment variables, credentials, or external configuration paths. Requested file writes are limited to notes/* and screenshots; no secrets or unrelated service tokens are required.
Persistence & Privilege
always is false and the skill does not request elevated system privileges or modify other skills. It does persist data locally (notes and screenshots), which is expected for its purpose.
Assessment
This skill looks internally consistent, but check these practical items before installing: - Confirm where the 'notes' directory lives and ensure you want screenshots and extracted text written there (who can read/backup/encrypt those files). - Ask the author how 'extract key content' is implemented (OCR/local tool or external API). If external OCR is used, content could leave your environment. - Clarify how reminders are created (which calendar or task system) and whether they will trigger notifications externally; the skill defaults to a 1-week reminder unless told otherwise. - Ensure the agent has appropriate filesystem permissions and that you’re comfortable with automatic saving of potentially sensitive screenshots (test with non-sensitive images first). - If you don’t want automatic autonomous behavior, consider restricting the skill’s ability to run without explicit user approval or ask for an explicit opt-in step before saving or setting reminders. If these questions are answered to your satisfaction (especially about OCR/reminder destinations and storage/access controls), the skill is proportionate to its stated purpose.

Like a lobster shell, security has layers — review code before you run it.

latestvk9778ajvkjwb7hma5rdhwgpd9h80rnkm
2.8kdownloads
1stars
1versions
Updated 1mo ago
v1.0.0
MIT-0

Screenshot Capture

When Enzo shares a screenshot with comments, execute this workflow:

1. Save Screenshot

cp [inbound image] notes/screenshots/[descriptive-name].jpg

Name should reflect content (e.g., positioning-angles.jpg, gpt-ads-hack.jpg)

2. Categorize

Based on Enzo's comment and content, determine category:

CategorySignalsDestination
FrameworkActionable mental model, how-to, processnotes/frameworks.md under main section
AI Hack"AI porn", hackathon material, overpromises but usefulnotes/frameworks.md under "AI Hacks & Hackathon Ideas"
IdeaOriginal thought, "I want to build", future projectnotes/ideas.md

3. Extract & Store

  • Extract key content from screenshot
  • Add to appropriate file with:
    • Date saved
    • Source (if visible)
    • Screenshot reference
    • Enzo's commentary (if provided)
    • Structured summary

4. Set Reminder

Always set a 1-week reminder unless Enzo specifies otherwise.

Reminder text should prompt action:

  • "Have you tested [framework] on anything?"
  • "Did you try [hack]?"
  • "Any progress on [idea]?"

5. Log Pattern

Add observation to notes/patterns.md:

- [category] [topic]: [brief description] — [intent signal]

Intent signals: learn, build, share, remember, reference, hackathon

6. Confirm

Reply with:

  • What was saved and where
  • Reminder date
  • Any commentary acknowledged

Keep confirmation brief.

Comments

Loading comments...