Computer Use Notes

v1.0.0

Record and classify user observations about what computer use can do, partially do, and cannot do. Use when the user says to remember/log/record capability f...

0· 109·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for gift-is-coding/computer-use-notes.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Computer Use Notes" (gift-is-coding/computer-use-notes) from ClawHub.
Skill page: https://clawhub.ai/gift-is-coding/computer-use-notes
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install computer-use-notes

ClawHub CLI

Package manager switcher

npx clawhub@latest install computer-use-notes
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the behavior: the skill extracts a single-sentence note, classifies it, and persists it. Required capabilities (none) are proportional to that purpose.
Instruction Scope
SKILL.md instructs the agent to extract a concise note, classify it, and call the included Python script. The instructions only read/write the skill's own memory files and do not request other system files, environment variables, or external endpoints.
Install Mechanism
No install spec; the skill is instruction+one local script. There is no network download or package install, and nothing is written outside the agent workspace's memory folder.
Credentials
No environment variables, credentials, or config paths are required. The script only writes/reads memory/computer-use-notes.* files under the agent workspace.
Persistence & Privilege
always is false and the skill does not modify other skills or system-wide settings. It writes its own memory files (expected behavior for a logging skill).
Assessment
This skill appears safe and does what it says: it will run a local Python script to append classified one-line notes to memory/computer-use-notes.jsonl and regenerate a Markdown board. Before installing, verify you are comfortable with the agent creating and storing notes in the agent workspace (these files may contain any user-provided text and could include sensitive content). Ensure python3 is available in the environment. If you need stricter controls, confirm where 'memory/' is mounted and consider restricting what the agent is allowed to log.

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

latestvk972nmx02hw374e1g3rcfmp0bx854r3a
109downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0

Computer Use Notes

When the user provides a capability observation, do the following:

  1. Extract one concise note sentence.
  2. Classify into one of three categories:
    • can-do: clearly works reliably
    • partial: works in some cases / unstable / needs workaround
    • cannot-do: currently not possible or repeatedly fails
  3. Append the note with timestamp via script:
    • python3 skills/computer-use-notes/scripts/add_note.py --category <category> --note "<text>"
  4. Reply with a short confirmation including category.

Classification hints

  • Contains words like “能做 / 可以 / 成功 / works” => can-do
  • Contains words like “部分能做 / 偶尔 / 不稳定 / workaround” => partial
  • Contains words like “不能做 / 无法 / 失败 / blocked” => cannot-do

If ambiguous, ask one short clarification question.

Data files

  • Raw log: memory/computer-use-notes.jsonl
  • Human-readable board: memory/computer-use-notes.md

Comments

Loading comments...