Agent skill

Recording

by codewhale-hq in codewhale-hq/Codewhale

Capture screenshots on registered computers, record on macOS or HarmonyOS, and manage saved captures.

MITAuto-check passedProductivity & Automation

Install Recording

skills CLI
$ npx skills add codewhale-hq/Codewhale --skill recording -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install codewhale-hq/Codewhale recording --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/codewhale-hq/Codewhale.git skills-src && mkdir -p .claude/skills && cp -r skills-src/crates/tui/plugins/computer-use/skills/recording .claude/skills/recording && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
recording
GitHub stars
41k
Token cost
~540 tokens
SKILL.md length
281 words
Files
1
Skills in repo
63
Repo updated
First seen
Licence
MIT

At a glance

Capture screenshots on registered computers, record on macOS or HarmonyOS, and manage saved captures.

  • Works in 5 steps: Pick the computer (computer_list, or… → Check request_access when readiness is… → Do the work (or let the user do it). → …
  • Productivity & Automation work in your project
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Recording is an agent skill from codewhale-hq/Codewhale. Capture screenshots on registered computers, record on macOS or HarmonyOS, and manage saved captures. Probe capabilities before recording.

Its SKILL.md is about 540 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation. It works with macOS. The repository describes itself as: Open-source coding agent for your terminal, built in Rust and on a journey of continuous community improvement. Issues and PRs welcome. The licence is MIT.

When your agent uses it

  • Productivity & Automation work in your project

Example prompts

  • “/recording”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Pick the computer (computer_list, or pass computer — it switches).
  2. Check request_access when readiness is unknown. On a supported target,
  3. Do the work (or let the user do it).
  4. recording_stop with the returned id → finalized file path + bytes.
  5. recording_list shows everything saved; recording_status checks one.

What it can do on your machine

Read from SKILL.md and the folder at commit fead51e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Recording loads about 540 tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 281 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~540

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from codewhale-hq/Codewhale at commit fead51e, republished under its MIT licence (© codewhale-hq). 281 words, ~540 tokens.

Download SKILL.mdSave it as .claude/skills/recording/SKILL.md (or your agent's skills folder).
name
recording
description
Capture screenshots on registered computers, record on macOS or HarmonyOS, and manage saved captures. Probe capabilities before recording.

Recording and screenshots

  1. Pick the computer (computer_list, or pass computer — it switches).
  2. Check request_access when readiness is unknown. On a supported target, use recording_start with optional display, region, fps and durationSec (macOS auto-stop), or intervalMs (HarmonyOS snapshot cadence).
  3. Do the work (or let the user do it).
  4. recording_stop with the returned id → finalized file path + bytes.
  5. recording_list shows everything saved; recording_status checks one.

Platform truths:

  • macOS: ScreenCaptureKit inside the signed helper captures a display or region straight to .mov — no system recorder selection UI and no desktop dimming overlay. If capture is denied, Screen Recording permission is missing for whoever ran it: the Codewhale Computer Use app when request_access says via: "app", else the terminal that hosts the server — tell the user which, do not retry.
  • Windows and Linux: recording is unavailable pending session-owned recorder cleanup. Use screenshots; installing ffmpeg does not enable it.
  • HarmonyOS: no native CLI recorder; the backend captures snapshot_display frames at intervalMs and muxes with ffmpeg on stop. The receipt labels the mode snapshot-series — never call it real-time.

Screenshots: screenshot returns a saved path, geometry and raster_id. Carry that ID in pixel targets and as the parent of zoom when a target is too small to read. Each zoom returns a new child ID; use it for child-image coordinates. OCR coordinate targets already include their pin. Pins remain reusable while current; older unpinned calls retain latest-raster behavior. A replaced capture, app launch or route change retires the context. On raster_stale or no_raster, observe again; never drop the ID to retry. Pins detect capture replacement, not a changed UI: re-observe after UI changes and verify input separately. An omitted image cannot supply coordinates.

© codewhale-hq, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in crates/tui/plugins/computer-use/skills/recording of codewhale-hq/Codewhale.

Open the folder on GitHubat commit fead51e

Compare with similar skills

Recording next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Recording compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Recording this skillcodewhale-hq/Codewhale41k—~540Automated safety check: PassMIT
Mac Computer UseTo3akaRin/mac-computer-use1.1k1 repos~495Automated safety check: PassMIT
Verify Reelrselbach/reel118—~2kAutomated safety check: PassUnlicense
Slack Messaginghaojing8312/WorkClaw141—~897Automated safety check: PassApache-2.0
Steerdisler/mac-mini-agent272—~2.1kAutomated safety check: PassNone
Computer Usekunpengtalk/PeakCode166—~2.5kAutomated safety check: PassMIT

Similar skills

  • Mac Computer Use

    To3akaRin/mac-computer-use

    操作 macOS 桌面应用,探测窗口和自动化接口、截图、读取或修改辅助功能元素、执行鼠标键盘动作,以及通过 CDP 操作内嵌 Chromium 页面。适用于桌面应用自动化与界面验收;普通网页任务优先使用已有浏览器工具。

    1.1k GitHub starsUsed in 1 repo~495 tokens
    Productivity & AutomationAuto-check passed
  • Verify Reel

    rselbach/reel

    Verify Reel, the macOS menu-bar screen recorder, by launching a disposable app bundle and driving its real UI with Computer Use.

    118 GitHub stars~2k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed
  • Slack Messaging

    haojing8312/WorkClaw

    A skill your agent uses when asked to send or read Slack messages, check Slack channels, test Slack integrations, or interact with a Slack workspace from the command line.

    141 GitHub stars~897 tokensUpdated 4 mo ago
    Productivity & AutomationAuto-check passed
  • Steer

    disler/mac-mini-agent

    macOS GUI automation CLI. An agent skill from disler/mac-mini-agent.

    272 GitHub stars~2.1k tokensUpdated 7 mo ago
    Productivity & AutomationAuto-check passed
  • Computer Use

    kunpengtalk/PeakCode

    Drive a macOS app through the computer tool — read its accessibility tree, act on elements, and use real input only when the tree cannot reach the target.

    166 GitHub stars~2.5k tokensUpdated 16 days ago
    Productivity & AutomationAuto-check passed
  • Things Mac

    trpc-group/trpc-agent-go

    Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database).

    1.8k GitHub starsUsed in 12 repos~888 tokens
    Productivity & AutomationAuto-check passed

More from codewhale-hq/Codewhale

All 63 skills in this repo
  • Codewhale Dogfood Install

    codewhale-hq/Codewhale

    Proves a Codewhale change in the real product: a stamped release build, an atomic local install, fresh-shell verification and manual QA that automated gates cannot cover.

    41k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Codewhale Session Handoff

    codewhale-hq/Codewhale

    Writes a paste-ready handoff for the next agent session, opening with a state-check command block and separating done, suspected and blocked work.

    41k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Codewhale Landing Workflow

    codewhale-hq/Codewhale

    Decides how verified work should reach main, directly, in a worktree or on an integration branch, while keeping contributor credit and respecting merge gates.

    41k GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Sub-Agent Delegation

    codewhale-hq/Codewhale

    Guides when and how to split multi-step coding, research or verification work into focused sub-agent runs while the parent keeps integration and final checks.

    41k GitHub stars~790 tokensUpdated today
    Auto-check passed
  • Codewhale Fleet Manager

    codewhale-hq/Codewhale

    Triages and manages Codewhale fleet runs and workers with typed commands, classifying failures and choosing a safe restart, resume or escalation.

    41k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • GitHub Issue Bulk Assigner

    codewhale-hq/Codewhale

    Moves a list of GitHub issues into a milestone or assigns them to owners with the gh CLI, checking each one before and after the change.

    41k GitHub stars~953 tokensUpdated today
    Auto-check passed

Works with

Questions about Recording

What does Recording do?

Capture screenshots on registered computers, record on macOS or HarmonyOS, and manage saved captures. Recording is an agent skill from codewhale-hq/Codewhale. Capture screenshots on registered computers, record on macOS or HarmonyOS, and manage saved captures.

When should I use Recording?

Recording fits situations like: productivity & Automation work in your project.

How do I install Recording in Claude Code?

Run `npx skills add codewhale-hq/Codewhale --skill recording -a claude-code`. Or copy the skill folder (crates/tui/plugins/computer-use/skills/recording in codewhale-hq/Codewhale) into .claude/skills/recording in your project. Claude Code loads it when a task matches its description.

How do I install Recording in Codex?

Run `npx skills add codewhale-hq/Codewhale --skill recording -a codex`. Or copy the skill folder (crates/tui/plugins/computer-use/skills/recording in codewhale-hq/Codewhale) into .agents/skills/recording in your project. Codex loads it when a task matches its description.

Can I use Recording in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add codewhale-hq/Codewhale --skill recording -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/recording, .gemini/skills/recording, .github/skills/recording and .opencode/skills/recording in your project.

What does Recording need to run?

SKILL.md names no scripts, command-line tools or credentials: Recording is instructions for the agent only.

Does Recording access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Recording safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Recording use?

Recording is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Recording use?

About 540 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Recording?

Skills that share tags, products or a category with Recording: Mac Computer Use (To3akaRin/mac-computer-use, 1.1k stars), Verify Reel (rselbach/reel, 118 stars), Slack Messaging (haojing8312/WorkClaw, 141 stars) and Steer (disler/mac-mini-agent, 272 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Recording?

codewhale-hq (a GitHub organization) maintains it in codewhale-hq/Codewhale, which has 41,079 GitHub stars. The repository holds 63 skills in this directory. The repository was last updated on October 8, 2026.

Source: codewhale-hq/Codewhale on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.