Skip to content

CherryHQ/cherry-studio / resources/skills/cherry-tool-guide

cherry-tool-guide

Verified

Cherry tool routing: bun, uv, rg, knowledge, memory, schedules, skills, MCP, web. Read before shell workarounds.

FileKindSize
SKILL.mdskill md8.6 KB
references/automation.mdmarkdown1.5 KB
references/autonomy.mdmarkdown6.7 KB
references/cli.mdmarkdown4.3 KB
references/documents.mdmarkdown3.1 KB
references/knowledge.mdmarkdown2.6 KB
references/mcp.mdmarkdown2.8 KB
references/memory.mdmarkdown2.1 KB
references/outputs.mdmarkdown1.5 KB
references/sessions.mdmarkdown5.4 KB
references/skills.mdmarkdown1.9 KB
references/web.mdmarkdown2.4 KB

references/automation.md

View on GitHub
# Browser and Computer automation

Use the live Automation REPL: `automation_repl` / `automation_repl_reset` in ordinary
chat, or the `automation` server's `js` / `reset` tools in Agent sessions. Runtime
prefixes may differ. Code Mode is not required. Only enabled surfaces are usable.

- Browser tasks: load `cherry-browser`, then bind `var tab = await browser.getTab()`.
- Desktop tasks: load `cherry-computer`, then bind a known app with
  `var app = await computer.getApp('Calculator')`.

The first binding emits API documentation and initial state. Read them before the
next cell; do not search for the retired individual Browser/Computer MCP tools.
Use the object's methods to batch known actions and emit an observation at each
decision boundary. The host retains permissions, application ownership and stop state.

After context loss, request `browser.documentation()` or `computer.documentation()`.
Use `REPL_CONTEXT` to inspect variable names and generation, not repeated declarations.
After reset, bind again. Across turns, observe before acting with a retained handle.
Reset cannot grant permission, resume user-stopped control or authorize a new target.

If the tool is missing, check the session's Browser/Computer capability and the
corresponding global control setting. Desktop actions also require OS permissions.
Channel-linked or restricted Agent sessions may not expose automation. Report the
actual missing capability; do not use shell, browser profiles or global input to
bypass it. Runtime cleanup failures are distinct from a user stopping control.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
discernment-nudgeanthropics/skillsAfter you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.Stars: 195kUpdated Claude CodeCodexVerifiedInstall
internal-commsanthropics/skillsA set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).Stars: 195kUpdated Claude CodeCodexVerifiedInstall