Skip to content

CherryHQ/cherry-studio / resources/builtin-agents/cherry-assistant/.claude/skills/claude-automation-recommender

claude-automation-recommender

Verified

Recommend Claude Code automations (hooks, subagents, skills, plugins, MCP) and review an existing setup.

FileKindSize
LICENSEother11.1 KB
NOTICE.mdmarkdown1.7 KB
SKILL.mdskill md12.0 KB
references/hooks-patterns.mdmarkdown6.2 KB
references/mcp-servers.mdmarkdown7.2 KB
references/plugins-reference.mdmarkdown2.9 KB
references/skills-reference.mdmarkdown9.4 KB
references/subagent-templates.mdmarkdown4.9 KB
# Notice

This skill is **claude-code-setup** (or specifically the `claude-automation-recommender`
sub-skill of it), authored by Anthropic and originally published at:

- Source: https://github.com/anthropics/claude-plugins (via `/plugin install claude-code-setup@claude-plugins-official` in Claude Code)
- Plugin version: 1.0.0
- License: Apache License 2.0 (see `LICENSE` in this directory)
- Author: Isabella He <isabella@anthropic.com>, Anthropic

It is bundled into Cherry Assistant under the terms of the Apache 2.0 license.
The original `plugin.json` wrapper has been omitted — only the skill itself is
shipped, since Cherry Studio's runtime loads `.claude/skills/*` directly.

## Modifications from upstream

Per Apache License 2.0 §4(b), this section lists notable changes Cherry Studio
made to the upstream `SKILL.md`:

- **Added `## Workflow → Phase 0: Confirm Before Scanning` section** before the
  original Phase 1. The upstream skill starts scanning immediately on trigger;
  the Cherry Studio addition requires the agent to first announce the token
  budget (~20–40K) and obtain explicit user confirmation before any filesystem
  read or Bash call. Rationale: Cherry Assistant runs in interactive chat
  sessions where unexpected long scans degrade the UX. The confirmation gate
  lets the user opt for a narrower scope, a verbal-only consultation, or
  deferral. No other behavior is changed.

The `references/*.md` files are unmodified.

## Updating

To update: refresh the cache via `/plugin install claude-code-setup@claude-plugins-official`
on the developer's Claude Code install, then copy the latest
`skills/claude-automation-recommender/SKILL.md` and supporting files into this
directory and re-run `pnpm build:builtin-knowledge`.
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: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall