CherryHQ/cherry-studio / resources/skills/cherry-tool-guide
cherry-tool-guide
VerifiedCherry tool routing: bun, uv, rg, knowledge, memory, schedules, skills, MCP, web. Read before shell workarounds.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.6 KB |
| references/automation.md | markdown | 1.5 KB |
| references/autonomy.md | markdown | 6.7 KB |
| references/cli.md | markdown | 4.3 KB |
| references/documents.md | markdown | 3.1 KB |
| references/knowledge.md | markdown | 2.6 KB |
| references/mcp.md | markdown | 2.8 KB |
| references/memory.md | markdown | 2.1 KB |
| references/outputs.md | markdown | 1.5 KB |
| references/sessions.md | markdown | 5.4 KB |
| references/skills.md | markdown | 1.9 KB |
| references/web.md | markdown | 2.4 KB |
references/autonomy.md
View on GitHub# Autonomy: scheduling, notification, and channels
Covers `mcp__cherry-tools__cron`, `mcp__cherry-tools__notify`, and
`mcp__cherry-tools__config`. These three form **one channel-delivery workflow**:
`config` connects the IM channels, `cron` schedules work that can deliver to them, and
`notify` pushes messages/files through them.
Get exact argument shapes from the live tool schema — this reference gives routing,
sequencing, prerequisites, and safety only.
## Intent gate
Schedule changes, notifications, and agent/channel configuration may execute **without
an approval card**. Don't call them merely because they're available — first confirm the
user requested the effect or it's necessary to complete an already-approved task.
## Scheduling — `mcp__cherry-tools__cron`
Schedules work **inside Cherry**. Never use OS `crontab`, `at`, or a background shell
loop for user-facing schedules — Cherry owns execution, delivery, and lifecycle.
Actions:
- **`add`** — a recurring or one-time job. A job needs **exactly one trigger shape**
(recurring expression, interval, or a single future timestamp) — consult the schema
for which fields express that.
- **`update`** — edit an existing job by ID. Supply only changed fields; omitted fields
keep their values. Use this to edit prompts instead of removing and re-creating jobs.
- **`list`** — existing jobs owned by the current Agent.
- **`remove`** — delete a job.
`reuse_session` on `add` / `update` controls whether executions continue in the same
session. It defaults to false on add; omission on update preserves the setting.
For delivery, omitting `channel_ids` on update preserves recipients; `[]` clears them.
Names are unique across all Agents, including disabled jobs. If a name conflict is
not visible in `list`, choose a different name or inspect Settings > Scheduled Tasks.
Use `update` with an owned job ID when editing an existing task.
Jobs can deliver their results to channels (see notify/config below), so scheduling a
report that lands in Telegram is a single `cron` job, not a hand-rolled OS cron entry
plus a separate send.
Omit `channel_ids` to save this turn's configured recipients on the task; use `[]` for
no channel delivery. Explicit IDs follow the same recipient policy as `notify` below.
A task created without channels has no notification recipients until the user adds
channels in the scheduled-task editor's "Send to Channels" field.
## Notification — `mcp__cherry-tools__notify`
Proactively sends the user a message and/or a workspace file through **connected
channels** — use it to push a result, status update, or produced file without waiting to
be asked.
- **Requires configured recipients for this turn.** `notify` is absent otherwise:
desktop turns and brand-new Sessions have none. A channel-originated Session uses
its source channel; a scheduled run uses exactly the task's configured channels,
snapshotted at run start. An offline configured channel does not hide the tool,
but delivery requires a connection.
- **Omit `channel_id` to deliver to all configured recipients**, listed in the tool
description. An explicit ID outside that set is refused with a policy error, never
silently redirected. Only a channel-originated Session may additionally select
another live channel owned by the same Agent.
- **File support varies by channel** — some forward any file, some images only, some
none yet. The tool reports per-channel outcomes; relay them honestly.
`notify` pushes a message/file *through a channel*. To merely register a produced file as
a deliverable in the Cherry UI (no channel send), that's `report_artifacts` — a different
tool; see [outputs.md](outputs.md).
## Channels & self-config — `mcp__cherry-tools__config`
Inspects and manages the agent's own configuration.
**Always `status` first.** It lists current channels (with connection state), the model,
and the adapter types you can add — so you act on real IDs instead of guessing.
Then:
- **`add_channel`** — connect a new IM channel (Telegram, Feishu, Discord, Slack,
WeChat, QQ). Credential-based types need their fields; WeChat/Feishu can use QR mode.
- **`update_channel`** / **`remove_channel`** — change or delete an existing channel by
ID.
- **`reconnect_channel`** — re-establish a dropped channel; for WeChat/Feishu this
re-issues a QR code to re-scan (expired session or failed initial setup).
- **`rename`** the agent, or **`complete_bootstrap`** / **`reset_bootstrap`** onboarding.
**When a channel needs a QR scan**, the tool returns the QR image — display it to the
user and let them scan; the connection completes out of band. Confirm with a follow-up
`status`.
## Recovery
- **`notify` absent** → this session/turn has no configured recipients; don't seek a
workaround. To route scheduled results to a channel, create the task from that
channel's conversation: omit `channel_ids` to save its source channel, or supply
explicit `channel_ids` from a channel-originated Session. A desktop turn cannot
authorize explicit channel IDs. Alternatively, ask the user to set the task's
channels in the scheduled-task editor's "Send to Channels" field; it lists the
owning Agent's channels.
Use `mcp__cherry-tools__config` (`status`) to inspect owned channels and connection state.
- **Recipient policy error naming a channel** → the ID is outside this turn's allowed
recipients; select a configured one or omit `channel_id` (`channel_ids` for `cron`).
- **Configured recipient unavailable** → inspect its connection with `config` (`status`)
and reconnect it; an offline recipient remains configured.
- **Unsupported channel/file** → `notify` reports it per channel; adjust rather than
resending the same payload.
- **Tool error result** → read the message and correct the call; don't silently retry.
## Examples
**Schedule a report and notify on completion**
> "Every weekday morning, summarize my unread items and send it to Telegram."
From the Telegram channel's conversation, use `mcp__cherry-tools__config` (`status`)
to confirm the channel is connected →
`mcp__cherry-tools__cron` (`add`) a recurring weekday job whose prompt builds the summary,
omitting `channel_ids` to save that channel as its recipient. The scheduled run does the
work and delivery; you don't hand-roll an OS cron entry.
**Connect an IM channel**
> "Hook me up to Slack so you can message me there."
`mcp__cherry-tools__config` (`status`) to see supported types and existing channels →
`mcp__cherry-tools__config` (`add_channel`, type Slack) with the required credentials from
the schema → confirm it shows connected in a follow-up `status`. Continue from that
channel's conversation to use `mcp__cherry-tools__notify` there; connecting a channel
does not grant a desktop turn notification recipients.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 463k | Updated | Claude CodeCodex | Verified | Install |
| 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: 463k | Updated | Claude CodeCodex | Verified | Install |
| 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: 195k | Updated | Claude CodeCodex | Verified | Install |
| 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: 195k | Updated | Claude CodeCodex | Verified | Install |