deepchat-cli skill
✓ VerifiedManage DeepChat operations including model inference, media generation, transcription, OCR, and MCP configurations via a command-line interface.
- GitHub stars
- 6,388
- Files
- 1
- Last commit
- Nov 11, 2026
- License
- Apache-2.0
- Allowed tools
- —
What does the deepchat-cli skill do?
deepchat-cli manages DeepChat operations including model inference, media generation, transcription, OCR, and MCP configurations via a command-line interface.
Summary generated from the skill's SKILL.md.
About the deepchat-cli skill
Managing DeepChat operations through a command-line interface allows developers to control model inference, media generation, and system configurations. An agent should load this skill when a user needs to perform tasks not covered by specific tools, such as comparing models, running benchmarks, or inspecting the runtime state. It uses the deepchat command to interact with a main process that owns all providers, credentials, and MCP servers.
The skill provides tools for generating images, video, and speech, as well as performing transcription and OCR. It can also manage public settings like font size or notifications and install HTTPS Skills or remote MCP configurations. While it can inspect artifacts and model configurations using the --json or --jsonl flags, it cannot download artifact bytes, upload local files, or perform destructive operations like deleting artifacts or removing MCP servers. These sensitive actions require a human terminal or the DeepChat UI.
What an agent can do with it
- 1Extract text from imagesPerform OCR on an existing artifact to retrieve text content.
- 2Configure presentation settingsAdjust user interface preferences such as font size or auto-scroll settings.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the deepchat-cli skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the deepchat-cli skill in Claude Code
~/.claude/skills/deepchat-cli/SKILL.md
$ npx degit ThinkInAIXYZ/deepchat/resources/skills/deepchat-cli ~/.claude/skills/deepchat-cliInstall the deepchat-cli skill in Claude Code (project)
.claude/skills/deepchat-cli/SKILL.md
$ npx degit ThinkInAIXYZ/deepchat/resources/skills/deepchat-cli .claude/skills/deepchat-cliInstall the deepchat-cli skill in Codex
~/.agents/skills/deepchat-cli/SKILL.md
$ npx degit ThinkInAIXYZ/deepchat/resources/skills/deepchat-cli ~/.agents/skills/deepchat-cliInstall the deepchat-cli skill in Gemini CLI
~/.gemini/skills/deepchat-cli/SKILL.md
$ npx degit ThinkInAIXYZ/deepchat/resources/skills/deepchat-cli ~/.gemini/skills/deepchat-cliInstall the deepchat-cli skill in Claude.ai
npx degit ThinkInAIXYZ/deepchat/resources/skills/deepchat-cli deepchat-cli && zip -r deepchat-cli.zip deepchat-cli # claude.ai → Customize → Skills → + → Create skill → Upload a skill → deepchat-cli.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachablethinkinaixyz/deepchat/resources/skills/deepchat-cli is public and reachablegithub.com/thinkinaixyz/deepchat/tree/HEAD/resources/skills/ ↗Pass
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-11github.com/thinkinaixyz/deepchat/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/thinkinaixyz/deepchat/blob/HEAD/resources/skills/ ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/thinkinaixyz/deepchat/blob/HEAD/resources/skills/ ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 112 linesgithub.com/thinkinaixyz/deepchat/blob/HEAD/resources/skills/ ↗Pass
SKILL.md
View on GitHubDeepChat CLI
Use the bundled deepchat command to ask the running DeepChat main process to perform supported
operations. The main process remains the sole owner of providers, credentials, Skills, MCP servers,
artifacts, Agent runs, and approvals.
Command rules
- Every command must begin exactly with
deepchat <domain> <verb>. Put--json,--jsonl,--timeout, and all domain options after the domain and verb. - Execute one standalone command per
execcall. Do not use pipes, redirection, command separators, command substitution, environment assignments, or shell wrappers arounddeepchat. - Quote every user-controlled argument for the current shell. Never interpolate untrusted text into an unquoted command.
- Prefer
--jsonfor one result and--jsonlfor streaming or benchmark collection. Use text mode only when its output will be returned directly to the user. - Do not inspect authentication environment variables or DeepChat's local descriptor. Authorization is injected only after the command has passed the normal shell permission check.
- A shell approval authorizes command execution. Sensitive mutations can additionally pause for a renderer approval; wait for that decision and never attempt to manufacture confirmation data.
- Use
deepchat helpordeepchat <domain> <verb> --helponly when the options below are insufficient. Do not probe undocumented routes.
Agent file and recursion boundaries
- Agent callers may consume a DeepChat-owned artifact with
--artifact <id>and inspect metadata withartifact describe. - Do not use
--file,--out,--overwrite,artifact get, orartifact delete. Agent callers cannot upload arbitrary local bytes, download artifact bytes, or choose output paths. - Do not call
agent runorrun watch. An Agent cannot recursively create a detached Agent run, and waiting on its own currently executing run would deadlock it. Userun getfor a nonblocking snapshot orrun cancelto request cancellation. - Generated media remains in DeepChat's artifact spool. Return the artifact metadata or ID so the application can render or reuse it.
Discovery and model calls
deepchat system status --json
deepchat system capabilities --json
deepchat system doctor --json
deepchat provider list --enabled-only --json
deepchat model list --provider <provider-id> --json
deepchat model config-get --provider <provider-id> --model <model-id> --json
deepchat model invoke --provider <provider-id> --model <model-id> --prompt <quoted-text> --jsonl
Always discover provider and model IDs rather than guessing them. model invoke is a raw provider
call: it does not create a chat session, run tools, or start an Agent loop.
Media, transcription, and OCR
deepchat image generate --provider <provider-id> --model <model-id> --prompt <quoted-text> --jsonl
deepchat video generate --provider <provider-id> --model <model-id> --prompt <quoted-text> --jsonl
deepchat audio speak --provider <provider-id> --model <model-id> --text <quoted-text> --jsonl
deepchat audio transcribe --provider <provider-id> --model <model-id> --artifact <artifact-id> --json
deepchat ocr status --json
deepchat ocr extract --artifact <artifact-id> --json
deepchat artifact describe --id <artifact-id> --json
Use the provider/model lists to choose a compatible runtime. OCR is local and does not require a provider. OCR text is returned inline and is not written to the artifact spool.
Public configuration and management
Read-only operations:
deepchat settings get --json
deepchat skill list --json
deepchat mcp list --json
Agent callers may request renderer approval for preference-only settings, query-free HTTPS Skill installation, and adding a new disabled HTTPS remote MCP configuration. Only perform one when it directly satisfies the user's request:
deepchat settings set --key <public-key> --value <json-scalar> --json
deepchat skill install --url <https-url> --json
deepchat mcp add --name <server-name> --stdin --json
The Agent setting allowlist is limited to presentation preferences such as font size/family, artifact effects, auto-scroll, notifications, and copy-with-reasoning. Agent Skill URLs cannot carry credentials, query parameters, or fragments. The main process classifies MCP input before approval and rejects stdio commands, non-HTTPS endpoints, headers, authorization bindings, or configurations too large to review safely. Provider/model configuration, credential writes, local Skill archives, Skill enable/disable/removal, MCP update/runtime control/removal, and every destructive operation require the DeepChat UI or a human terminal.
Benchmark discipline
- Pin provider/model IDs and pass per-invocation options; do not mutate global defaults to prepare a benchmark.
- Record structured output, exit status, wall time, and errors. Preserve failed samples.
- For OCR, distinguish cache hit, cache miss with warm runtime, cold runtime after app restart, and
offline availability.
ocr clear-cacheinitializes the resource graph but does not start the OCR helper, so classify the next extraction from its reported pre-extraction runtime state. - Run samples sequentially unless the benchmark explicitly measures concurrency; Agent compute is rate-limited and bounded by the main process.
Files in this skill
1deepchat-cli skill questions
How do I install the deepchat-cli skill in Claude Code?
Run npx degit ThinkInAIXYZ/deepchat/resources/skills/deepchat-cli ~/.claude/skills/deepchat-cli. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the deepchat-cli skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
How can I perform model inference using the CLI?
You can use the deepchat model invoke command, providing the provider ID, model ID, and the prompt.
Can the CLI be used to download or upload local files?
No, agent callers are restricted from using commands like --file, --out, or artifact get to prevent uploading or downloading arbitrary bytes.
Does OCR require a specific provider?
No, OCR is a local operation and does not require a provider to function.