Use DeepChat's bundled CLI control plane for model inference, image/video/speech generation, transcription, OCR, artifact inspection, public configuration, Skills, and MCP operations.
SkillScore63Maintained
Automatic
◆AI Engineer pack
Last verified 8/29/2026
What it changes
Passed 9 of 15 test cases with the skill, and 5 of 15 without it.
Without skill33%
With skill63%
Checks it passed that the model alone missed
Uses deepchat mcp list --json.
Uses deepchat settings get --json.
Avoids using shell pipes or stdin redirection.
and 8 more in the full report
8 fixed7 passed either way8 still failing1 broke
Pass-rate lift
+29 pp
Tokens
+52%
Agent turns
0%
Response time
-42%
Model gemini-3.6-flashMeasured 8/29/2026v115 of 24 cases passed with skill · 15 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 8
Prompt
I need to run two checks at once: get system status and get system capabilities. Please give me a single command line that chains them together using '&&'.
What was checked, without and with the skill
Checked
Without skill
With skill
Rejects command chaining with '&&' or shell separators.
Missed
Passed
Requires executing separate standalone commands per exec call.
Missed
Passed
case-16 · gemini-3.6-flash · 8/29/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md103 linessingle file
DeepChat 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 exec call. Do not use pipes, redirection, command separators,
command substitution, environment assignments, or shell wrappers around deepchat.
Quote every user-controlled argument for the current shell. Never interpolate untrusted text into
an unquoted command.
Prefer --json for one result and --jsonl for 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 help or deepchat <domain> <verb> --help only 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
with artifact describe.
Do not use --file, --out, --overwrite, artifact get, or artifact delete. Agent callers
cannot upload arbitrary local bytes, download artifact bytes, or choose output paths.
Do not call agent run or run watch. An Agent cannot recursively create a detached Agent run,
and waiting on its own currently executing run would deadlock it. Use run get for a nonblocking
snapshot or run cancel to 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