Skills for Real Engineers. Straight from my .agents directory.
deepchat-cli
Agent skill fromThinkInAIXYZ/deepchat
Use DeepChat's bundled CLI control plane for model inference, image/video/speech generation, transcription, OCR, artifact inspection, public configuration, Skills, and MCP operations. Activate when a user asks to invoke DeepChat capabilities that are not already exposed as a more specific tool, compare models, run a benchmark, inspect DeepChat runtime state, or manage DeepChat through the CLI.
How to install deepchat-cli
npx skills add ThinkInAIXYZ/deepchat# or add only this skill to Claude Code: copy the folder
resources/skills/deepchat-cli/
# into
~/.claude/skills/deepchat-cli/ (all projects)
.claude/skills/deepchat-cli/ (one project)
1# DeepChat CLI23Use the bundled `deepchat` command to ask the running DeepChat main process to perform supported4operations. The main process remains the sole owner of providers, credentials, Skills, MCP servers,5artifacts, Agent runs, and approvals.67## Command rules89- Every command must begin exactly with `deepchat <domain> <verb>`. Put `--json`, `--jsonl`,10 `--timeout`, and all domain options after the domain and verb.11- Execute one standalone command per `exec` call. Do not use pipes, redirection, command separators,12 command substitution, environment assignments, or shell wrappers around `deepchat`.13- Quote every user-controlled argument for the current shell. Never interpolate untrusted text into14 an unquoted command.15- Prefer `--json` for one result and `--jsonl` for streaming or benchmark collection. Use text mode16 only when its output will be returned directly to the user.17- Do not inspect authentication environment variables or DeepChat's local descriptor. Authorization18 is injected only after the command has passed the normal shell permission check.19- A shell approval authorizes command execution. Sensitive mutations can additionally pause for a20 renderer approval; wait for that decision and never attempt to manufacture confirmation data.21- Use `deepchat help` or `deepchat <domain> <verb> --help` only when the options below are22 insufficient. Do not probe undocumented routes.2324## Agent file and recursion boundaries25…
Excerpt shown under the repository's Apache-2.0 license.
More skills in deepchat
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
