Add Provider (DeepChat)
Adds a new LLM provider to DeepChat through reviewed source changes.
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 12, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 3e742dd
Main change since our 12.07 test: upstream refactored the main process architecture (PR #1987), and all paths from old notes died — src/main/presenter/configPresenter/providers.ts no longer exists. The author synchronously rewrote the skill to the new layout (src/main/provider/defaults.ts, providerId.ts, providerRegistry.ts, aiSdk/providerFactory.ts, managers/providerInstanceManager.ts), and we re-checked: all 8 mentioned paths are in place, all three validation commands (pnpm run format/i18n/lint) are actually in package.json. Ran A/B on the task 'add Cerebras provider' directly in a fresh clone and checked the result via bun-import of real modules: baseline only modifies defaults.ts and gets a working entry, but with a default fallback by apiType (checkStrategy: fetch-models), while the skill additionally leads to providerRegistry.ts, where resolveAiSdkProviderDefinition returns an already configured definition (generate-text, credentialStrategy api-key, checkModelId) — the difference is real, but small. However, both variants did not touch src/renderer/src/components/icons/modelIconRegistry.ts and llm-icons, which upstream modifies with every real provider addition commit (TokenLab, DaoXE) — these files are not in the skill's lists. Verdict remains the same, setup: outside the DeepChat monorepo clone, the skill is still non-functional, the installed folder is a single SKILL.md referencing external sources.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 6/10
- Docs & honesty 4/5
What Add Provider (DeepChat) does
Add a DeepChat LLM provider through explicit reviewed source changes. Use when a developer asks Codex to add a provider, provider profile, upstream provider config, model catalog mapping, provider auth behavior, or a special provider adapter in this repository.
How to install Add Provider (DeepChat)
git clone https://github.com/ThinkInAIXYZ/deepchat
mkdir -p ~/.claude/skills
cd deepchat && cp -r .agents/skills/add-provider ~/.claude/skills/add-provider
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Add Provider (DeepChat)
-
/add-providerAdds a new LLM provider to DeepChat through reviewed source changes.
It also activates on plain-language prompts like these:
-
Add a new LLM provider to DeepChat -
Set up a model catalog mapping for this provider -
Add auth handling for a new provider adapter
Frequently asked questions
- Is the Add Provider (DeepChat) skill free?
- Yes. The skill itself is free from ThinkInAIXYZ/deepchat. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Add Provider (DeepChat) work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 12, 2026. Verdict: Works with setup. Main change since our 12.07 test: upstream refactored the main process architecture (PR #1987), and all paths from old notes died — src/main/presenter/configPresenter/providers.ts no longer exists. The author synchronously rewrote the skill to the new layout (src/main/provider/defaults.ts, providerId.ts, providerRegistry.ts, aiSdk/providerFactory.ts, managers/providerInstanceManager.ts), and we re-checked: all 8 mentioned paths are in place, all three validation commands (pnpm run format/i18n/lint) are actually in package.json. Ran A/B on the task 'add Cerebras provider' directly in a fresh clone and checked the result via bun-import of real modules: baseline only modifies defaults.ts and gets a working entry, but with a default fallback by apiType (checkStrategy: fetch-models), while the skill additionally leads to providerRegistry.ts, where resolveAiSdkProviderDefinition returns an already configured definition (generate-text, credentialStrategy api-key, checkModelId) — the difference is real, but small. However, both variants did not touch src/renderer/src/components/icons/modelIconRegistry.ts and llm-icons, which upstream modifies with every real provider addition commit (TokenLab, DaoXE) — these files are not in the skill's lists. Verdict remains the same, setup: outside the DeepChat monorepo clone, the skill is still non-functional, the installed folder is a single SKILL.md referencing external sources.
- What is the Add Provider (DeepChat) SkillProof Score?
- 8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 4/5.
- How do I install Add Provider (DeepChat)?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Add Provider (DeepChat) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.