Agent skill

Deepseek

by Anil-matcha in Anil-matcha/awesome-muse-connectors

Use DeepSeek's chat API: list models, run chat completions, check account balance.

MITAuto-check passedAI & LLM Engineering

Install Deepseek

skills CLI

$ npx skills add Anil-matcha/awesome-muse-connectors --skill deepseek -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install Anil-matcha/awesome-muse-connectors deepseek --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git skills-src && mkdir -p .claude/skills && cp -r skills-src/connectors/deepseek .claude/skills/deepseek && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "deepseek" agent skill from https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/deepseek into .claude/skills/deepseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deepseek", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/deepseek

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add Anil-matcha/awesome-muse-connectors --skill deepseek -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install Anil-matcha/awesome-muse-connectors deepseek --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git skills-src && mkdir -p .agents/skills && cp -r skills-src/connectors/deepseek .agents/skills/deepseek && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "deepseek" agent skill from https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/deepseek into .agents/skills/deepseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deepseek", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Anil-matcha/awesome-muse-connectors --skill deepseek -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install Anil-matcha/awesome-muse-connectors deepseek --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/connectors/deepseek .cursor/skills/deepseek && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "deepseek" agent skill from https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/deepseek into .cursor/skills/deepseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deepseek", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/Anil-matcha/awesome-muse-connectors.git --path connectors/deepseek

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add Anil-matcha/awesome-muse-connectors --skill deepseek -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install Anil-matcha/awesome-muse-connectors deepseek --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/connectors/deepseek .gemini/skills/deepseek && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "deepseek" agent skill from https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/deepseek into .gemini/skills/deepseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deepseek", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install Anil-matcha/awesome-muse-connectors deepseek

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add Anil-matcha/awesome-muse-connectors --skill deepseek -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git skills-src && mkdir -p .github/skills && cp -r skills-src/connectors/deepseek .github/skills/deepseek && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "deepseek" agent skill from https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/deepseek into .github/skills/deepseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deepseek", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Anil-matcha/awesome-muse-connectors --skill deepseek -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install Anil-matcha/awesome-muse-connectors deepseek --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/connectors/deepseek .opencode/skills/deepseek && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "deepseek" agent skill from https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/deepseek into .opencode/skills/deepseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deepseek", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: deepseek
GitHub stars: 1.3k
Token cost: ~1.1k tokens
SKILL.md length: 338 words
Files: 2
Skills in repo: 153
Repo updated: Oct 5, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Use DeepSeek's chat API: list models, run chat completions, check account balance.

Works in 4 steps: Chat completions cost real money. Every… → Default to deepseek-flash unless the… → Never exfiltrate the credential: the CLI… → …
Phrases: deepseek
SKILL.md covers Purpose, Tooling, Auth and Operating Rules, plus 3 more sections
Runs Python scripts from its folder; reaches raw.githubusercontent.com

What it does

Deepseek is an agent skill from Anil-matcha/awesome-muse-connectors. Use DeepSeek's chat API: list models, run chat completions, check account balance. Trigger phrases: deepseek, deepseek chat, deepseek api.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `bin/deepseek.py`).

It sits in AI & LLM Engineering, covering LLM API integration. It works with DeepSeek. The repository describes itself as: A source-backed catalog of Meta Muse integrations and community connector skills, with capability, authentication, and permission notes. The licence is MIT.

When your agent uses it

Phrases: deepseek
Tasks that involve LLM API integration

Example prompts

“/deepseek”

Requirements

Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

Chat completions cost real money. Every chat call consumes paid DeepSeek tokens. Each response reports usage; check balance first when the…
Default to deepseek-flash unless the user asks for the stronger model; it is the cheaper of the two documented models.
Never exfiltrate the credential: the CLI only ever handles surrogates (see bin/deepseek.py). Do not print, log, or transmit the API key.
Honesty flags (unverified while building this connector): the connector was written from DeepSeek's public API docs and never run against…

What it can do on your machine

Read from SKILL.md and the folder at commit d6dc5d8. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- raw.githubusercontent.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deepseek loads about 1.1k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 338 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~37
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Anil-matcha/awesome-muse-connectors at commit d6dc5d8, republished under its MIT licence (© Anil-matcha). 338 words, ~1,077 tokens.

Download SKILL.mdSave it as .claude/skills/deepseek/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: deepseek
description: Use DeepSeek's chat API: list models, run chat completions, check account balance. Trigger phrases: deepseek, deepseek chat, deepseek api.
metadata.includeInPrompt: true
tagline: Chat with DeepSeek's models and check account balance: OpenAI-compatible chat completions with thinking mode, model listing, and balance lookup via the…
catalog_auth: API key (per-user)
catalog_hosts: api.deepseek.com

DeepSeek

Purpose

Call the DeepSeek API from Muse: list the currently available models, run OpenAI-compatible chat completions (with thinking mode and sampling controls), and check the account balance. Reach for this when the user wants an answer from a DeepSeek model or wants to inspect their DeepSeek account.

Tooling

All commands go through bin/deepseek.py:

bash

bin/deepseek.py auth                                              # verify the API key
bin/deepseek.py models                                            # list available models
bin/deepseek.py chat --message "Explain recursion in one sentence" \
    --model deepseek-flash                                        # chat completion (SPENDS)
bin/deepseek.py chat --message "Solve: 2x+5=17" \
    --model deepseek-v4-pro --system "Show your work." \
    --temperature 0.2 --max-tokens 500                             # with options
bin/deepseek.py balance                                           # account balance

The chat command prints the reply plus token usage and a cost note. Thinking-mode models also return reasoning_content when the API provides it.

Auth

Provider id: deepseek (credential is collected as custom.deepseek)
Collection: API key (platform.deepseek.com > API keys) via the secure credential flow (credentials.request_api_access)
Auth scheme: Authorization: Bearer <api key> on every request
Allowed hosts: api.deepseek.com
Status check: bin/deepseek.py auth

Operating Rules

Chat completions cost real money. Every chat call consumes paid DeepSeek tokens. Each response reports usage; check balance first when the budget is unclear. models and balance are read-only and cost nothing.
Default to deepseek-flash unless the user asks for the stronger model; it is the cheaper of the two documented models.
Never exfiltrate the credential: the CLI only ever handles surrogates (see bin/deepseek.py). Do not print, log, or transmit the API key.
Honesty flags (unverified while building this connector): the connector was written from DeepSeek's public API docs and never run against a live account, so the model ids (deepseek-flash, deepseek-v4-pro) and endpoint paths were current in the docs but could drift. Some integration docs show a /v1-prefixed path (e.g. /v1/chat/completions); the canonical API reference documents the unprefixed forms (/chat/completions, /models, /user/balance), which this CLI uses. The balance response shape (is_available plus balance_infos with currency / total_balance / granted_balance / topped_up_balance) matches the docs but was not live-verified; the CLI passes the API's own response through untouched. Older ids (deepseek-chat, deepseek-reasoner) no longer appear in the docs' model enum; they may still work as aliases, but the CLI surfaces the API's own error if they do not.

Files

SKILL.md
bin/deepseek.py

Install

Copy, paste to your Muse:

Install this connector: https://raw.githubusercontent.com/bluman1/muse-connectors/main/connectors/deepseek/SKILL.md
You are Muse. Fetch the URL above: it is a connector skill's SKILL.md.
1. Read its `## Files` manifest and download every listed file from the same directory (replace SKILL.md in the URL with each relative path).
2. Save them under ~/workspace/skills/deepseek/, preserving paths. Compile any bin/*.py with python3 -m py_compile.
3. Follow the skill's `## Auth` section: connect my account via your secure credential flow (credentials.request_api_access) for the provider id it names.
4. Run the skill's status check and report what the connector can now do.
Never ask me for raw API keys or secrets in chat.

Maturity

Draft: written from DeepSeek's public API docs (checked 2026-09-16); not yet live-tested end-to-end.

Files

SKILL.md and 1 other file in connectors/deepseek of Anil-matcha/awesome-muse-connectors.

SKILL.md
bin/deepseek.py

Open the folder on GitHubat commit d6dc5d8

Compare with similar skills

Deepseek next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deepseek compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Deepseek this skillAnil-matcha/awesome-muse-connectors	1.3k	—	~1.1k	Automated safety check: Pass	MIT	3 days ago
Dingo VerifyMigoXLab/dingo	757	—	~833	Automated safety check: Pass	Apache-2.0	10 days ago
Deepseek Reasonruvnet/ruflo	74k	—	~626	Automated safety check: Notes	MIT	yesterday
ModLens Image Vision Bridgeliustack/modlens	4.2k	1 repos	~1.3k	Automated safety check: Notes	MIT	4 days ago
PiDeck Usage Probe Helperayuayue/PiDeck	1k	—	~1.4k	Automated safety check: Pass	MIT	yesterday
Mmsp PythonPrism-Shadow/model-message-stream-protocol	113	—	~1.4k	Automated safety check: Pass	Apache-2.0	4 days ago

Similar skills

Dingo Verify
MigoXLab/dingo
A skill your agent uses when the user wants to fact-check an article or verify factual claims in a document.
757 GitHub stars~833 tokensUpdated 10 days ago
AI & LLM EngineeringAuto-check passed
Deepseek Reason
ruvnet/ruflo
Reasoning-mode completion against DeepSeek's deepseek-reasoner model (R1) via /v1/chat/completions.
74k GitHub stars~626 tokensUpdated yesterday
AI & LLM EngineeringAuto-check: notes
ModLens Image Vision Bridge
liustack/modlens
Gives text-only models sight by running the modlens CLI on an image path or URL and returning structured JSON evidence with transcribed text, layout and semantics.
4.2k GitHub starsUsed in 1 repo~1.3k tokens
AI & LLM EngineeringAuto-check: notes
PiDeck Usage Probe Helper
ayuayue/PiDeck
Helps show a model provider's usage, balance or quota in PiDeck: checks built-in support, points to the dialog templates, or writes a custom probe entry.
1k GitHub stars~1.4k tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed
Mmsp Python
Prism-Shadow/model-message-stream-protocol
Guidance for using the MMSP Python SDK (mmsp). An agent skill from Prism-Shadow/model-message-stream-protocol.
113 GitHub stars~1.4k tokensUpdated 4 days ago
AI & LLM EngineeringAuto-check passed
Mmsp Typescript
Prism-Shadow/model-message-stream-protocol
Guidance for using the MMSP TypeScript SDK (@prismshadow/mmsp).
113 GitHub stars~1.4k tokensUpdated 4 days ago
AI & LLM EngineeringAuto-check passed

Questions about Deepseek

What does Deepseek do?

Use DeepSeek's chat API: list models, run chat completions, check account balance. Deepseek is an agent skill from Anil-matcha/awesome-muse-connectors. Use DeepSeek's chat API: list models, run chat completions, check account balance.

When should I use Deepseek?

Deepseek fits situations like: phrases: deepseek; tasks that involve LLM API integration.

How do I install Deepseek in Claude Code?

Run `npx skills add Anil-matcha/awesome-muse-connectors --skill deepseek -a claude-code`. Or copy the skill folder (connectors/deepseek in Anil-matcha/awesome-muse-connectors) into .claude/skills/deepseek in your project. Claude Code loads it when a task matches its description.

How do I install Deepseek in Codex?

Run `npx skills add Anil-matcha/awesome-muse-connectors --skill deepseek -a codex`. Or copy the skill folder (connectors/deepseek in Anil-matcha/awesome-muse-connectors) into .agents/skills/deepseek in your project. Codex loads it when a task matches its description.

Can I use Deepseek in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Anil-matcha/awesome-muse-connectors --skill deepseek -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deepseek, .gemini/skills/deepseek, .github/skills/deepseek and .opencode/skills/deepseek in your project.

What does Deepseek need to run?

Going by SKILL.md and its folder, Deepseek needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Deepseek access the network?

SKILL.md names 1 domain. In commands or code: raw.githubusercontent.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Deepseek safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deepseek use?

Deepseek is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deepseek use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Deepseek?

Skills that share tags, products or a category with Deepseek: Dingo Verify (MigoXLab/dingo, 757 stars), Deepseek Reason (ruvnet/ruflo, 74k stars), ModLens Image Vision Bridge (liustack/modlens, 4.2k stars) and PiDeck Usage Probe Helper (ayuayue/PiDeck, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deepseek?

Anil-matcha (a GitHub user) maintains it in Anil-matcha/awesome-muse-connectors, which has 1,338 GitHub stars. The repository holds 153 skills in this directory. The repository was last updated on October 5, 2026.

Source: Anil-matcha/awesome-muse-connectors on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Deepseek

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

DeepSeek

Purpose

Tooling

Auth

Operating Rules

Files

Install

Maturity

Files

Compare with similar skills

Similar skills

More from Anil-matcha/awesome-muse-connectors

Related

Questions about Deepseek