deepseek-prompt

deepseek-prompt is a skill for Claude Code, Codex from knopki/agent-skills. It costs 84 tokens per session (5,712 once invoked), scanned A, original, MIT.

A prompt-writing guide for tasks sent to DeepSeek models, including DeepSeek V4. It provides separate approaches for prompts used directly by a person and prompts used to launch an autonomous subagent.

In plain words
What is it for?
Use it to draft, refine, or assemble a DeepSeek prompt, choose a thinking mode, or prepare instructions for a DeepSeek subagent.
Why use it?
It helps structure instructions around documented failure patterns such as commentary instead of execution and unclear task modes.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: mentions subagents.

Good fit Use it to draft, refine, or assemble a DeepSeek prompt, choose a thinking mode, or prepare instructions for a DeepSeek subagent.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/knopki/agent-skills/deepseek-prompt
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add knopki/agent-skills --skill deepseek-prompt
Clone the repo
git clone --depth 1 https://github.com/knopki/agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for deepseek-prompt

README.md
[![agentmods](https://agentmods.dev/badge/skills/knopki/agent-skills/deepseek-prompt/github.svg)](https://agentmods.dev/skills/knopki/agent-skills/deepseek-prompt)
Your own site
<a href="https://agentmods.dev/skills/knopki/agent-skills/deepseek-prompt"><img src="https://agentmods.dev/badge/skills/knopki/agent-skills/deepseek-prompt/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for deepseek-prompt

Your own site · 80×15
<a href="https://agentmods.dev/skills/knopki/agent-skills/deepseek-prompt"><img src="https://agentmods.dev/badge/skills/knopki/agent-skills/deepseek-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,712 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.05712
Opus 5 $0.00042 $0.02856
Sonnet 5 $0.00017 $0.01142
Haiku 4.5 $0.00008 $0.00571

Measured 12d ago against content hash d5bd7012a463, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

deepseek-prompt scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- For a fix: `curl … ; expect { "ok": true }`
skills/deepseek-prompt/SKILL.md · 516 lines

How it starts

The opening of the file, as written. The whole thing — 516 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeepSeek Prompt Skill

Overview

Build prompts that play to DeepSeek V4's strengths and avoid its known failure modes: commentary instead of execution, roleplay-style thinking (internal monologue, parenthetical asides), mode collapse, and weak discipline injection.

This skill operates in two lanes (how you use it):

  • Interactive mode (prompt is for the end user in this session): run the interrogation in §3 — collect the info the user has, then fill the template.
  • Subagent / autonomous mode (prompt will be sent to a DeepSeek subagent or a fresh DeepSeek session): decide the content yourself from available context — do NOT interrogate the user. Use §4.

Separately, DeepSeek V4 itself has three thinking modes you can force by appending a Chinese instruction block — Default / Pure Analysis / Role Immersion. That is the prompt-injection mechanism this skill relies on; see Three thinking modes — when and whether to inject below.

Decide the mode from how the request is phrased:

  • "write me a prompt for DeepSeek to do X" / "I want to prompt DeepSeek to…" → interactive.
  • "launch a subagent to do X on DeepSeek" / "prepare a prompt for the DeepSeek agent" / the prompt is a parameter you pass to a Task/Agent call → subagent mode.

If the intent is ambiguous, ask one clarifying question: "Is this prompt for you to send into a DeepSeek session yourself, or should I write it as a subagent/Agent task prompt?" — then proceed.

When to Use

Trigger this skill whenever you are about to produce a prompt whose target runtime is a DeepSeek model (deepseek-v4-pro, deepseek-v4-flash in API or Expert Mode). Concretely:

  • The user asks you to "write / draft / compose a prompt for DeepSeek", "make a prompt for DeepSeek", "format this task for DeepSeek".
  • You are composing the prompt: argument of a task() / subagent call that will run on a DeepSeek model.
  • You are translating a vague user request into a clean DeepSeek task spec.

Do not trigger this skill for non-DeepSeek models. The injection block works on API + Expert Mode only; DeepSeek Web Quick Mode ignores it — don't promise its effect there.

Read the full file on GitHub · 516 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 516 lines · 84 tokens per session scan A d5bd7012a463

Subscribe to this mod's changes

deepseek-prompt is a skill published in the GitHub repository knopki/agent-skills (2 stars, last pushed 10d ago), licensed MIT. It adds 84 tokens to every session and 5,712 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

llm-app-patterns

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

davila7/claude-code-templates · 54 tokens

prompt-optimization

Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…

langwatch/langwatch · 105 tokens

enhance-prompt

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

google-labs-code/stitch-skills · 41 tokens

prompt-engineer

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…

Jeffallan/claude-skills · 93 tokens

seedance-vocab-en

This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.

Emily2040/seedance-2.0 · 61 tokens

ideogram4

Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…

digitalsamba/claude-code-video-toolkit · 99 tokens