system-prompt-creator

Name: system-prompt-creator
Author: tronghieu

37stars20forks

How to install system-prompt-creator?

tronghieu/agent-skills/system-prompt-creator

$npx -y skills add tronghieu/agent-skills --skill system-prompt-creator

Installs into the current project.

Summary

Create high-quality, model-aware system prompts for any LLM (Claude, GPT, Gemini, open-source, etc.). Use this skill whenever the user wants to create, write, build, design, draft, or improve a system prompt, system instructions, or custom instructions for any AI model. Also trig

Files · 1

View on GitHub

SKILL.md

1	# System Prompt Creator
2
3	Build effective system prompts for any LLM using a structured, research-backed process derived from the official prompting guides of Claude (Anthropic), GPT-5 (OpenAI), and Gemini (Google).
4
5	This skill guides you through interview, analysis, structuring, drafting, and optimization — producing system prompts that are clear, well-structured, and tailored to the target model.
6
7	## Workflow
8
9	Follow these 5 steps in order. Each step builds on the previous.
10
11	### Step 1: Interview — Gather Requirements
12
13	Before writing anything, collect these essentials from the user:
14
15	1. Target model — Which LLM? (Claude, GPT, Gemini, open-source, or model-agnostic)
16	2. Use case — What will the AI do? (chatbot, agent, content generator, data extractor, code assistant, etc.)
17	3. Persona — Who should the AI be? (role, expertise level, personality traits)
18	4. Audience — Who interacts with it? (developers, end users, internal team, customers)
19	5. Input types — What will users send? (free text, code, documents, images, structured data)
20	6. Output format — What should responses look like? (prose, JSON, markdown, code, tables)
21	7. Tone & style — Formal, casual, technical, friendly? Concise or detailed?
22	8. Constraints — What must it NOT do? (safety rules, topic limits, action restrictions)
23	9. Tools & capabilities — Does it have tool access? (APIs, file system, web search, code execution)
24	10. Examples — Can the user provide examples of good/bad responses?
25
26	If the user is vague on some points, suggest reasonable defaults and confirm before proceeding.
27
28	Push for completeness: After gathering basics, ask "What else might users ask about?" Many prompts fail not because they handle their core task poorly, but because they don't anticipate adjacent scenarios. A billing chatbot also gets account access questions, product questions, and complaints. A coding agent needs to handle not just building features but also debugging, refactoring, and project setup. Map the full territory before writing.
29
30	### Step 2: Analyze — Determine Complexity & Scope
31
32	Based on the interview, classify the prompt complexity:
33
34	\| Complexity \| Characteristics \| Typical Length \|
35	\|-----------\|----------------\|---------------\|
36	\| Simple \| Single task, no tools, fixed format \| 50-200 words \|
37	\| Moderate \| Multiple behaviors, some tools, varied outputs \| 200-800 words \|
38	\| Complex \| Agentic, multi-tool, long-running, safety-critical \| 800-2000+ words \|
39
40	Then determine which sections are needed:
41
42	- Role/Persona — Almost always needed
43	- Context/Knowledge — When domain expertise or background is required
44	- Instructions/Rules — Always needed
45	- Domain Playbooks — When the system handles multiple distinct operational scenarios (see below)
46	- Output Format — When response structure matters
47	- Examples — When accuracy and consistency matter (3-5 diverse examples)
48	- Tool Usage — When the model has access to tools or APIs
49	- Safety/Guardrails — When actions have real-world consequences
50	- Agentic Behavior — When the model operates autonomously
51
52	Domain Playbooks: For systems that handle multiple distinct workflows (a coding agent that builds, debugs, refactors, and reviews; a support bot that handles billing, accounts, and technical issues), include named playbooks — concise step-by-step patterns for each operational scenario. These give the model a reliable decision tree for common situations rather than forcing it to derive the approach from general instructions every time. Place playbooks inside the `<instructions>` section, organized by scenario name.
53
54	### Step 3: Structure — Apply the Layered Architecture
55
56	Organize the prompt using this universal architecture. Include only the sections relevant to the use case.
57
58	XML structure (preferred for complex prompts):
59
60	```xml
61	<role>
62	Who the AI is, expertise, personality
63	</role>
64
65	<context>
66	Domain knowledge, background information, constraints
67	</context>
68
69	<instructions>
70	Core behavior rules, workflow steps, decision criteria
71	</instructions>
72
73	<output_format>
74	Response structure, formatting rules, verbosity guidelines
75	</output_format>
76
77	<examples>
78	3-5 diverse input/output pairs covering normal cases and edge cases
79	</ex

People who liked this also viewed

6 picks

Type

system-prompt-creator

37stars20forks

View on GitHub

How to install system-prompt-creator?

tronghieu/agent-skills/system-prompt-creator

$npx -y skills add tronghieu/agent-skills --skill system-prompt-creator

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# System Prompt Creator
2
3	Build effective system prompts for any LLM using a structured, research-backed process derived from the official prompting guides of Claude (Anthropic), GPT-5 (OpenAI), and Gemini (Google).
4
5	This skill guides you through interview, analysis, structuring, drafting, and optimization — producing system prompts that are clear, well-structured, and tailored to the target model.
6
7	## Workflow
8
9	Follow these 5 steps in order. Each step builds on the previous.
10
11	### Step 1: Interview — Gather Requirements
12
13	Before writing anything, collect these essentials from the user:
14
15	1. Target model — Which LLM? (Claude, GPT, Gemini, open-source, or model-agnostic)
16	2. Use case — What will the AI do? (chatbot, agent, content generator, data extractor, code assistant, etc.)
17	3. Persona — Who should the AI be? (role, expertise level, personality traits)
18	4. Audience — Who interacts with it? (developers, end users, internal team, customers)
19	5. Input types — What will users send? (free text, code, documents, images, structured data)
20	6. Output format — What should responses look like? (prose, JSON, markdown, code, tables)
21	7. Tone & style — Formal, casual, technical, friendly? Concise or detailed?
22	8. Constraints — What must it NOT do? (safety rules, topic limits, action restrictions)
23	9. Tools & capabilities — Does it have tool access? (APIs, file system, web search, code execution)
24	10. Examples — Can the user provide examples of good/bad responses?
25
26	If the user is vague on some points, suggest reasonable defaults and confirm before proceeding.
27
28	Push for completeness: After gathering basics, ask "What else might users ask about?" Many prompts fail not because they handle their core task poorly, but because they don't anticipate adjacent scenarios. A billing chatbot also gets account access questions, product questions, and complaints. A coding agent needs to handle not just building features but also debugging, refactoring, and project setup. Map the full territory before writing.
29
30	### Step 2: Analyze — Determine Complexity & Scope
31
32	Based on the interview, classify the prompt complexity:
33
34	\| Complexity \| Characteristics \| Typical Length \|
35	\|-----------\|----------------\|---------------\|
36	\| Simple \| Single task, no tools, fixed format \| 50-200 words \|
37	\| Moderate \| Multiple behaviors, some tools, varied outputs \| 200-800 words \|
38	\| Complex \| Agentic, multi-tool, long-running, safety-critical \| 800-2000+ words \|
39
40	Then determine which sections are needed:
41
42	- Role/Persona — Almost always needed
43	- Context/Knowledge — When domain expertise or background is required
44	- Instructions/Rules — Always needed
45	- Domain Playbooks — When the system handles multiple distinct operational scenarios (see below)
46	- Output Format — When response structure matters
47	- Examples — When accuracy and consistency matter (3-5 diverse examples)
48	- Tool Usage — When the model has access to tools or APIs
49	- Safety/Guardrails — When actions have real-world consequences
50	- Agentic Behavior — When the model operates autonomously
51
52	Domain Playbooks: For systems that handle multiple distinct workflows (a coding agent that builds, debugs, refactors, and reviews; a support bot that handles billing, accounts, and technical issues), include named playbooks — concise step-by-step patterns for each operational scenario. These give the model a reliable decision tree for common situations rather than forcing it to derive the approach from general instructions every time. Place playbooks inside the `<instructions>` section, organized by scenario name.
53
54	### Step 3: Structure — Apply the Layered Architecture
55
56	Organize the prompt using this universal architecture. Include only the sections relevant to the use case.
57
58	XML structure (preferred for complex prompts):
59
60	```xml
61	<role>
62	Who the AI is, expertise, personality
63	</role>
64
65	<context>
66	Domain knowledge, background information, constraints
67	</context>
68
69	<instructions>
70	Core behavior rules, workflow steps, decision criteria
71	</instructions>
72
73	<output_format>
74	Response structure, formatting rules, verbosity guidelines
75	</output_format>
76
77	<examples>
78	3-5 diverse input/output pairs covering normal cases and edge cases
79	</ex

People who liked this also viewed

6 picks

Type