ai-agent-builder

Name: ai-agent-builder
Author: claude-office-skills

319stars70forks

How to install ai-agent-builder?

claude-office-skills/skills/ai-agent-builder

$npx -y skills add claude-office-skills/skills --skill ai-agent-builder

Installs into the current project.

Summary

Build AI agents with tools, memory, and multi-step reasoning - ChatGPT, Claude, Gemini integration patterns

Files · 1

View on GitHub

SKILL.md

1	# AI Agent Builder
2
3	Design and build AI agents with tools, memory, and multi-step reasoning capabilities. Covers ChatGPT, Claude, Gemini integration patterns based on n8n's 5,000+ AI workflow templates.
4
5	## Overview
6
7	This skill covers:
8	- AI agent architecture design
9	- Tool/function calling patterns
10	- Memory and context management
11	- Multi-step reasoning workflows
12	- Platform integrations (Slack, Telegram, Web)
13
14	---
15
16	## AI Agent Architecture
17
18	### Core Components
19
20	```
21	┌─────────────────────────────────────────────────────────────────┐
22	│ AI AGENT ARCHITECTURE │
23	├─────────────────────────────────────────────────────────────────┤
24	│ │
25	│ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │
26	│ │ Input │────▶│ Agent │────▶│ Output │ │
27	│ │ (Query) │ │ (LLM) │ │ (Response) │ │
28	│ └─────────────┘ └──────┬──────┘ └─────────────┘ │
29	│ │ │
30	│ ┌───────────────────┼───────────────────┐ │
31	│ │ │ │ │
32	│ ▼ ▼ ▼ │
33	│ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │
34	│ │ Tools │ │ Memory │ │ Knowledge │ │
35	│ │ (Functions) │ │ (Context) │ │ (RAG) │ │
36	│ └─────────────┘ └─────────────┘ └─────────────┘ │
37	│ │
38	└─────────────────────────────────────────────────────────────────┘
39	```
40
41	### Agent Types
42
43	```yaml
44	agent_types:
45	reactive_agent:
46	description: "Single-turn response, no memory"
47	use_case: simple_qa, classification
48	complexity: low
49
50	conversational_agent:
51	description: "Multi-turn with conversation memory"
52	use_case: chatbots, support
53	complexity: medium
54
55	tool_using_agent:
56	description: "Can call external tools/APIs"
57	use_case: data_lookup, actions
58	complexity: medium
59
60	reasoning_agent:
61	description: "Multi-step planning and execution"
62	use_case: complex_tasks, research
63	complexity: high
64
65	multi_agent:
66	description: "Multiple specialized agents collaborating"
67	use_case: complex_workflows
68	complexity: very_high
69	```
70
71	---
72
73	## Tool Calling Pattern
74
75	### Tool Definition
76
77	```yaml
78	tool_definition:
79	name: "get_weather"
80	description: "Get current weather for a location"
81	parameters:
82	type: object
83	properties:
84	location:
85	type: string
86	description: "City name or coordinates"
87	units:
88	type: string
89	enum: ["celsius", "fahrenheit"]
90	default: "celsius"
91	required: ["location"]
92
93	implementation:
94	type: api_call
95	endpoint: "https://api.weather.com/v1/current"
96	method: GET
97	params:
98	q: "{location}"
99	units: "{units}"
100	```
101
102	### Common Tool Categories
103
104	```yaml
105	tool_categories:
106	data_retrieval:
107	- web_search: search the internet
108	- database_query: query SQL/NoSQL
109	- api_lookup: call external APIs
110	- file_read: read documents
111
112	actions:
113	- send_email: send emails
114	- create_calendar: schedule events
115	- update_crm: modify CRM records
116	- post_slack: send Slack messages
117
118	computation:
119	- calculator: math operations
120	- code_interpreter: run Python
121	- data_analysis: analyze datasets
122
123	generation:
124	- image_generation: create images
125	- document_creation: generate docs
126	- chart_creation: create visualizations
127	```
128
129	### n8n Tool Integration
130
131	```yaml
132	n8n_agent_workflow:
133	nodes:
134	- trigger:
135	type: webhook
136	path: "/ai-agent"
137
138	- ai_agent:
139	type: "@n8n/n8n-nodes-langchain.agent"
140	model: openai_gpt4
141	system_prompt: \|
142	You are a helpful assistant that can:
143	1. Search the web for information
144	2. Query our customer database
145	3. Send emails on behalf of the user
146
147	tools:
148	- web_search
149	- database_query
150	- send_email
151
152	- respond:
153	type: respond_to_webhook
154	data: "{{ $json.output }}"
155	```
156
157	---
158
159	## Memory Patterns
160
161	### Memory Types
162
163	```yaml
164	memory_types:
165	buffer_memory:
166	description: "Store last N messages"
167	im

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

ai-agent-builder

319stars70forks

View on GitHub

How to install ai-agent-builder?

claude-office-skills/skills/ai-agent-builder

$npx -y skills add claude-office-skills/skills --skill ai-agent-builder

Installs into the current project.

Summary

Build AI agents with tools, memory, and multi-step reasoning - ChatGPT, Claude, Gemini integration patterns

Files · 1

View on GitHub

SKILL.md

1	# AI Agent Builder
2
3	Design and build AI agents with tools, memory, and multi-step reasoning capabilities. Covers ChatGPT, Claude, Gemini integration patterns based on n8n's 5,000+ AI workflow templates.
4
5	## Overview
6
7	This skill covers:
8	- AI agent architecture design
9	- Tool/function calling patterns
10	- Memory and context management
11	- Multi-step reasoning workflows
12	- Platform integrations (Slack, Telegram, Web)
13
14	---
15
16	## AI Agent Architecture
17
18	### Core Components
19
20	```
21	┌─────────────────────────────────────────────────────────────────┐
22	│ AI AGENT ARCHITECTURE │
23	├─────────────────────────────────────────────────────────────────┤
24	│ │
25	│ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │
26	│ │ Input │────▶│ Agent │────▶│ Output │ │
27	│ │ (Query) │ │ (LLM) │ │ (Response) │ │
28	│ └─────────────┘ └──────┬──────┘ └─────────────┘ │
29	│ │ │
30	│ ┌───────────────────┼───────────────────┐ │
31	│ │ │ │ │
32	│ ▼ ▼ ▼ │
33	│ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │
34	│ │ Tools │ │ Memory │ │ Knowledge │ │
35	│ │ (Functions) │ │ (Context) │ │ (RAG) │ │
36	│ └─────────────┘ └─────────────┘ └─────────────┘ │
37	│ │
38	└─────────────────────────────────────────────────────────────────┘
39	```
40
41	### Agent Types
42
43	```yaml
44	agent_types:
45	reactive_agent:
46	description: "Single-turn response, no memory"
47	use_case: simple_qa, classification
48	complexity: low
49
50	conversational_agent:
51	description: "Multi-turn with conversation memory"
52	use_case: chatbots, support
53	complexity: medium
54
55	tool_using_agent:
56	description: "Can call external tools/APIs"
57	use_case: data_lookup, actions
58	complexity: medium
59
60	reasoning_agent:
61	description: "Multi-step planning and execution"
62	use_case: complex_tasks, research
63	complexity: high
64
65	multi_agent:
66	description: "Multiple specialized agents collaborating"
67	use_case: complex_workflows
68	complexity: very_high
69	```
70
71	---
72
73	## Tool Calling Pattern
74
75	### Tool Definition
76
77	```yaml
78	tool_definition:
79	name: "get_weather"
80	description: "Get current weather for a location"
81	parameters:
82	type: object
83	properties:
84	location:
85	type: string
86	description: "City name or coordinates"
87	units:
88	type: string
89	enum: ["celsius", "fahrenheit"]
90	default: "celsius"
91	required: ["location"]
92
93	implementation:
94	type: api_call
95	endpoint: "https://api.weather.com/v1/current"
96	method: GET
97	params:
98	q: "{location}"
99	units: "{units}"
100	```
101
102	### Common Tool Categories
103
104	```yaml
105	tool_categories:
106	data_retrieval:
107	- web_search: search the internet
108	- database_query: query SQL/NoSQL
109	- api_lookup: call external APIs
110	- file_read: read documents
111
112	actions:
113	- send_email: send emails
114	- create_calendar: schedule events
115	- update_crm: modify CRM records
116	- post_slack: send Slack messages
117
118	computation:
119	- calculator: math operations
120	- code_interpreter: run Python
121	- data_analysis: analyze datasets
122
123	generation:
124	- image_generation: create images
125	- document_creation: generate docs
126	- chart_creation: create visualizations
127	```
128
129	### n8n Tool Integration
130
131	```yaml
132	n8n_agent_workflow:
133	nodes:
134	- trigger:
135	type: webhook
136	path: "/ai-agent"
137
138	- ai_agent:
139	type: "@n8n/n8n-nodes-langchain.agent"
140	model: openai_gpt4
141	system_prompt: \|
142	You are a helpful assistant that can:
143	1. Search the web for information
144	2. Query our customer database
145	3. Send emails on behalf of the user
146
147	tools:
148	- web_search
149	- database_query
150	- send_email
151
152	- respond:
153	type: respond_to_webhook
154	data: "{{ $json.output }}"
155	```
156
157	---
158
159	## Memory Patterns
160
161	### Memory Types
162
163	```yaml
164	memory_types:
165	buffer_memory:
166	description: "Store last N messages"
167	im

People who liked this also viewed

6 picks

Type