pinme-llm

Name: pinme-llm
Author: glitternetwork

3.7kstars272forks

How to install pinme-llm?

glitternetwork/pinme/pinme-llm

$npx -y skills add glitternetwork/pinme --skill pinme-llm

Installs into the current project.

Summary

Use this skill when a PinMe project (Worker TypeScript) needs to call OpenRouter-backed LLM APIs, including models, chat/completions, streaming, or OpenRouter web search. Guides AI to generate correct Worker TS code.

Files · 1

View on GitHub

SKILL.md

1	# PinMe Worker OpenRouter API Integration
2
3	Guides how to call PinMe platform's OpenRouter proxy APIs in a PinMe Worker (TypeScript). Workers use the PinMe project API key; they never hold the real OpenRouter API key.
4
5	## Environment Variables
6
7	The following environment variables are automatically injected when the Worker is created — no manual configuration needed:
8
9	```typescript
10	// backend/src/worker.ts
11	export interface Env {
12	DB: D1Database;
13	API_KEY: string; // Project API Key from create_worker
14	PROJECT_NAME: string; // Actual project_name from create_worker; must match API_KEY
15	BASE_URL?: string; // Optional override for PinMe API base URL, defaults to https://pinme.cloud
16	}
17	```
18
19	> `API_KEY` authenticates the Worker to PinMe. `PROJECT_NAME` is required for `chat/completions` and must belong to the same project as `API_KEY`. When `BASE_URL` is not set, use `https://pinme.cloud`.
20
21	---
22
23	## Models API
24
25	Endpoint: `GET {BASE_URL}/api/v1/models`
26	Authentication: `X-API-Key` header (using `env.API_KEY`)
27	Request Body: none
28
29	Use this when the Worker needs to list available OpenRouter models. The response body, status, and headers are passed through from OpenRouter `/models`.
30
31	```typescript
32	async function listModels(env: Env): Promise<unknown> {
33	const baseUrl = env.BASE_URL ?? 'https://pinme.cloud';
34	const resp = await fetch(`${baseUrl}/api/v1/models`, {
35	headers: { 'X-API-Key': env.API_KEY },
36	});
37
38	if (!resp.ok) {
39	throw new Error(await extractPinmeOpenRouterError(resp));
40	}
41
42	return await resp.json();
43	}
44	```
45
46	---
47
48	## Chat Completions API
49
50	Endpoint: `POST {BASE_URL}/api/v1/chat/completions?project_name={project_name}`
51	Authentication: `X-API-Key` header (using `env.API_KEY`)
52	Request Body: OpenRouter chat/completions format, passed through as-is after a 1MB size check
53	Streaming: Supports SSE (`stream: true`)
54	Web Search: Supports OpenRouter `openrouter:web_search` server tool via the `tools` array
55
56	### Request Format
57
58	```json
59	{
60	"model": "openai/gpt-4o-mini",
61	"messages": [
62	{ "role": "system", "content": "You are a helpful assistant." },
63	{ "role": "user", "content": "Hello!" }
64	],
65	"stream": true
66	}
67	```
68
69	> Use `env.PROJECT_NAME` from `create_worker`; always URL-encode it in the query string. For available models, call `GET /api/v1/models` or refer to OpenRouter model IDs.
70
71	### OpenRouter Web Search
72
73	PinMe does not provide a raw search endpoint. To search the web, pass OpenRouter's `openrouter:web_search` server tool to `chat/completions`; the model decides whether and when to search.
74
75	Always set `max_results` and `max_total_results` to keep search volume and cost bounded.
76
77	```typescript
78	async function searchWithLLM(env: Env, query: string): Promise<string> {
79	const baseUrl = env.BASE_URL ?? 'https://pinme.cloud';
80	const resp = await fetch(
81	`${baseUrl}/api/v1/chat/completions?project_name=${encodeURIComponent(env.PROJECT_NAME)}`,
82	{
83	method: 'POST',
84	headers: {
85	'Content-Type': 'application/json',
86	'X-API-Key': env.API_KEY,
87	},
88	body: JSON.stringify({
89	model: 'openai/gpt-5.2',
90	messages: [{ role: 'user', content: query }],
91	tools: [
92	{
93	type: 'openrouter:web_search',
94	parameters: {
95	engine: 'auto',
96	max_results: 5,
97	max_total_results: 10,
98	},
99	},
100	],
101	}),
102	},
103	);
104
105	if (!resp.ok) {
106	throw new Error(await extractPinmeOpenRouterError(resp));
107	}
108
109	const data = await resp.json() as { choices: Array<{ message?: { content?: string } }> };
110	return data.choices[0]?.message?.content ?? '';
111	}
112	```
113
114	### Response Format
115
116	Successful requests return OpenRouter's raw response body.
117
118	Non-streaming Success (200):
119	```json
120	{
121	"id": "chatcmpl-...",
122	"choices": [{ "message": { "role": "assistant", "content": "Hello!" }, "finish_reason": "stop" }],
123	"usage": { "prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15 }
124	}
125	```
126
127	Streaming Success (200): SSE format
128	```
129	data: {"choices":[{"delta":{"content":"Hello"}}]}
130	data: {"choices":[{"delta":{"content":" there"}}]}
131	data: [DONE]
132	```
133
134	Errors:
135
136	\| HTTP Status \| Meaning \| data.error Example \|
137	\|-------------\|---------\|-------------------\|
138	\| 401 \| API Key missing, invalid, or mismatched with project_name \| `"X-API-Key header is required"` / `"Invalid API key"` / `"Invalid API key or project name"` \|
139	\| 400 \| project_name missing or OpenRouter key not configured \| `"project_name is required"` / `"LLM service not configured for this project"` \|
140	\| 403 \| LLM balance insufficient or disabled \| `"Insufficient balance, please recharge to continue using LLM service"` \|
141	\| 413 \| Request body exce

People who liked this also viewed

6 picks

Type

microsoft-foundryDeploy, evaluate, fine-tune, and manage Foundry agents end-to-end with azd: hosted agent scaffold/run/deploy, prompt agent create, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffoSkillsJul 2026476k1.3k
azure-deployExecute Azure deployments for ALREADY-PREPARED applications that have existing .azure/deployment-plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application SkillsJul 2026472k1.3k
azure-preparePrepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wSkillsJul 2026471k1.3k
azure-validate--- name: azure-validate description: "Pre-deployment validation for Azure readiness. Run deep checks on configuration, infrastructure (Bicep or Terraform), RBAC role assignments, managed identity pSkillsJul 2026471k1.3k
azure-aigatewayConfigure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbSkillsJul 2026470k1.3k
azure-hosted-copilot-sdkOfficial agent plugin providing skills and MCP server configurations for Azure scenarios.SkillsJul 2026424k1.3k

pinme-llm

3.7kstars272forks

View on GitHub

How to install pinme-llm?

glitternetwork/pinme/pinme-llm

$npx -y skills add glitternetwork/pinme --skill pinme-llm

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# PinMe Worker OpenRouter API Integration
2
3	Guides how to call PinMe platform's OpenRouter proxy APIs in a PinMe Worker (TypeScript). Workers use the PinMe project API key; they never hold the real OpenRouter API key.
4
5	## Environment Variables
6
7	The following environment variables are automatically injected when the Worker is created — no manual configuration needed:
8
9	```typescript
10	// backend/src/worker.ts
11	export interface Env {
12	DB: D1Database;
13	API_KEY: string; // Project API Key from create_worker
14	PROJECT_NAME: string; // Actual project_name from create_worker; must match API_KEY
15	BASE_URL?: string; // Optional override for PinMe API base URL, defaults to https://pinme.cloud
16	}
17	```
18
19	> `API_KEY` authenticates the Worker to PinMe. `PROJECT_NAME` is required for `chat/completions` and must belong to the same project as `API_KEY`. When `BASE_URL` is not set, use `https://pinme.cloud`.
20
21	---
22
23	## Models API
24
25	Endpoint: `GET {BASE_URL}/api/v1/models`
26	Authentication: `X-API-Key` header (using `env.API_KEY`)
27	Request Body: none
28
29	Use this when the Worker needs to list available OpenRouter models. The response body, status, and headers are passed through from OpenRouter `/models`.
30
31	```typescript
32	async function listModels(env: Env): Promise<unknown> {
33	const baseUrl = env.BASE_URL ?? 'https://pinme.cloud';
34	const resp = await fetch(`${baseUrl}/api/v1/models`, {
35	headers: { 'X-API-Key': env.API_KEY },
36	});
37
38	if (!resp.ok) {
39	throw new Error(await extractPinmeOpenRouterError(resp));
40	}
41
42	return await resp.json();
43	}
44	```
45
46	---
47
48	## Chat Completions API
49
50	Endpoint: `POST {BASE_URL}/api/v1/chat/completions?project_name={project_name}`
51	Authentication: `X-API-Key` header (using `env.API_KEY`)
52	Request Body: OpenRouter chat/completions format, passed through as-is after a 1MB size check
53	Streaming: Supports SSE (`stream: true`)
54	Web Search: Supports OpenRouter `openrouter:web_search` server tool via the `tools` array
55
56	### Request Format
57
58	```json
59	{
60	"model": "openai/gpt-4o-mini",
61	"messages": [
62	{ "role": "system", "content": "You are a helpful assistant." },
63	{ "role": "user", "content": "Hello!" }
64	],
65	"stream": true
66	}
67	```
68
69	> Use `env.PROJECT_NAME` from `create_worker`; always URL-encode it in the query string. For available models, call `GET /api/v1/models` or refer to OpenRouter model IDs.
70
71	### OpenRouter Web Search
72
73	PinMe does not provide a raw search endpoint. To search the web, pass OpenRouter's `openrouter:web_search` server tool to `chat/completions`; the model decides whether and when to search.
74
75	Always set `max_results` and `max_total_results` to keep search volume and cost bounded.
76
77	```typescript
78	async function searchWithLLM(env: Env, query: string): Promise<string> {
79	const baseUrl = env.BASE_URL ?? 'https://pinme.cloud';
80	const resp = await fetch(
81	`${baseUrl}/api/v1/chat/completions?project_name=${encodeURIComponent(env.PROJECT_NAME)}`,
82	{
83	method: 'POST',
84	headers: {
85	'Content-Type': 'application/json',
86	'X-API-Key': env.API_KEY,
87	},
88	body: JSON.stringify({
89	model: 'openai/gpt-5.2',
90	messages: [{ role: 'user', content: query }],
91	tools: [
92	{
93	type: 'openrouter:web_search',
94	parameters: {
95	engine: 'auto',
96	max_results: 5,
97	max_total_results: 10,
98	},
99	},
100	],
101	}),
102	},
103	);
104
105	if (!resp.ok) {
106	throw new Error(await extractPinmeOpenRouterError(resp));
107	}
108
109	const data = await resp.json() as { choices: Array<{ message?: { content?: string } }> };
110	return data.choices[0]?.message?.content ?? '';
111	}
112	```
113
114	### Response Format
115
116	Successful requests return OpenRouter's raw response body.
117
118	Non-streaming Success (200):
119	```json
120	{
121	"id": "chatcmpl-...",
122	"choices": [{ "message": { "role": "assistant", "content": "Hello!" }, "finish_reason": "stop" }],
123	"usage": { "prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15 }
124	}
125	```
126
127	Streaming Success (200): SSE format
128	```
129	data: {"choices":[{"delta":{"content":"Hello"}}]}
130	data: {"choices":[{"delta":{"content":" there"}}]}
131	data: [DONE]
132	```
133
134	Errors:
135
136	\| HTTP Status \| Meaning \| data.error Example \|
137	\|-------------\|---------\|-------------------\|
138	\| 401 \| API Key missing, invalid, or mismatched with project_name \| `"X-API-Key header is required"` / `"Invalid API key"` / `"Invalid API key or project name"` \|
139	\| 400 \| project_name missing or OpenRouter key not configured \| `"project_name is required"` / `"LLM service not configured for this project"` \|
140	\| 403 \| LLM balance insufficient or disabled \| `"Insufficient balance, please recharge to continue using LLM service"` \|
141	\| 413 \| Request body exce

People who liked this also viewed

6 picks

Type