qwencloud-model-selector

Name: qwencloud-model-selector
Author: QwenCloud

32stars0forks

How to install qwencloud-model-selector?

qwencloud/qwencloud-ai/qwencloud-model-selector

$npx -y skills add QwenCloud/qwencloud-ai --skill qwencloud-model-selector

Installs into the current project.

Summary

[QwenCloud] Recommend the best Qwen model and parameters. TRIGGER when: choosing between Qwen models, comparing Qwen model pricing, understanding Qwen model capabilities, checking usage or billing, viewing cost history, when an execution skill needs model selection advice, or use

Files · 1

View on GitHub

SKILL.md

1	> Agent setup: If your agent doesn't auto-load skills (e.g. Claude Code),
2	> see [agent-compatibility.md](references/agent-compatibility.md) once per session.
3
4	# Qwen Model Selector (Advisor)
5
6	This skill operates in two modes:
7
8	1. Interactive advisory — asks diagnostic questions to recommend the right model (see Diagnostic Flow).
9	2. Cross-skill resolution — provides a fast-path model lookup for execution skills that need a model
10	decision without user interaction (see [recommendation-matrix.md](references/recommendation-matrix.md)).
11
12	Do not fabricate model names — only recommend models listed in this skill or returned by CLI.
13	This skill is part of qwencloud/qwencloud-ai.
14
15	## Skill directory
16
17	Load on demand. Do not fetch external URLs unless the user explicitly asks for the latest data.
18
19	\| Location \| Purpose \|
20	\|-------------------------------------------\|----------------------------------------------------------------------------------\|
21	\| `references/cli-usage.md` \| CLI-first data strategy: when to use CLI, 3-step login flow, display rules \|
22	\| `references/error-handling.md` \| CLI error classification & recovery actions (auth, not-found, network, ...) \|
23	\| `references/recommendation-matrix.md` \| Full model recommendation tables, Cross-Skill Resolution, Coding Plan, Thinking \|
24	\| `references/pricing-disclaimer.md` \| Pricing guidance + mandatory cost-estimation disclaimer (CN/EN) + console links \|
25	\| `references/pricing.md` \| Pricing structural overview (offline snapshot) \|
26	\| `references/model-list.md` \| Model catalog (offline snapshot) \|
27	\| `references/sources.md` \| Official documentation URLs (manual lookup only) \|
28	\| `references/agent-compatibility.md` \| Agent self-check for skill registration \|
29
30	## Prerequisites
31
32	QwenCloud CLI is strongly recommended — it is the authoritative real-time data source for model
33	availability, pricing, and quotas. Verify with:
34
35	```bash
36	qwencloud version
37	```
38
39	If not installed:
40
41	```bash
42	npm install -g @qwencloud/qwencloud-cli
43	```
44
45	Node.js >= 18 required. Without CLI you can still answer general navigation questions from offline
46	snapshots, but you cannot answer "latest", "exact price", or "specific model details" questions.
47
48	## Security & Credential Model
49
50	QwenCloud has two independent credential systems — never confuse them:
51
52	\| Credential \| Purpose \| How to provide \|
53	\|------------\|---------\|----------------\|
54	\| API Key (`sk-...` / `sk-sp-...`) \| Call model APIs in your code \| `$DASHSCOPE_API_KEY` / `$QWEN_API_KEY` env var \|
55	\| CLI session \| Authorize `qwencloud` CLI subcommands \| `qwencloud auth login` (browser device flow) \|
56
57	Red lines (apply to both):
58
59	- NEVER output any credential value in plaintext. Use variable references; report only status
60	("set" / "not set", "valid" / "invalid"). Never display `.env` or config file contents.
61	- NEVER conflate the two systems. When CLI returns `Not authenticated` / `AUTH_REQUIRED`, run the
62	3-step device-flow login (see [cli-usage.md](references/cli-usage.md#authentication-3-step-login-flow)).
63	DO NOT ask the user for an API key, and DO NOT try to set `$DASHSCOPE_API_KEY` to fix CLI auth.
64
65	## Data Resolution Order
66
67	Match the user's question to the right data source. **Do not fall back to a lower tier without trying
68	the recovery actions in the higher tier first.**
69
70	\| Question type \| Primary source \| Notes \|
71	\|----------------------------------------------------------------\|---------------------------------------------------------\|------------------------------------------------------\|
72	\| General navigation ("which family for text chat?") \| SKILL.md `Default` table + `recommendation-matrix.md` \| Offline-answerable \|
73	\| Latest / exact / specific (price, model details, quota) \| **CLI MUST be u

People who liked this also viewed

6 picks

Type

qwencloud-model-selector

32stars0forks

View on GitHub

How to install qwencloud-model-selector?

qwencloud/qwencloud-ai/qwencloud-model-selector

$npx -y skills add QwenCloud/qwencloud-ai --skill qwencloud-model-selector

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	> Agent setup: If your agent doesn't auto-load skills (e.g. Claude Code),
2	> see [agent-compatibility.md](references/agent-compatibility.md) once per session.
3
4	# Qwen Model Selector (Advisor)
5
6	This skill operates in two modes:
7
8	1. Interactive advisory — asks diagnostic questions to recommend the right model (see Diagnostic Flow).
9	2. Cross-skill resolution — provides a fast-path model lookup for execution skills that need a model
10	decision without user interaction (see [recommendation-matrix.md](references/recommendation-matrix.md)).
11
12	Do not fabricate model names — only recommend models listed in this skill or returned by CLI.
13	This skill is part of qwencloud/qwencloud-ai.
14
15	## Skill directory
16
17	Load on demand. Do not fetch external URLs unless the user explicitly asks for the latest data.
18
19	\| Location \| Purpose \|
20	\|-------------------------------------------\|----------------------------------------------------------------------------------\|
21	\| `references/cli-usage.md` \| CLI-first data strategy: when to use CLI, 3-step login flow, display rules \|
22	\| `references/error-handling.md` \| CLI error classification & recovery actions (auth, not-found, network, ...) \|
23	\| `references/recommendation-matrix.md` \| Full model recommendation tables, Cross-Skill Resolution, Coding Plan, Thinking \|
24	\| `references/pricing-disclaimer.md` \| Pricing guidance + mandatory cost-estimation disclaimer (CN/EN) + console links \|
25	\| `references/pricing.md` \| Pricing structural overview (offline snapshot) \|
26	\| `references/model-list.md` \| Model catalog (offline snapshot) \|
27	\| `references/sources.md` \| Official documentation URLs (manual lookup only) \|
28	\| `references/agent-compatibility.md` \| Agent self-check for skill registration \|
29
30	## Prerequisites
31
32	QwenCloud CLI is strongly recommended — it is the authoritative real-time data source for model
33	availability, pricing, and quotas. Verify with:
34
35	```bash
36	qwencloud version
37	```
38
39	If not installed:
40
41	```bash
42	npm install -g @qwencloud/qwencloud-cli
43	```
44
45	Node.js >= 18 required. Without CLI you can still answer general navigation questions from offline
46	snapshots, but you cannot answer "latest", "exact price", or "specific model details" questions.
47
48	## Security & Credential Model
49
50	QwenCloud has two independent credential systems — never confuse them:
51
52	\| Credential \| Purpose \| How to provide \|
53	\|------------\|---------\|----------------\|
54	\| API Key (`sk-...` / `sk-sp-...`) \| Call model APIs in your code \| `$DASHSCOPE_API_KEY` / `$QWEN_API_KEY` env var \|
55	\| CLI session \| Authorize `qwencloud` CLI subcommands \| `qwencloud auth login` (browser device flow) \|
56
57	Red lines (apply to both):
58
59	- NEVER output any credential value in plaintext. Use variable references; report only status
60	("set" / "not set", "valid" / "invalid"). Never display `.env` or config file contents.
61	- NEVER conflate the two systems. When CLI returns `Not authenticated` / `AUTH_REQUIRED`, run the
62	3-step device-flow login (see [cli-usage.md](references/cli-usage.md#authentication-3-step-login-flow)).
63	DO NOT ask the user for an API key, and DO NOT try to set `$DASHSCOPE_API_KEY` to fix CLI auth.
64
65	## Data Resolution Order
66
67	Match the user's question to the right data source. **Do not fall back to a lower tier without trying
68	the recovery actions in the higher tier first.**
69
70	\| Question type \| Primary source \| Notes \|
71	\|----------------------------------------------------------------\|---------------------------------------------------------\|------------------------------------------------------\|
72	\| General navigation ("which family for text chat?") \| SKILL.md `Default` table + `recommendation-matrix.md` \| Offline-answerable \|
73	\| Latest / exact / specific (price, model details, quota) \| **CLI MUST be u

People who liked this also viewed

6 picks

Type