grok-search

Name: grok-search
Author: Dianel555

23installs6forks

How to install grok-search?

dianel555/dskills/grok-search

$npx -y skills add Dianel555/DSkills --skill grok-search

Installs into the current project.

Summary

Enhanced web search and real-time content retrieval via Grok API with forced tool routing. Use when: (1) Web search / information retrieval / fact-checking, (2) Webpage content extraction / URL parsing, (3) Breaking knowledge cutoff limits for current information, (4) Real-time n

Files · 1

View on GitHub

SKILL.md

1	# Grok Search
2
3	Enhanced web search via Grok API. Standalone CLI only (no MCP dependency).
4
5	## Implementation Layout
6
7	- `scripts/groksearch_cli.py` - CLI entrypoint and compatibility facade
8	- `scripts/groksearch/` - internal modules for config, HTTP retry, Grok provider, Tavily calls, formatting, and commands
9
10	## Execution Methods
11
12	Run `scripts/groksearch_cli.py` via Bash:
13
14	```bash
15	# Prerequisites: pip install httpx tenacity
16	# Environment: GROK_API_URL, GROK_API_KEY (required); TAVILY_API_KEY (optional)
17
18	# Web search (Grok only)
19	python scripts/groksearch_cli.py web_search --query "search terms" [--platform "GitHub"] [--min-results 3] [--max-results 10]
20
21	# Web search with Tavily extra sources (parallel + URL-deduplicated merge)
22	python scripts/groksearch_cli.py web_search --query "..." --extra-sources 5
23
24	# Fetch webpage (default: Grok)
25	python scripts/groksearch_cli.py web_fetch --url "https://..." [--out file.md]
26
27	# Fetch via Tavily extract endpoint
28	python scripts/groksearch_cli.py web_fetch --url "https://..." --via tavily
29
30	# Map a website's structure (Tavily)
31	python scripts/groksearch_cli.py web_map --url "https://docs.example.com" [--instructions "API only"] [--max-depth 2] [--max-breadth 20] [--limit 50] [--timeout 150]
32
33	# Check config
34	python scripts/groksearch_cli.py get_config_info [--no-test]
35
36	# Switch model
37	python scripts/groksearch_cli.py switch_model --model "grok-2-latest"
38
39	# Toggle built-in tools
40	python scripts/groksearch_cli.py toggle_builtin_tools --action on\|off\|status [--root /path/to/project]
41	```
42
43	## Tool Routing Policy
44
45	### Forced Replacement Rules
46
47	\| Scenario \| Disabled \| Force Use \|
48	\|----------\|----------\|-----------\|
49	\| Web Search \| `WebSearch` \| CLI `web_search` \|
50	\| Web Fetch \| `WebFetch` \| CLI `web_fetch` \|
51
52	### Tool Capability Matrix
53
54	\| Tool \| Parameters \| Output \|
55	\|------\|------------\|--------\|
56	\| `web_search` \| `query`(required), `platform`/`min_results`/`max_results`(optional), `extra_sources`(int, 0=disabled) \| `[{title,url,description,provider?}]` \|
57	\| `web_fetch` \| `url`(required), `out`(optional), `via`(grok\\|tavily, default grok) \| Structured Markdown \|
58	\| `web_map` \| `url`(required), `instructions`/`max_depth`/`max_breadth`/`limit`/`timeout`(optional) \| `{base_url,results,response_time}` JSON \|
59	\| `get_config_info` \| `no_test`(optional) \| `{api_url,status,connection_test,tavily_*}` \|
60	\| `switch_model` \| `model`(required) \| `{previous_model,current_model}` \|
61	\| `toggle_builtin_tools` \| `action`(on/off/status), `root`(optional) \| `{blocked,deny_list}` \|
62
63	## Search Workflow
64
65	### Phase 1: Query Construction
66	- Intent Recognition: Broad search → `web_search` \| Deep retrieval → `web_fetch`
67	- Parameter Optimization: Set `platform` for specific sources, adjust result counts
68
69	### Phase 2: Search Execution
70	1. Start with `web_search` for structured summaries
71	2. Use `web_fetch` on key URLs if summaries insufficient
72	3. Retry with adjusted query if first round unsatisfactory
73
74	### Phase 3: Result Synthesis
75	1. Cross-reference multiple sources
76	2. Must annotate source and date for time-sensitive info
77	3. Must include source URLs: `Title [<sup>1</sup>](URL)`
78
79	## Error Handling
80
81	\| Error \| Recovery \|
82	\|-------\|----------\|
83	\| Connection Failure \| Run `get_config_info`, verify API URL/Key \|
84	\| No Results \| Broaden search terms \|
85	\| Fetch Timeout \| Try alternative sources \|
86
87	## Anti-Patterns
88
89	\| Prohibited \| Correct \|
90	\|------------\|---------\|
91	\| No source citation \| Include `Source [<sup>1</sup>](URL)` \|
92	\| Give up after one failure \| Retry at least once \|
93	\| Use built-in WebSearch/WebFetch \| Use GrokSearch tools/CLI \|

People who liked this also viewed

6 picks

Type

grok-search

23installs6forks

View on GitHub

How to install grok-search?

dianel555/dskills/grok-search

$npx -y skills add Dianel555/DSkills --skill grok-search

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Grok Search
2
3	Enhanced web search via Grok API. Standalone CLI only (no MCP dependency).
4
5	## Implementation Layout
6
7	- `scripts/groksearch_cli.py` - CLI entrypoint and compatibility facade
8	- `scripts/groksearch/` - internal modules for config, HTTP retry, Grok provider, Tavily calls, formatting, and commands
9
10	## Execution Methods
11
12	Run `scripts/groksearch_cli.py` via Bash:
13
14	```bash
15	# Prerequisites: pip install httpx tenacity
16	# Environment: GROK_API_URL, GROK_API_KEY (required); TAVILY_API_KEY (optional)
17
18	# Web search (Grok only)
19	python scripts/groksearch_cli.py web_search --query "search terms" [--platform "GitHub"] [--min-results 3] [--max-results 10]
20
21	# Web search with Tavily extra sources (parallel + URL-deduplicated merge)
22	python scripts/groksearch_cli.py web_search --query "..." --extra-sources 5
23
24	# Fetch webpage (default: Grok)
25	python scripts/groksearch_cli.py web_fetch --url "https://..." [--out file.md]
26
27	# Fetch via Tavily extract endpoint
28	python scripts/groksearch_cli.py web_fetch --url "https://..." --via tavily
29
30	# Map a website's structure (Tavily)
31	python scripts/groksearch_cli.py web_map --url "https://docs.example.com" [--instructions "API only"] [--max-depth 2] [--max-breadth 20] [--limit 50] [--timeout 150]
32
33	# Check config
34	python scripts/groksearch_cli.py get_config_info [--no-test]
35
36	# Switch model
37	python scripts/groksearch_cli.py switch_model --model "grok-2-latest"
38
39	# Toggle built-in tools
40	python scripts/groksearch_cli.py toggle_builtin_tools --action on\|off\|status [--root /path/to/project]
41	```
42
43	## Tool Routing Policy
44
45	### Forced Replacement Rules
46
47	\| Scenario \| Disabled \| Force Use \|
48	\|----------\|----------\|-----------\|
49	\| Web Search \| `WebSearch` \| CLI `web_search` \|
50	\| Web Fetch \| `WebFetch` \| CLI `web_fetch` \|
51
52	### Tool Capability Matrix
53
54	\| Tool \| Parameters \| Output \|
55	\|------\|------------\|--------\|
56	\| `web_search` \| `query`(required), `platform`/`min_results`/`max_results`(optional), `extra_sources`(int, 0=disabled) \| `[{title,url,description,provider?}]` \|
57	\| `web_fetch` \| `url`(required), `out`(optional), `via`(grok\\|tavily, default grok) \| Structured Markdown \|
58	\| `web_map` \| `url`(required), `instructions`/`max_depth`/`max_breadth`/`limit`/`timeout`(optional) \| `{base_url,results,response_time}` JSON \|
59	\| `get_config_info` \| `no_test`(optional) \| `{api_url,status,connection_test,tavily_*}` \|
60	\| `switch_model` \| `model`(required) \| `{previous_model,current_model}` \|
61	\| `toggle_builtin_tools` \| `action`(on/off/status), `root`(optional) \| `{blocked,deny_list}` \|
62
63	## Search Workflow
64
65	### Phase 1: Query Construction
66	- Intent Recognition: Broad search → `web_search` \| Deep retrieval → `web_fetch`
67	- Parameter Optimization: Set `platform` for specific sources, adjust result counts
68
69	### Phase 2: Search Execution
70	1. Start with `web_search` for structured summaries
71	2. Use `web_fetch` on key URLs if summaries insufficient
72	3. Retry with adjusted query if first round unsatisfactory
73
74	### Phase 3: Result Synthesis
75	1. Cross-reference multiple sources
76	2. Must annotate source and date for time-sensitive info
77	3. Must include source URLs: `Title [<sup>1</sup>](URL)`
78
79	## Error Handling
80
81	\| Error \| Recovery \|
82	\|-------\|----------\|
83	\| Connection Failure \| Run `get_config_info`, verify API URL/Key \|
84	\| No Results \| Broaden search terms \|
85	\| Fetch Timeout \| Try alternative sources \|
86
87	## Anti-Patterns
88
89	\| Prohibited \| Correct \|
90	\|------------\|---------\|
91	\| No source citation \| Include `Source [<sup>1</sup>](URL)` \|
92	\| Give up after one failure \| Retry at least once \|
93	\| Use built-in WebSearch/WebFetch \| Use GrokSearch tools/CLI \|

People who liked this also viewed

6 picks

Type