parallel-deep-research

Name: parallel-deep-research
Author: parallel-web

12kinstalls6forks

How to install parallel-deep-research?

parallel-web/parallel-agent-skills/parallel-deep-research

$npx -y skills add parallel-web/parallel-agent-skills --skill parallel-deep-research

Installs into the current project.

Summary

ONLY use when user explicitly says 'deep research', 'exhaustive', 'comprehensive report', or 'thorough investigation'. Slower and more expensive than parallel-web-search. For normal research/lookup requests, use parallel-web-search instead. Supports multi-turn: pass --previous-in

Files · 1

View on GitHub

SKILL.md

1	# Deep Research
2
3	Research topic: $ARGUMENTS
4
5	> Requires `parallel-cli` ≥ 0.3.0. If any command below errors with `no such option`, `no such command`, or `unrecognized arguments`, the user is on an older CLI. Tell them to run `parallel-cli update` (or `pipx upgrade parallel-web-tools` if installed via pipx), then retry.
6
7	## When to use (vs parallel-web-search)
8
9	ONLY use this skill when the user explicitly requests deep/exhaustive research. Deep research is 10-100x slower and more expensive than parallel-web-search. For normal "research X" requests, quick lookups, or fact-checking, use parallel-web-search instead.
10
11	## Step 1: Start the research
12
13	Choose a descriptive filename based on the topic (e.g., `ai-chip-market-2026`, `react-vs-vue-comparison`). Use lowercase with hyphens, no spaces. Reuse this base name in step 2 as `-o "$FILENAME"`.
14
15	```bash
16	parallel-cli research run "$ARGUMENTS" --processor pro-fast --text --no-wait --json
17	```
18
19	The `--text` flag tells the API to return a markdown report (with inline citations) when the task completes, instead of the default structured JSON. Use it for narrative/report-style requests, which is what most users want from "deep research." Drop `--text` if the user explicitly wants structured JSON output.
20
21	Optional with `--text`: pass `--text-description "Keep under 1500 words, focus on M&A activity"` to steer length, format, or focus.
22
23	If this is a follow-up to a previous research or enrichment task where you know the `interaction_id`, add context chaining:
24
25	```bash
26	parallel-cli research run "$ARGUMENTS" --processor lite-fast --text --no-wait --json --previous-interaction-id "$INTERACTION_ID"
27	```
28
29	By chaining `interaction_id` values across requests, each follow-up question automatically has the full context of prior turns — so you can drill deeper without restating what was already researched. Use a lighter processor (`lite-fast` or `base-fast`) for follow-ups since the heavy lifting was done in the initial turn.
30
31	This returns instantly. Do NOT omit `--no-wait` — without it the command blocks for minutes and will time out.
32
33	Processor options (choose based on user request):
34
35	\| Processor \| Expected latency \| Use when \|
36	\|-----------\|-----------------\|----------\|
37	\| `lite-fast` \| 10–60s \| Quick lookups, follow-ups \|
38	\| `base-fast` \| 15–100s \| Simple questions \|
39	\| `core-fast` \| 1–5 min \| Moderate research \|
40	\| `pro-fast` \| 2–10 min \| Default — exploratory research, good depth/speed balance \|
41	\| `ultra-fast` \| 5–25 min \| Multi-source deep research (~2× cost) \|
42	\| `ultra2x-fast` / `ultra4x-fast` / `ultra8x-fast` \| up to 2 hr \| Hardest questions, only when explicitly requested \|
43
44	Notes on the `-fast` suffix: `-fast` tiers use cached web data and are quicker. The non-fast variants (`pro`, `ultra`, etc.) re-fetch fresher data — slower but better for very recent events. Default to `-fast` unless the user specifically asks about news from the last day or two.
45
46	Run `parallel-cli research processors` to see the full list with latencies.
47
48	Parse the JSON output to extract the `run_id`, `interaction_id`, and monitoring URL. Immediately tell the user:
49
50	- Deep research has been kicked off
51	- The expected latency for the processor tier chosen (from the table above)
52	- The monitoring URL where they can track progress
53
54	Tell them they can background the polling step to continue working while it runs.
55
56	## Step 2: Poll for results
57
58	```bash
59	parallel-cli research poll "$RUN_ID" -o "$FILENAME" --timeout 540
60	```
61
62	Important:
63
64	- Use `--timeout 540` (9 minutes) to stay within tool execution limits
65	- Do NOT pass `--json` — the full output is large and will flood context. The `-o` flag writes results to files instead.
66	- With `-o "$FILENAME"`:
67	- `$FILENAME.json` is always written (metadata + basis)
68	- `$FILENAME.md` is written only if step 1 used `--text` (markdown report)
69	- The poll command prints an executive summary to stdout when the research completes. Share this executive summary with the user — it gives them a quick overview without having to open the files.
70	- Pass `--force` if re-polling and you want to overwrite existing files
71
72	### If the poll times out
73
74	Higher processor tiers can take longer than 9 minutes. If the poll exits without completing:
75
76	1. Tell the user the research is still running server-side
77	2. Re-run the same `parallel-cli research poll` command to continue waiting
78
79	## Response format
80
81	**After s

People who liked this also viewed

6 picks

Type

parallel-deep-research

12kinstalls6forks

View on GitHub

How to install parallel-deep-research?

parallel-web/parallel-agent-skills/parallel-deep-research

$npx -y skills add parallel-web/parallel-agent-skills --skill parallel-deep-research

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Deep Research
2
3	Research topic: $ARGUMENTS
4
5	> Requires `parallel-cli` ≥ 0.3.0. If any command below errors with `no such option`, `no such command`, or `unrecognized arguments`, the user is on an older CLI. Tell them to run `parallel-cli update` (or `pipx upgrade parallel-web-tools` if installed via pipx), then retry.
6
7	## When to use (vs parallel-web-search)
8
9	ONLY use this skill when the user explicitly requests deep/exhaustive research. Deep research is 10-100x slower and more expensive than parallel-web-search. For normal "research X" requests, quick lookups, or fact-checking, use parallel-web-search instead.
10
11	## Step 1: Start the research
12
13	Choose a descriptive filename based on the topic (e.g., `ai-chip-market-2026`, `react-vs-vue-comparison`). Use lowercase with hyphens, no spaces. Reuse this base name in step 2 as `-o "$FILENAME"`.
14
15	```bash
16	parallel-cli research run "$ARGUMENTS" --processor pro-fast --text --no-wait --json
17	```
18
19	The `--text` flag tells the API to return a markdown report (with inline citations) when the task completes, instead of the default structured JSON. Use it for narrative/report-style requests, which is what most users want from "deep research." Drop `--text` if the user explicitly wants structured JSON output.
20
21	Optional with `--text`: pass `--text-description "Keep under 1500 words, focus on M&A activity"` to steer length, format, or focus.
22
23	If this is a follow-up to a previous research or enrichment task where you know the `interaction_id`, add context chaining:
24
25	```bash
26	parallel-cli research run "$ARGUMENTS" --processor lite-fast --text --no-wait --json --previous-interaction-id "$INTERACTION_ID"
27	```
28
29	By chaining `interaction_id` values across requests, each follow-up question automatically has the full context of prior turns — so you can drill deeper without restating what was already researched. Use a lighter processor (`lite-fast` or `base-fast`) for follow-ups since the heavy lifting was done in the initial turn.
30
31	This returns instantly. Do NOT omit `--no-wait` — without it the command blocks for minutes and will time out.
32
33	Processor options (choose based on user request):
34
35	\| Processor \| Expected latency \| Use when \|
36	\|-----------\|-----------------\|----------\|
37	\| `lite-fast` \| 10–60s \| Quick lookups, follow-ups \|
38	\| `base-fast` \| 15–100s \| Simple questions \|
39	\| `core-fast` \| 1–5 min \| Moderate research \|
40	\| `pro-fast` \| 2–10 min \| Default — exploratory research, good depth/speed balance \|
41	\| `ultra-fast` \| 5–25 min \| Multi-source deep research (~2× cost) \|
42	\| `ultra2x-fast` / `ultra4x-fast` / `ultra8x-fast` \| up to 2 hr \| Hardest questions, only when explicitly requested \|
43
44	Notes on the `-fast` suffix: `-fast` tiers use cached web data and are quicker. The non-fast variants (`pro`, `ultra`, etc.) re-fetch fresher data — slower but better for very recent events. Default to `-fast` unless the user specifically asks about news from the last day or two.
45
46	Run `parallel-cli research processors` to see the full list with latencies.
47
48	Parse the JSON output to extract the `run_id`, `interaction_id`, and monitoring URL. Immediately tell the user:
49
50	- Deep research has been kicked off
51	- The expected latency for the processor tier chosen (from the table above)
52	- The monitoring URL where they can track progress
53
54	Tell them they can background the polling step to continue working while it runs.
55
56	## Step 2: Poll for results
57
58	```bash
59	parallel-cli research poll "$RUN_ID" -o "$FILENAME" --timeout 540
60	```
61
62	Important:
63
64	- Use `--timeout 540` (9 minutes) to stay within tool execution limits
65	- Do NOT pass `--json` — the full output is large and will flood context. The `-o` flag writes results to files instead.
66	- With `-o "$FILENAME"`:
67	- `$FILENAME.json` is always written (metadata + basis)
68	- `$FILENAME.md` is written only if step 1 used `--text` (markdown report)
69	- The poll command prints an executive summary to stdout when the research completes. Share this executive summary with the user — it gives them a quick overview without having to open the files.
70	- Pass `--force` if re-polling and you want to overwrite existing files
71
72	### If the poll times out
73
74	Higher processor tiers can take longer than 9 minutes. If the poll exits without completing:
75
76	1. Tell the user the research is still running server-side
77	2. Re-run the same `parallel-cli research poll` command to continue waiting
78
79	## Response format
80
81	**After s

People who liked this also viewed

6 picks

Type