parallel-findall

Name: parallel-findall
Author: parallel-web

9.4kinstalls6forks

How to install parallel-findall?

parallel-web/parallel-agent-skills/parallel-findall

$npx -y skills add parallel-web/parallel-agent-skills --skill parallel-findall

Installs into the current project.

Summary

Discover entities (companies, people, products, etc.) matching a natural-language description. Use when the user asks to 'find all X' or 'list every Y that…' — e.g., 'Find AI startups that raised Series A in 2026', 'List roofing companies in Charlotte NC', 'Show me YC W24 dev too

Files · 1

View on GitHub

SKILL.md

1	# FindAll: Entity Discovery
2
3	Find: $ARGUMENTS
4
5	> Requires `parallel-cli` ≥ 0.6.0 (the `findall entity-search` command was added in 0.6.0; the broader `findall` command was added in 0.3.0). If either errors with `no such command` or similar, tell the user to run `parallel-cli update` (or `pipx upgrade parallel-web-tools` if installed via pipx), then retry.
6
7	## When to use this skill
8
9	Use FindAll when the user wants a structured list of entities matching a description, not webpages or a narrative answer.
10
11	\| User asks for… \| Use \|
12	\|---\|---\|
13	\| "Find all X that…" / "List every Y…" \| parallel-findall (this skill) \|
14	\| Webpage results / quick answers / current info \| parallel-web-search \|
15	\| Narrative report / analysis / "research X" \| parallel-deep-research \|
16	\| Add fields to a list you already have \| parallel-data-enrichment \|
17
18	If the user already has a list and just wants to add fields, this is the wrong skill — use parallel-data-enrichment.
19
20	FindAll has two paths: the comprehensive, asynchronous `findall run` (Steps 1–2) and the fast, synchronous `entity-search` (final section).
21
22	- `entity-search` — very fast (few seconds), only supports people or company search. Supports a more limited set of query arguments. Optimized for recall over precision; results are not individually verified.
23	- `findall run` — Provides comprehensive coverage, complex, match conditions, exclusions, enrichment, citations, or a type other than people/companies.
24
25	If it's ambiguous, ask the user which they'd prefer and offer a default. Remember entity search limits: companies/people only, no exclusions/generator/enrichment, and `entity_set_id` can't be used with `enrich`/`extend` (re-run via `findall run` if needed).
26
27	Switch to `entity-search` only when the user explicitly signals they want a fast, throwaway list. `entity-search` is also strictly more limited: it only supports `companies` or `people` entity types, no exclusions, no generator choice, no enrichment, and the returned `entity_set_id` is not usable with `findall enrich`/`extend`. If you start there and the user later asks to enrich or extend, you'll have to re-run via `findall run`.
28
29	## Step 1: Start the run
30
31	```bash
32	parallel-cli findall run "$ARGUMENTS" --no-wait --json
33	```
34
35	Defaults: generator `core`, match limit `10`. Stick with `core` unless the user has a reason to escalate:
36
37	- `-g pro` — most thorough generator (slower, costlier). Use when the user asks for "comprehensive" coverage or matches are sparse on `core`
38	- `-g base` — fastest, but markedly lower quality. Often returns query-echo entities (e.g., directory pages, the literal query string), entries with no URL, or category placeholders. Only use if the user explicitly asks for a quick scan and accepts noise; otherwise prefer `core`
39	- `-n 50` — return up to 50 matched entities (5–1000 allowed)
40
41	If the user wants to exclude known entities (e.g., "find competitors but not Google or OpenAI"):
42
43	```bash
44	parallel-cli findall run "$ARGUMENTS" --no-wait --json \
45	--exclude '[{"name":"Google","url":"google.com"},{"name":"OpenAI","url":"openai.com"}]'
46	```
47
48	Tip — preview the schema first if the objective is ambiguous: `parallel-cli findall ingest "$ARGUMENTS" --json` shows the entity type and match conditions the API inferred, so you can refine wording before paying for a run.
49
50	Parse the JSON output to extract the `findall_id` and any monitoring URL. Tell the user:
51
52	- A FindAll run has been started
53	- Approximate cadence (minutes for `core`, longer for `pro`)
54	- They can keep working while it runs
55
56	## Step 2: Poll for results
57
58	Choose a descriptive filename (e.g., `series-a-ai-2026`, `charlotte-roofers`). Use lowercase with hyphens, no spaces.
59
60	```bash
61	parallel-cli findall poll "$FINDALL_ID" -o "/tmp/$FILENAME.json" --timeout 540
62	```
63
64	Important:
65
66	- Use `--timeout 540` (9 minutes) to stay within tool execution limits
67	- Do NOT pass `--json` for large result sets — it will flood context. `-o` saves the full results to disk
68
69	### If the poll times out
70
71	Re-run the same `parallel-cli findall poll` command to continue waiting. Server-side the run continues regardless.
72
73	## Response format
74
75	Before presenting matches, filter the results for obvious noise:
76
77	- Drop entries with empty/missing `url`
78	- Drop entrie

People who liked this also viewed

6 picks

Type

parallel-findall

9.4kinstalls6forks

View on GitHub

How to install parallel-findall?

parallel-web/parallel-agent-skills/parallel-findall

$npx -y skills add parallel-web/parallel-agent-skills --skill parallel-findall

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# FindAll: Entity Discovery
2
3	Find: $ARGUMENTS
4
5	> Requires `parallel-cli` ≥ 0.6.0 (the `findall entity-search` command was added in 0.6.0; the broader `findall` command was added in 0.3.0). If either errors with `no such command` or similar, tell the user to run `parallel-cli update` (or `pipx upgrade parallel-web-tools` if installed via pipx), then retry.
6
7	## When to use this skill
8
9	Use FindAll when the user wants a structured list of entities matching a description, not webpages or a narrative answer.
10
11	\| User asks for… \| Use \|
12	\|---\|---\|
13	\| "Find all X that…" / "List every Y…" \| parallel-findall (this skill) \|
14	\| Webpage results / quick answers / current info \| parallel-web-search \|
15	\| Narrative report / analysis / "research X" \| parallel-deep-research \|
16	\| Add fields to a list you already have \| parallel-data-enrichment \|
17
18	If the user already has a list and just wants to add fields, this is the wrong skill — use parallel-data-enrichment.
19
20	FindAll has two paths: the comprehensive, asynchronous `findall run` (Steps 1–2) and the fast, synchronous `entity-search` (final section).
21
22	- `entity-search` — very fast (few seconds), only supports people or company search. Supports a more limited set of query arguments. Optimized for recall over precision; results are not individually verified.
23	- `findall run` — Provides comprehensive coverage, complex, match conditions, exclusions, enrichment, citations, or a type other than people/companies.
24
25	If it's ambiguous, ask the user which they'd prefer and offer a default. Remember entity search limits: companies/people only, no exclusions/generator/enrichment, and `entity_set_id` can't be used with `enrich`/`extend` (re-run via `findall run` if needed).
26
27	Switch to `entity-search` only when the user explicitly signals they want a fast, throwaway list. `entity-search` is also strictly more limited: it only supports `companies` or `people` entity types, no exclusions, no generator choice, no enrichment, and the returned `entity_set_id` is not usable with `findall enrich`/`extend`. If you start there and the user later asks to enrich or extend, you'll have to re-run via `findall run`.
28
29	## Step 1: Start the run
30
31	```bash
32	parallel-cli findall run "$ARGUMENTS" --no-wait --json
33	```
34
35	Defaults: generator `core`, match limit `10`. Stick with `core` unless the user has a reason to escalate:
36
37	- `-g pro` — most thorough generator (slower, costlier). Use when the user asks for "comprehensive" coverage or matches are sparse on `core`
38	- `-g base` — fastest, but markedly lower quality. Often returns query-echo entities (e.g., directory pages, the literal query string), entries with no URL, or category placeholders. Only use if the user explicitly asks for a quick scan and accepts noise; otherwise prefer `core`
39	- `-n 50` — return up to 50 matched entities (5–1000 allowed)
40
41	If the user wants to exclude known entities (e.g., "find competitors but not Google or OpenAI"):
42
43	```bash
44	parallel-cli findall run "$ARGUMENTS" --no-wait --json \
45	--exclude '[{"name":"Google","url":"google.com"},{"name":"OpenAI","url":"openai.com"}]'
46	```
47
48	Tip — preview the schema first if the objective is ambiguous: `parallel-cli findall ingest "$ARGUMENTS" --json` shows the entity type and match conditions the API inferred, so you can refine wording before paying for a run.
49
50	Parse the JSON output to extract the `findall_id` and any monitoring URL. Tell the user:
51
52	- A FindAll run has been started
53	- Approximate cadence (minutes for `core`, longer for `pro`)
54	- They can keep working while it runs
55
56	## Step 2: Poll for results
57
58	Choose a descriptive filename (e.g., `series-a-ai-2026`, `charlotte-roofers`). Use lowercase with hyphens, no spaces.
59
60	```bash
61	parallel-cli findall poll "$FINDALL_ID" -o "/tmp/$FILENAME.json" --timeout 540
62	```
63
64	Important:
65
66	- Use `--timeout 540` (9 minutes) to stay within tool execution limits
67	- Do NOT pass `--json` for large result sets — it will flood context. `-o` saves the full results to disk
68
69	### If the poll times out
70
71	Re-run the same `parallel-cli findall poll` command to continue waiting. Server-side the run continues regardless.
72
73	## Response format
74
75	Before presenting matches, filter the results for obvious noise:
76
77	- Drop entries with empty/missing `url`
78	- Drop entrie

People who liked this also viewed

6 picks

Type