parallel-findall Skill for Claude: What It Does and How to Install It
Makes Claude find companies, people or products that match a description and return a structured list.
- Installs
- 12.5K
- on skills.sh
- Stars
- 91
- on GitHub
- Updated
- Oct 2026
- last repo commit
This is Parallel's own entity discovery skill. For requests like "find all X" or "list every Y that...", Claude starts a parallel-cli findall run, polls it, and presents only the candidates marked as matched, with evidence and the run ID.
It needs parallel-cli installed, signed in and funded. The folder holds only SKILL.md and bundles no scripts.
Good for
- Sales and market researchers building lists such as startups of a given stage
- Anyone who wants a table of entities, not a pile of web pages
- Developers who want raw results saved as JSON
Install parallel-findall
Claude Code
- 1
Copy this prompt.
Install the parallel-findall skill in Claude Code. Run this command: /plugin marketplace add parallel-web/parallel-agent-skills /plugin install parallel Then check that it loaded and tell me how to use it.
- 2
Paste it into Claude Code. It shows the change and asks before running it.
Pick one route. The plugin installs all 15 skills (counted from the repo), a hosted Parallel Search MCP server (parallel-search, anonymous) and a Bash-only agent called parallel-subagent. Restart Claude Code after installing it. This skill needs parallel-cli installed, signed in and funded; the second method in each tab lists the install commands from the repo's setup skill, and /parallel:parallel-cli-setup runs them for you. In Codex, use $ instead of / for skill names. The repo's .agents/skills folder, which Codex reads inside a clone, links 12 of the 15 skills and not this one.
From the project README. Source.
What's in the skill
When it loads
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 tools companies'. Different from web-search (which returns webpages) and deep-research (which returns a narrative report). Use this when the user wants a structured list of entities.
Sections in SKILL.md
- When to use this skill
- Step 1: Start and retain the run
- Step 2: Add requested fields explicitly
- Step 3: Check status and retrieve results
- Present matches and evidence
- Get more matches
- Fast entity search
- Setup
Key facts
- Installs on skills.sh
- 12,468 (Nov 2, 2026)
- GitHub stars
- 91 for the whole repo (Nov 2, 2026)
- Last repo commit
- Oct 28, 2026
- Audits on skills.sh
- Gen Agent Trust Hub: pass, Socket: pass, Snyk: pass
- What it includes
- 1 file: SKILL.md. It bundles no scripts
What it includes
Previews the entity type, conditions and suggested enrichments for your objective
This calls the API, so it is not a free offline test.
Runs code ·
findall ingestStarts an asynchronous search for entities matching your description
Defaults: generator core, match limit 10. -n sets 5 to 1000 matches. --exclude skips named entities.
Try: “Find AI startups that raised Series A in 2026”
Runs code ·
findall runAdds requested fields, such as CEO or employee count, to the matches
It takes a JSON Schema object. Mentioning the fields in the objective is not enough.
Runs code ·
findall enrichChecks progress, waits in chunks, or takes a snapshot of results
A snapshot does not prove the run is complete. Read status and is_active together.
Runs code ·
findall status / poll / resultAdds more matches to a run, up to a total of 1000
The number you pass is an increment. Preview runs cannot be extended.
Runs code ·
findall schema / extendFast, synchronous rough list of companies or people
For explicit speed requests only. Results are unverified leads with no exclusions or enrichment.
Runs code ·
findall entity-searchShows only candidates marked matched, with evidence and the run ID
Unmatched and discarded candidates stay in the raw file.
Presenting matches
From the official docs
Permissions
Medium risk
What it can do
- Read your data
- Create and change things
- Delete things
- Read-only mode
Watch out for
Your queries are sent to Parallel
The README says task inputs go to Parallel's API under its Customer Terms and Privacy Policy, and tells you not to send secrets or sensitive local content. Review what Claude puts in a request. github.com
It runs against your funded Parallel account
The README says CLI-backed skills are billed as ordinary API usage on your own Parallel account. Check current pricing on the vendor site before large runs. github.com
Bigger runs and add-ons cost more
SKILL.md says the pro generator is slower and costlier, and a run can take up to 1000 matches. It tells Claude not to create a replacement paid run automatically. Set the match limit and generator yourself. github.com
Enrichment and extend are separate requests
Fields such as CEO name need a separate `findall enrich` call, and `findall extend` adds matches to an existing run. Each is another call to Parallel's API under your account. github.com
The setup path installs and signs in a CLI
The repo's setup skill installs parallel-cli (brew, uv, npm or pipx), starts a device sign-in, and points to `parallel-cli balance add` for top-ups. The search and research skills say never to add funds without explicit confirmation. github.com
Technical details
| Turning on read-only | There is no read-only switch. The skill runs parallel-cli commands that call Parallel's API under your account. |
|---|---|
| Sign-in and keys | parallel-cli signs in with a device OAuth flow you approve in a browser. The README says CLI-backed skills use credentials you already configured. |
| Scopes |
|
Questions
What does the parallel-findall skill do?
It makes Claude find a structured list of entities that match a description, such as companies, people or products, using parallel-cli findall. It returns the matched entities with evidence, not a list of web pages.
How do I install parallel-findall?
Use the install box above. The plugin installs it with 14 other skills. Then install and sign in to parallel-cli.
Which parallel-cli version does it need?
The frontmatter says 0.6.0 or newer. The text says full FindAll needs 0.3.0 or newer and only the optional entity-search path needs 0.6.0. Use 0.6.0 or newer to avoid any doubt.
Is "find all" exhaustive?
No. SKILL.md says "Find all" does not guarantee exhaustive coverage of the internet. It tells Claude to spot-check claims such as batch, year and geography against the evidence.
findall vs web search vs deep research?
SKILL.md: web search returns webpages, deep research returns a narrative report, and FindAll returns a structured list of entities. To add fields to a list you already have, it points to parallel-data-enrichment.
How many results can I get?
The default is 10 matches. You can ask for 5 to 1000 with -n, and extend a completed run if its termination reason was match_limit_met, up to 1000 in total.
Is it safe?
It runs parallel-cli in Bash, sends your objective and exclusions to Parallel, and writes result files. Runs are billed to your account. Our advice: start with the default 10 matches and review before asking for more.
Does it work in Codex?
The README documents a Codex install with $skill-installer. The repo's .agents/skills folder, which Codex reads inside a clone, links 12 of the 15 skills and not this one. The Codex plugin manifest points at the whole skills folder.
Is it an official Parallel skill?
It is in Parallel Web Systems' own repo, and the repo's marketplace.json describes the plugin as the "Official Parallel Web Systems plugin for Claude Code".
Information
updated Nov 2, 2026
- Repository
- parallel-web/parallel-agent-skills
- Folder
skills/parallel-findall
Sources
Docs, issue trackers and discussions this page is built from.
Show all 5Hide
- parallel-agent-skills README · github.com
- parallel-agent-skills marketplace.json · github.com
- parallel plugin.json · github.com
- parallel-cli-setup SKILL.md · github.com
- parallel-findall SKILL.md · github.com