Flowleap ops

Skill flowleap-ai/flowleap-plugins/plugins/flowleap/skills/flowleap-ops

The FlowLeap Plugin Marketplace — curated, free-to-install skill packs for patent and IP work.

Install

npx -y skills add flowleap-ai/flowleap-plugins --skill flowleap-ops

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Direct EPO Open Patent Services access through the FlowLeap backend — CQL search plus per-document bibliography, claims, description, family, legal status, and abstract. Trigger when an agent needs authoritative EPO document data for a known publication number, full claims or description text, family members, legal-status events, or a raw OPS CQL search. For query-building or ranked discovery use flowleap-patent; use OPS for authoritative per-document data.

SKILL.md

3.0 KB, 703 tokens by cl100k_base, as published. Nobody here has run it

FlowLeap OPS

Auth and global flags: see flowleap-shared.

Direct access to the European Patent Office (EPO) Open Patent Services API.

Commands

Search

flowleap ops search --cql <query> [flags]

Flag	Description	Default
`--cql`	CQL query string (required)	—
`--start`	Start position	`1`
`--end`	End position	`25`

Document Commands

All document commands take a patent document number (e.g., EP1234567). claims and description accept --lang (defaults to en):

flowleap ops biblio <doc>                  # Bibliographic data
flowleap ops claims <doc> --lang en        # Claims text
flowleap ops description <doc> --lang en   # Full description
flowleap ops family <doc>                  # Patent family members
flowleap ops legal <doc>                   # Legal status events
flowleap ops abstract <doc>                # Abstract text

Doc IDs are normalized server-side — ep1.000.000 and EP1000000 both resolve.

For a non-EP-style number (US grant/application, or an original-format KR/CN number), convert it to DOCDB first so OPS can match it:

flowleap convert-number US5443036.A --to docdb

A SERVER.EntityNotFound on some KR/CN documents is an OPS coverage gap, not a retryable error — don't retry it; fall back to another source for that document.

Response envelope

OPS endpoints return data wrapped in a success/error envelope. The CLI unwraps data automatically so --json prints just the payload. Pass --verbose to see cache status and execution time. Errors use code values: MISSING_PARAM, NOT_FOUND, RATE_LIMITED, INTERNAL_ERROR.

Examples

# CQL search
flowleap ops search --cql "ti=solar AND pa=Tesla"

# Get bibliographic data
flowleap ops biblio EP1234567

# Get claims in German
flowleap ops claims US10123456 --lang de

# Get family members (JSON for agents)
flowleap ops family EP1234567 --json

# Search with pagination
flowleap ops search --cql "ti=battery" --start 1 --end 50

# Verbose shows cache status and timing
flowleap ops biblio EP1234567 --verbose

Workflow: Deep Patent Analysis

Search: flowleap ops search --cql "ti=solar AND pa=Tesla"
Get details: flowleap ops biblio EP1234567
Read claims: flowleap ops claims EP1234567
Check family: flowleap ops family EP1234567
Check legal status: flowleap ops legal EP1234567

One-call alternative: flowleap --json summary EP1234567 bundles biblio, legal status, family, and term.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most ship operate skills give in 703 tokens

Counted across 779 of the 1,178 authors here whose files we hold, read 2026-08-07

Document a rollback plan before deploymentin 41 of 779, across 22 files
Update the changelogin 21 of 779, across 19 files
Run the test suitein 20 of 779
Create an annotated git tagin 20 of 779
Clean up feature flags after full rolloutin 18 of 779, across 10 files
Verify deployment health after launchin 18 of 779, across 10 files
Test both feature flag statesin 17 of 779, across 9 files
Verify the working tree is cleanin 17 of 779
Make database migrations backward-compatiblein 16 of 779, across 8 files
Set up error monitoring before launchin 15 of 779, across 7 files
Monitor metrics at each rollout stagein 14 of 779, across 5 files
Create a GitHub releasein 14 of 779

Said here and by no other author read

Use the CLI to run OPS CQL searches
Pass the CQL query string via the required flag
Use document subcommands to fetch specific sections
Convert non-EP numbers to DOCDB format first
Do not retry SERVER.EntityNotFound errors
Fall back to another source on EntityNotFound

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.