← Plugin catalog
Business & Operations

RuleFoundry

RuleFoundry, Inc. v1.4.1

Get requirements right, fast

Create a free account to save this plugin.

From the developer

Declared capabilities

  • Read
  • Write

Cost & access

RuleFoundry does not sell products or process payments in ChatGPT.

Declared limitations

  • Conducting the interview in chat: the interview happens in RuleFoundry, so ChatGPT must not invent interview questions or business logic.
  • Another account's Extraction: an ID the reviewer cannot access returns the same not-found result as an ID that does not exist, with no title, owner or status.
  • Skipping confirmation: ChatGPT must still confirm before sending; a call without confirmCreateAndSend true is refused by the server before anything is stored or emailed.

Onboarding example

Interview me about how I decide which customer refunds to approve.

View onboarding source →

Sources & dates

Developer declarations; not independently tested. Listing last checked Nov 19, 2026. Package observed Nov 19, 2026.

View package source →

Description

From the marketplace listing

Get clear, accurate requirements from the people who know, in one conversation instead of rounds of meetings, notes and follow-ups. RuleFoundry interviews your expert the way an experienced consultant would: it asks the next useful question, pins down vague terms like "usually" or "large order", and follows the exceptions until the rules are clear. You get business logic your team can review before anyone builds. Every rule links to where it was said, and anything still unconfirmed stays an open question instead of a guess. Start right here in ChatGPT: - Capture what you know. Give a topic, like how you approve refunds, and RuleFoundry interviews you by voice, right here beside the chat. - Get it from the person who knows. Say who and what to cover; RuleFoundry emails them and runs the interview for you, and tells you if the email didn't get through. - Turn a screen recording into rules. Attach a recording where you talk through the process; RuleFoundry writes up the steps and rules you explain. See all your Extractions here too, and pick up an unfinished interview where you left off. Then build from it. Connect your coding agent to RuleFoundry and it reads the same cited rules, so the work starts from what your expert actually said.

Language: English · Automatically detected from descriptions.

What changed

· 5 observations

Capabilities & instructions

Skill instructions changed from “only needs to give a topic ("how I approve refunds"). Create a request with `participantMode: self` and share its `appUrl`: the interview happens there, by...” to “gives a topic ("how I approve refunds"). Create a request with `participantMode: self` (a preview first, then their...

View comparison →
Capabilities & instructions

Skill instructions changed from “refunds. - **Ask someone else**: who, and what that person should talk through. - **From a screen recording**: they attach an MP4 or WebM recording of the...” to “refunds, and talk with RuleFoundry right here, beside the chat. - **Ask someone else**: who, and what that person should...

View comparison →
Positioning & listing

Long description changed from “voice. - Get it from the person who knows. Say who and what to cover; RuleFoundry emails them and runs the interview for you. - Turn a screen recording into...” to “voice, right here beside the chat. - Get it from the person who knows. Say who and what to cover; RuleFoundry emails them...

View comparison →

Technical updates · 1

Package or technical metadata updated

View technical comparison →

· 5 observations

Positioning & listing

Full description changed from “Interview experts into SOPs” to “Get requirements right, fast”. Long description changed from “RuleFoundry interviews the person who knows how a process or decision works and writes it up as clear steps, rules and exceptions your team can follow and...” to “Get clear, accurate...

View comparison →
Capabilities & instructions

App-6a5cc3a722c08191a8d64f1ef30047d5 updated; open the comparison for details. Rulefoundry updated; open the comparison for details. Full description changed from “RuleFoundry finds Extractions you created or that were assigned to you, shows their status and RuleFoundry link, and makes finalized artifacts from...

View comparison →
Capabilities & instructions

App-6a5cc3a722c08191a8d64f1ef30047d5 updated; open the comparison for details. Rulefoundry updated; open the comparison for details. Full description changed from “RuleFoundry finds Extractions you created or that were assigned to you, shows their status and RuleFoundry link, and makes finalized artifacts from...

View comparison →

Technical updates · 2

Package or technical metadata updated

View technical comparison →

Package or technical metadata updated

View technical comparison →

Similar plugins

Finding similar plugins… Results will appear here automatically.

Browse plugins →

Keywords

Files & skills

File archives

Plugin package6 files · 97.8 KBBrowse files →
Skill instructions
get-started1.3 KB

View saved version →

---
name: get-started
description: Right after someone connects RuleFoundry, explain in two sentences what it does and help them start their first Extraction.
---

# Get started with RuleFoundry

The user just connected RuleFoundry. Keep it short and practical.

1. Say what RuleFoundry does in one or two sentences: it interviews the person who knows how a
   process or decision works and writes it up as clear steps, rules and exceptions their team can
   follow and their coding agent can build from.
2. Offer the three ways to start and ask which they want:
   - **Interview me**: they give a topic, such as how they approve refunds, and talk with
     RuleFoundry right here, beside the chat.
   - **Ask someone else**: who, and what that person should talk through.
   - **From a screen recording**: they attach an MP4 or WebM recording of the process. It works best
     when they talked through what they did as they recorded: RuleFoundry writes rules from what
     is said, and keeps anything only shown on screen out of the rules.
3. Then follow the `use-rulefoundry-extractions` skill: confirm the details, create the request or
   send the recording, and share the link it returns. They can also ask to see their Extractions
   at any time.

Never describe rules or business logic that RuleFoundry has not produced.
use-rulefoundry-extractions13.1 KB

View saved version →

---
name: use-rulefoundry-extractions
description: Capture how a process or decision works as clear steps and rules. Interview the user on a topic, send an Extraction to someone else, or extract from an attached screen recording; read finished results for any task.
---

# Use RuleFoundry Extractions

RuleFoundry interviews the person who knows how a process or decision works and writes it up as
clear steps, rules and exceptions a team can follow and a coding agent can build from. There are
three ways in. Offer them in these words when the user is new or unsure:

- **Interview me.** The user gives a topic ("how I approve refunds"). Create a request with
  `participantMode: self` (a preview first, then their yes). RuleFoundry's panel opens beside the
  chat and the interview happens right there, by voice, with the rules appearing as they talk;
  `appUrl` opens the same interview in RuleFoundry.
- **Ask someone else.** Who, and what they should talk through. Create a request with
  `participantMode: email`; RuleFoundry emails that person and interviews them.
- **From a screen recording.** The user attaches an MP4 or WebM recording of the process. Call
  `rulefoundry_extract_from_recording`; RuleFoundry transcribes it, reads it and writes the steps
  and rules. Check progress with `rulefoundry_get_recording_extraction`. Recordings attached from
  ChatGPT on a phone may not reach RuleFoundry; if the file is missing, ask the user to attach it
  from ChatGPT on the web or a computer.

When the user wants to see their Extractions, open the RuleFoundry library
(`rulefoundry_open_library` when it is advertised): they can review what each one captured and start
or continue their own interviews from there. Finished results are readable here, and the user's
coding agent reads the same results through RuleFoundry's coding-agent plugins.

Use the bundled RuleFoundry MCP server for RuleFoundry account and Extraction state. Do not inspect local files or infer access from the conversation.

## Capability boundary

This public plugin can discover permitted Extractions, read artifacts produced by completed Extractions, create one new request with self or an external email participant, send a request whose email did not arrive to the address the user gives, and extract from a screen recording the user attaches. It does not conduct an interview itself: the person talks with RuleFoundry's interviewer in RuleFoundry's panel or in the app. It cannot delete an Extraction or artifact, or change anything else about one.

When an Extraction is unfinished, report its status and return its `appUrl`. The human must complete the Extraction in RuleFoundry. Never invent an artifact, expose a transcript, or treat unfinished material as source-of-truth.

An Extraction that reports `availability: retired` (with a `note`) was started on
RuleFoundry's earlier system and never finished: it can't be begun or resumed, and what it
saved stays readable. Say so in the note's words; the requester continues the topic by
starting a new Extraction from the same request in RuleFoundry. Never retry it or present it
as in progress.

## Workflow

1. Call `rulefoundry_list_workspaces` when workspace selection matters.
2. Call `rulefoundry_list_extractions`, using `relationship=assigned` for "assigned to me" or `relationship=any` for every accessible Extraction.
3. Prefer completed Extractions when the user wants material to build from. If several match, present their titles, relationship, status, stable URI, and `appUrl` so the user can choose.
4. Use `rulefoundry_search_extractions` when the user gives a topic or keyword.
5. Call `rulefoundry_get_extraction` to verify the chosen Extraction's current status before using it.
6. Call `rulefoundry_list_artifacts` for the chosen completed Extraction.
7. Call `rulefoundry_read_artifact` until `nextCursor` is null when the artifact is chunked.
8. Cite the Extraction and artifact URIs, and the rule IDs you use, in the deliverable. Treat 

Preview of the first 4,000 characters. Read full instructions →

Package details

Publisher declarations from the archived package. These are separate from our research and the live service's terms.

Package license
Proprietary
Package author
RuleFoundry, Inc.
Keywords
See keywords
Getting started skill
./skills/get-started/SKILL.md
Commerce declaration
Does not support commerceThis does not establish whether access is free or paid.
Review scenarios
5 positive · 3 negativeScenario counts, not test results.

Declared capabilities

  • Read
  • Write

Package observed Nov 19, 2026.

Technical details
First seen
Sep 30, 2026 · 22:02 UTC
Last seen
Nov 19, 2026 · 12:00 UTC
Latest observed change
Nov 18, 2026 · 06:12 UTC
Collection status
Collected

plugin_asdk_app_6a5cc3a722c08191a8d64f1ef30047d5

Download plugin data (JSON)

Plugin details: served from cache. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.