rudder-profiles-project

Name: rudder-profiles-project
Author: rudderlabs

18stars0forks

How to install rudder-profiles-project?

rudderlabs/rudder-agent-skills/rudder-profiles-project

$npx -y skills add rudderlabs/rudder-agent-skills --skill rudder-profiles-project

Installs into the current project.

Summary

Creates a new RudderStack Profiles project with discovered warehouse resources and validated YAML. Use when creating a Profiles project, bootstrapping identity resolution, generating pb_project.yaml, or building inputs and features from scratch.

Files · 1

View on GitHub

SKILL.md

1	# RudderStack Profiles Project Creation
2
3	Create a new Profiles project by discovering real warehouse resources first, then generating the three core YAML files with explicit user confirmation at each decision point.
4
5	## Workflow
6
7	1. Verify setup — Check that Profiles MCP tools are available. If not, send the user to `/rudder-profiles-setup`.
8	2. Discover connections — Call `get_existing_connections()`.
9	- If connections exist, present the list and let the user pick one.
10	- If no connections exist, instruct the user to run `pb init connection` in their terminal, wait for confirmation that it completed, then re-check with `get_existing_connections()`.
11	3. Discover tables — Call `input_table_suggestions()` for candidate tables. Call `describe_table()` on each candidate to confirm columns, types, and timestamps.
12	4. Confirm with user — Present discovered resources and get explicit approval (see confirmation gates below).
13	5. Generate YAML — Write `pb_project.yaml`, `models/inputs.yaml`, and `models/profiles.yaml` using only discovered names and the exact shapes in `references/basic-yaml-templates.md`. Derive `schema_version` from the installed binary (scaffold with `pb init pb-project` or MCP `setup_new_profiles_project()`; verify with `pb version`) — do not hardcode a remembered number. For each event-stream input set `contract: { is_event_stream: true, is_append_only: true }` plus `app_defaults.occurred_at_col` (the contract unlocks later incremental migration without a checkpoint-invalidating schema change, and `is_append_only` is rejected without `occurred_at_col`). Start with the default ID stitcher (no explicit `id_stitcher` model) unless the user needs custom edge sources. Add `filters:` on id_types to exclude junk values (`"unknown"`, `"NaN"`, `""`, internal test IDs) — the cheapest over-stitching prevention available.
14	6. Pre-compile review — Run through the validation checklist in `references/validation-checklist.md`.
15	7. Validate access — Run `pb validate access` to confirm the warehouse role can read the inputs and write to the output schema. Fix permission gaps here, before compiling.
16	8. Compile — Run `pb compile`. If it fails, fix one issue at a time and re-compile.
17	9. Pilot run — Offer `pb run --begin_time <ISO-8601>` only after compile succeeds and the user confirms.
18
19	## Confirmation Gates (5 mandatory)
20
21	Never proceed past a gate without explicit user approval:
22
23	1. Which warehouse connection to use?
24	2. Which tables to include as input sources?
25	3. Which columns for ID types and timestamps?
26	4. Entity name and which features to create?
27	5. Final YAML review before writing files?
28
29	## Critical Rules
30
31	These are the most common sources of broken projects. Violating any of them will cause compile or run failures:
32
33	- No placeholders. Never use names like `my_database`, `example_table`, `my_connection`, or `sample_schema`. Every resource name must come from MCP discovery or the user.
34	- Aggregation requirement. If an entity var has a `from` key, its `select` MUST use an aggregation function: `count`, `sum`, `max`, `min`, `avg`, `first_value`, or `last_value` (order-dependent ones need a `window:` with `order_by`). A bare column reference in `select` with `from` will fail.
35	- Var reference syntax. Reference another entity_var with the dot form `{{<entity_name>.<var_name>}}` — e.g., `'{{user.order_count}}'` for an entity named `user`. The first segment is the entity's name from pb_project.yaml, not the literal word `entity`. Quote the whole `select:` with single quotes. (The `{{user.Var("order_count")}}` function form also works but the dot form is preferred.)
36	- Model paths, not ref(). `from:` takes a path to a model — `inputs/<input_name>`, `models/<model_name>`, or `packages/<pkg>/...`. pb has no dbt-style `ref('...')` function.
37	- No date filters in YAML. Never add `WHERE` clauses with date filters in input or profile definitions. Use `pb run --begin_time` at runtime instead.
38	- Verify before using. Always confirm table and column existence with `describe_table()` before writing them into YAML. Do not trust user-provided names without verification.
39
40	## Writing Strategy
41
42	- Discover first, then draft YAML.
43	- Prefer the smallest correct project that compiles over a broad first draft.
44	- Show the final YAML or diff to the user before writing files.
45	- If `pb compile` fails, fix one issue at a time and re-run compile before making more edits.
46
47	## Credential Security
48
49	- Do not request secrets in chat during connection setup.
50	- If `pb init connection` prompts interactively, let the user complete that step in their

People who liked this also viewed

6 picks

Type

rudder-profiles-project

18stars0forks

View on GitHub

How to install rudder-profiles-project?

rudderlabs/rudder-agent-skills/rudder-profiles-project

$npx -y skills add rudderlabs/rudder-agent-skills --skill rudder-profiles-project

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# RudderStack Profiles Project Creation
2
3	Create a new Profiles project by discovering real warehouse resources first, then generating the three core YAML files with explicit user confirmation at each decision point.
4
5	## Workflow
6
7	1. Verify setup — Check that Profiles MCP tools are available. If not, send the user to `/rudder-profiles-setup`.
8	2. Discover connections — Call `get_existing_connections()`.
9	- If connections exist, present the list and let the user pick one.
10	- If no connections exist, instruct the user to run `pb init connection` in their terminal, wait for confirmation that it completed, then re-check with `get_existing_connections()`.
11	3. Discover tables — Call `input_table_suggestions()` for candidate tables. Call `describe_table()` on each candidate to confirm columns, types, and timestamps.
12	4. Confirm with user — Present discovered resources and get explicit approval (see confirmation gates below).
13	5. Generate YAML — Write `pb_project.yaml`, `models/inputs.yaml`, and `models/profiles.yaml` using only discovered names and the exact shapes in `references/basic-yaml-templates.md`. Derive `schema_version` from the installed binary (scaffold with `pb init pb-project` or MCP `setup_new_profiles_project()`; verify with `pb version`) — do not hardcode a remembered number. For each event-stream input set `contract: { is_event_stream: true, is_append_only: true }` plus `app_defaults.occurred_at_col` (the contract unlocks later incremental migration without a checkpoint-invalidating schema change, and `is_append_only` is rejected without `occurred_at_col`). Start with the default ID stitcher (no explicit `id_stitcher` model) unless the user needs custom edge sources. Add `filters:` on id_types to exclude junk values (`"unknown"`, `"NaN"`, `""`, internal test IDs) — the cheapest over-stitching prevention available.
14	6. Pre-compile review — Run through the validation checklist in `references/validation-checklist.md`.
15	7. Validate access — Run `pb validate access` to confirm the warehouse role can read the inputs and write to the output schema. Fix permission gaps here, before compiling.
16	8. Compile — Run `pb compile`. If it fails, fix one issue at a time and re-compile.
17	9. Pilot run — Offer `pb run --begin_time <ISO-8601>` only after compile succeeds and the user confirms.
18
19	## Confirmation Gates (5 mandatory)
20
21	Never proceed past a gate without explicit user approval:
22
23	1. Which warehouse connection to use?
24	2. Which tables to include as input sources?
25	3. Which columns for ID types and timestamps?
26	4. Entity name and which features to create?
27	5. Final YAML review before writing files?
28
29	## Critical Rules
30
31	These are the most common sources of broken projects. Violating any of them will cause compile or run failures:
32
33	- No placeholders. Never use names like `my_database`, `example_table`, `my_connection`, or `sample_schema`. Every resource name must come from MCP discovery or the user.
34	- Aggregation requirement. If an entity var has a `from` key, its `select` MUST use an aggregation function: `count`, `sum`, `max`, `min`, `avg`, `first_value`, or `last_value` (order-dependent ones need a `window:` with `order_by`). A bare column reference in `select` with `from` will fail.
35	- Var reference syntax. Reference another entity_var with the dot form `{{<entity_name>.<var_name>}}` — e.g., `'{{user.order_count}}'` for an entity named `user`. The first segment is the entity's name from pb_project.yaml, not the literal word `entity`. Quote the whole `select:` with single quotes. (The `{{user.Var("order_count")}}` function form also works but the dot form is preferred.)
36	- Model paths, not ref(). `from:` takes a path to a model — `inputs/<input_name>`, `models/<model_name>`, or `packages/<pkg>/...`. pb has no dbt-style `ref('...')` function.
37	- No date filters in YAML. Never add `WHERE` clauses with date filters in input or profile definitions. Use `pb run --begin_time` at runtime instead.
38	- Verify before using. Always confirm table and column existence with `describe_table()` before writing them into YAML. Do not trust user-provided names without verification.
39
40	## Writing Strategy
41
42	- Discover first, then draft YAML.
43	- Prefer the smallest correct project that compiles over a broad first draft.
44	- Show the final YAML or diff to the user before writing files.
45	- If `pb compile` fails, fix one issue at a time and re-run compile before making more edits.
46
47	## Credential Security
48
49	- Do not request secrets in chat during connection setup.
50	- If `pb init connection` prompts interactively, let the user complete that step in their

People who liked this also viewed

6 picks

Type