Skip to content

feat: add support for skills#109

Open
twishabansal wants to merge 19 commits intomainfrom
feat-skills
Open

feat: add support for skills#109
twishabansal wants to merge 19 commits intomainfrom
feat-skills

Conversation

@twishabansal
Copy link
Contributor

@twishabansal twishabansal commented Feb 27, 2026

Does not yet contain support for multiple sub-toolsets for cloudsql postgres

@github-actions github-actions bot requested a review from Myst9 February 27, 2026 07:40
@twishabansal twishabansal changed the title Feat skills feat: add support for skills Feb 27, 2026
@twishabansal twishabansal removed the request for review from Myst9 February 27, 2026 07:41
@twishabansal twishabansal changed the base branch from main to license-fix March 2, 2026 07:53
@twishabansal twishabansal marked this pull request as ready for review March 2, 2026 08:02
@twishabansal twishabansal requested review from a team as code owners March 2, 2026 08:02
Base automatically changed from license-fix to main March 2, 2026 08:02
@twishabansal twishabansal added the do not merge Indicates a pull request not ready for merge, due to either quality or timing. label Mar 3, 2026
## Use Full Table Name Format "DATABASE_NAME.SCHEMA_NAME.TABLE_NAME"

**ALWAYS** use the full table name format, `DATABASE_NAME.SCHEMA_NAME.TABLE_NAME` in the generated SQL when using the `execute_sql` or `cloud_sql_postgresql__execute_sql` tool.
**ALWAYS** use the full table name format, `DATABASE_NAME.SCHEMA_NAME.TABLE_NAME` in the generated SQL when using the `execute_sql` or `cloud_sql_postgresql__execute_sql` skill.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: should we update this to be execute_sql script?

}
},
"contextFileName": "CLOUD-SQL-POSTGRESQL.md",
"settings": [
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Have you tested with the settings in the .env and having the extension load in the env vars? Does this allow the agents to use these variables without additional input from the user?

kind: sources
name: cloud-sql-admin-source
type: cloud-sql-admin
defaultProject: twisha-dev
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Haoyu's implementation is suppose to propagate the Env var placeholders from the prebuilt tools to here. It doesn't seem like that's working.

"type": "string"
},
"project": {
"default": "twisha-dev",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

need to propagate env var here too

ipType: public
database: inventory
user: postgres
password: TestPassword1@
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you force override this commit to remove this from the git history?

@@ -0,0 +1,704 @@
---
name: cloudsql-postgres
description: skill for running tool operations in CloudSql postgres
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

For the first iteration, we will have to manually add the descriptions since Grouping (with the descriptions) most likely wont be complete.

@@ -0,0 +1,12 @@
kind: tools
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We may need to update Haoyu's implementation to add the license or add that during the generation process

@helloeve
Copy link

helloeve commented Mar 4, 2026

Thank you Twisha for authoring this PR! After looking at the generated config, I realized there should be some improvements done to the skill generation logic we previously introduced.

  • As Averi pointed out, the env variable placeholder for defining the sources are not propagated as the current generation logic will rely on the parsed version of the environment variable rather than leaving it as a placeholder.
  • The generated skill.md is too large and I think we may want to move the tool-specific parameter definition into its own file under references/ to take advantages from skill's dynamic loading capability.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

do not merge Indicates a pull request not ready for merge, due to either quality or timing.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants