[v3-2-test] Add AI-driven prepare-providers-documentation skill (#65882)#66169
Merged
[v3-2-test] Add AI-driven prepare-providers-documentation skill (#65882)#66169
Conversation
* Add AI-driven prepare-providers-documentation skill Add a Claude Code skill that replaces the manual commit-by-commit classification step in `breeze release-management prepare-provider-documentation` with AI-driven analysis. The skill inspects every PR using sub-agents, scopes multi-provider PRs to the current provider's slice, applies an explicit breaking-change checklist against the actual diff, asks the release manager only when uncertain, and covers both the initial classification and the rebase-time incremental update flow. Auto-generated build files are still regenerated by breeze under the hood, so the skill stays consistent with existing release tooling. The interactive breeze command remains documented as a fallback. * Address review feedback on prepare-providers-documentation skill - Scope breaking-change checklist's "public symbol removed/renamed" rule to the actual public-interface paths (hooks, operators, sensors, triggers, notifications, decorators, executors, top-level package, and anything referenced from provider.yaml) so internal helpers like utils/, _internal/, or pod_manager.py don't auto-trigger BREAKING_RISK. - Extend "schema change in stored data" rule to cover the serialized state/context of BaseTrigger subclasses, so changes that would break deferred tasks running across a provider upgrade are flagged. - Document prerequisites in dev/README_RELEASE_PROVIDERS.md: the skill needs an agentic coding framework with the GitHub MCP server configured. Show install steps for Claude Code and OpenAI Codex CLI. - Generalise README references so the skill is presented as framework-neutral (loaded by Claude Code, OpenAI Codex CLI, or any MCP-compatible client that discovers SKILL.md from .claude/skills/), rather than Claude Code-exclusive. (cherry picked from commit 1b3bf55) Co-authored-by: Jarek Potiuk <jarek@potiuk.com>
6 tasks
potiuk
requested review from
amoghrajesh,
ashb,
bugraoz93,
choo121600,
jason810496,
jedcunningham,
jscheffl,
kaxil,
potiuk,
shahar1 and
vincbeck
as code owners
4 tasks
potiuk
added a commit
that referenced
this pull request
May 2, 2026
…#66275) The `insert-license` agentic-markdown hook on v3-2-test cannot detect license headers placed below YAML frontmatter, so it prepends a second license at the top of the file. That break also confuses markdownlint: the `---` line of the frontmatter, after a blank line, gets parsed as a setext-H2 underline, and every later `# ...` heading then fails MD003. This started failing on v3-2-test once #66169 landed `.github/skills/prepare-providers-documentation/SKILL.md`, which is not on the existing per-file exclude list. The same issue was solved on `main` in #65776 (commit 0960ad2) by passing `--detect-license-in-X-top-lines '30'` to the SHORT_LICENSE hook so it recognises an existing license inside the first 30 lines of the file. Backport only the `.pre-commit-config.yaml` change from that PR — not the new `aip-user-stories` skill that shipped alongside it — and add the matching license header inside `.github/instructions/code-review.instructions.md` (so it does not regress once `.github/instructions/` is no longer blanket-excluded).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add a Claude Code skill that replaces the manual commit-by-commit
classification step in
breeze release-management prepare-provider-documentationwith AI-driven analysis. The skillinspects every PR using sub-agents, scopes multi-provider PRs to the
current provider's slice, applies an explicit breaking-change checklist
against the actual diff, asks the release manager only when uncertain,
and covers both the initial classification and the rebase-time
incremental update flow.
Auto-generated build files are still regenerated by breeze under the
hood, so the skill stays consistent with existing release tooling. The
interactive breeze command remains documented as a fallback.
to the actual public-interface paths (hooks, operators, sensors,
triggers, notifications, decorators, executors, top-level package, and
anything referenced from provider.yaml) so internal helpers like
utils/, _internal/, or pod_manager.py don't auto-trigger BREAKING_RISK.
state/context of BaseTrigger subclasses, so changes that would break
deferred tasks running across a provider upgrade are flagged.
needs an agentic coding framework with the GitHub MCP server
configured. Show install steps for Claude Code and OpenAI Codex CLI.
framework-neutral (loaded by Claude Code, OpenAI Codex CLI, or any
MCP-compatible client that discovers SKILL.md from .claude/skills/),
rather than Claude Code-exclusive.
(cherry picked from commit 1b3bf55)
Co-authored-by: Jarek Potiuk jarek@potiuk.com