lfx-v2-newsletter-service

Cut a new GitHub release/tag for lfx-v2-newsletter-service from main, verify the tagged build published the image and Helm chart, then open a version-bump PR on lfx-v2-argocd pinning the target environments to the new version. Use when the user asks to "cut a release", "release a new version", or "bump the newsletter service in argocd".

How to drive an open lfx-v2-newsletter-service pull request through the agentic review flow: read the lfx-reviewer "Agentic review check" comment, fix or rebut every blocking finding, answer every review thread, push one batched round at a time, and loop until the check is green on the current head with every thread answered — then report the ending: needs-human review before merge, or clear for the gate/automerge path. Use whenever a PR is open on this repo and the work involves review iteration — responding to Copilot or conductor findings, checking why `agentic-review/clean` is failing or why the gate has not approved, handling the `needs-human` label, or pushing fixes to an open PR. This is the PR driver's operating manual: the driver is a worktree-isolated background agent that works the PR autonomously (fixes, rebuttals, replies, pushes). The main session only launches the driver right after opening any PR here — with a minimal prompt pointing at this skill — and relays its round notes.

The exact format for the two verdict comments the agentic review posts on a lfx-v2-newsletter-service pull request: the needs-human verdict (escalation) and the agentic-check verdict (conductor). Use whenever you post either verdict. Defines the human presentation and the machine-readable markers that the deterministic apply step parses, so writer and reader stay in sync.

Conduct an lfx-v2-newsletter-service pull request to a clean state: reconcile the AI reviewers' threads against the latest commits and developer replies, work with the engineer on findings that go against the architecture, and report whether the change is clean. Use when the task is to check whether AI-review findings are fixed or validly rebutted and to update the agentic gate. Posts one machine-readable agentic-check comment plus a summary of open blockers.

Decide whether an lfx-v2-newsletter-service pull request needs a human's sign-off before it can merge (the needs-human gate), regardless of code quality. Use when the task is the needs-human escalation on a PR. Posts a single machine-readable needs-human verdict comment via add_issue_comment.

Senior code-review method for lfx-v2-newsletter-service pull requests. Use when the task is to review a PR for correctness, design, and security and post review comments on this repo. Posts inline severity-tagged comments plus a summary on the PR itself.

Detailed boundaries behind the needs-human decision for lfx-v2-newsletter-service: the critical surfaces (auth, the unauthenticated surface, schema, send behavior), shared and cross-repo contracts, scale-with-importance, and pipeline/supply-chain. Load this whenever judging whether a newsletter-service PR needs a human, as the detail behind the `needs-human-escalation` skill.

How to judge the implementation of an lfx-v2-newsletter-service pull request: the general quality dimensions (correctness, error handling, tests, performance, readability, code truthfulness) and how to hold the diff to the repo's documented standards. Use on every PR that changes code, however small; this is the reviewer's line-level lens. Security has its own skill (newsletter-security-review).

Security review for lfx-v2-newsletter-service pull requests. Use when a PR touches a handler, auth, persistence, the dispatch path, recipient data, config, or the chart. Applies a diff-aware, high-confidence, low-false-positive methodology (adapted from Anthropic's claude-code-security-review) to this service's durable threat anchors: recipient PII, the deliberately unauthenticated endpoints, JWT verification, gateway-delegated authorization, SQL construction, and secrets. Discovers the concrete guards from the code at review time; this skill carries the method, not an inventory.