Add --noob onboarding-context mode to pr-approval skill - #7
Open
martensonbj wants to merge 1 commit into
Open
Conversation
Adds an opt-in --noob flag (alias --eli5) for review mode. When set, each per-PR analyst card opens with an "ELI5 & how we got here" block: a plain- language statement of what the PR is trying to do, plus a short lineage of the predecessor issues / PRs / ADRs that made it necessary -- context a first-time reader of the repo can't reconstruct from the diff alone. Off by default and ignored in triage (which stays a cheap, no-deep-read sweep). Length-capped so it leads a decision card, not a wiki page. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Adds an opt-in
--noobflag (alias--eli5) to thepr-approvalskill's review mode.When set, each per-PR analyst card opens with an "ELI5 & how we got here" block:
Off by default; ignored in triage (kept as a cheap, no-deep-read sweep); length-capped (~150 words) so it leads a decision card rather than turning into a wiki page.
Why
Reviewers rotate onto repos and bodies of work they're new to. A diff shows what changed but not the arc that made the change necessary — a feature that was "done on paper" a few tickets ago but never actually ran, an infra blocker fixed out-of-band, a superseded approach. That lineage usually lives only in the author's head or scattered across tickets.
--noobsurfaces it inline so someone reviewing cold can trust their call, without adding noise for reviewers who already have the context (hence off-by-default).How it flows
R1parses the flag →R2walks the Linear "Follows / Context" lineage (not just the PR's own issue) →R3hands the analyst the traced lineage + the instruction →R4renders the block first in each card (context before verdict).Validation
Tried live on two stacked PRs (an experimental-harness install + its follow-up). The block correctly surfaced context invisible in the diffs — e.g. "this feature was marked done three tickets ago but never actually ran because the binary was missing from the sandbox image." Tightened the length cap after a first pass came out wiki-length.
🤖 Generated with Claude Code