review-implement-phase
$
npx mdskill add prisma/prisma-next/review-implement-phaseExecutes triaged review fixes and commits changes
- Applies code modifications for actions marked to be addressed.
- Uses GitHub CLI gh and action status APIs for execution.
- Filters tasks by decision type will_address or pending state.
- Commits logical steps, posts updates, and resolves threads.
SKILL.md
.github/skills/review-implement-phaseView on GitHub ↗
---
name: review-implement-phase
description: Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
argument-hint: "[pr-url] [output-dir]"
---
# Review Implement Phase
Run only the implementation phase of the review-framework loop:
take triaged `will_address` actions, make code changes, commit in logical steps, post GitHub status updates, and update action status.
Run commands from this skill directory. All script paths below are relative to it.
## Inputs
- Required:
- PR URL
- existing `review-actions.json` in output dir
- Optional:
- output directory
- scope constraints (specific action IDs or files)
If output directory is omitted, derive:
`wip/reviews/<owner>_<repo>_pr-<number>/`
## Preconditions
`<output-dir>/review-actions.json` must exist and be valid v2.
System dependencies required on PATH:
- `gh` (GitHub CLI)
If `gh` is missing, halt immediately and ask the user to install it. The implement-phase scripts no longer depend on `jq`.
GitHub admin capability must be available before starting implementation:
```bash
node ./scripts/check-github-admin-ready.mjs --pr <PR_URL>
```
If missing, instruct user to run:
- `/review-fetch-phase <PR_URL> [output-dir]`
- `/review-triage-phase <PR_URL> [output-dir]`
## Behavior
1. Read actions JSON and select actionable rows:
- `decision: will_address`
- `status: pending | in_progress`
2. Preflight GitHub admin capability:
- run `check-github-admin-ready.mjs` and fail fast if unavailable
3. Always post standalone comments (**never pending PR reviews**):
- When posting progress updates, do **not** create a PR review (draft/pending or otherwise).
- Forbidden flows:
- `gh pr review --comment ...`
- GraphQL `addPullRequestReview`, `addPullRequestReviewComment`, `addPullRequestReviewThread` (this workflow never uses pending reviews)
- Allowed flows:
- thread replies via `addPullRequestReviewThreadReply` (or wrapper script)
- issue comments via `addComment` (or wrapper script)
- Before starting implementation:
- **Detect pending reviews authored by the acting user** on this PR.
- If any exist, **halt** and clean them up (submit or dismiss) before continuing.
- After posting any "On it" / "Done" comment:
- **Re-check for pending reviews authored by the acting user**.
- If any exist, the workflow is **blocked** until they are cleaned up.
- Implementation requirement:
- For `review_thread` targets, always reply using **thread replies** (never inline PR review comments).
- If you only have the thread node id, first fetch the thread’s primary comment node id, then call `addPullRequestReviewThreadReply`.
- For `pull_request_review` targets (review-body findings, `PRR_…` node ids), inline replies are not possible. `post-review-thread-reply.mjs` auto-detects this and posts a top-level PR issue comment instead (response `kind: "issue_comment"`); there is no thread to resolve, so the implementer skips `resolve-review-thread.mjs` for these and records the issue-comment id in the action's `done` record.
4. Delegate implementation to:
- `./agents/review-implementer.md`
5. Require implementer responsibilities:
- make code changes
- run relevant checks
- create focused commits
- post "On it" when starting each action
- post "Done" when finished (universal); resolve the thread **only when `target.kind === "review_thread"`** and a `threadNodeId` is available. `pull_request_review` targets have no inline thread, so the implementer skips the resolve step for them and records the issue-comment id in the action's `done` record (per behavior step 3).
- use encoded helper scripts for thread admin operations:
- `node ./scripts/post-review-thread-reply.mjs --repo <owner>/<repo> --pr <number> --comment-node-id <primaryCommentNodeId> --body "<text>"` (works for both `review_thread` and `pull_request_review` — auto-detects node kind)
- `node ./scripts/resolve-review-thread.mjs --thread-node-id <threadNodeId>` (only for `review_thread` targets)
- comments must be posted as individual standalone comments/replies, never as part of a pending review
- after each action completion (Done + resolve when applicable), verify no new pending review was created by the acting user
- never use inline parser snippets (for example: `python -c`, `node -e`, `ruby -e`, ad-hoc awk/sed JSON parsing)
- only set `status: done` after Done (and, for `review_thread` targets, resolve) succeeds
- update `review-actions.json` (`status`, `done.doneAt`, `done.summary`, `done.commits`) in the same completion step
6. Render latest action markdown:
```bash
node ../review-triage-phase/scripts/render-review-actions.mjs --in <output-dir>/review-actions.json --out <output-dir>/review-actions.md
```
## Ownership
- This phase owns actual fixes plus posting Done and resolving completed threads.
- If GitHub thread reply/resolve cannot be performed, the phase is blocked and must not report completion.
- If comments were accidentally posted as a pending review, the phase is blocked until the pending review is explicitly submitted or dismissed and the action comments are re-posted as standalone comments.
## Output to user
Return:
- commits created
- actions transitioned to done
- written artifacts (`review-actions.json`, `review-actions.md`)
Suggest next steps:
- `/review-fetch-phase <PR_URL> [output-dir]`
- `/review-triage-phase <PR_URL> [output-dir]`
More from prisma/prisma-next
- adr-review>-
- ast-visitor-pattern>-
- bumping-biomeBumps `biome` package versions (e.g. `@biomejs/biome`) using `pnpm`, aligns `biome.jsonc` files with the new version/s across the repository and runs biome-related checks. Use when required to update `biome` to a newer version - explicitly or implicitly (e.g. after running `pnpm up`, `pnpm update`, `pnpm upgrade` without specific package names).
- contrib-prOpen a high-quality external contributor PR against prisma-next. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.
- drive-agent-personasLibrary of agent personas — named bias-frames that other skills load to shift execution-time defaults. Skills name a persona by ID (e.g. "Adopt the architect persona"), and this skill resolves that ID to the persona doc that frames the executor for the rest of the task. Use when authoring a new skill that needs a particular reviewer/implementer/orchestrator stance, or when an existing skill instructs you to adopt a named persona.
- drive-create-plan>
- drive-create-project>
- drive-create-spec>
- drive-discussionDrops the agent into a structured Q&A mode that iterates with the user toward a complete understanding of a topic, then documents the outcome (project spec, plan, decision record, or whatever shape fits). The agent adopts one or more personas from the `drive-agent-personas` library — named explicitly by the user, or inferred from conversation context and announced. Typical use is design work at the start of a task, or mid-implementation when a load-bearing assumption has been falsified. Use ONLY when the user explicitly invokes this skill (e.g. "discussion mode", "pressure-test this", "let's design this", "design mode", "tech design mode", "product mode", "pm mode", "challenge my idea"). Never auto-invoke.
- drive-orchestrate-plan>