Official agent skill

Review Implement Phase

by prisma in prisma/orm

Implements triaged pull request review actions, commits focused fixes, posts status replies on GitHub and resolves the threads.

OfficialApache-2.0Auto-check passedDevelopment

Install Review Implement Phase

skills CLI
$ npx skills add prisma/orm --skill review-implement-phase -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install prisma/orm review-implement-phase --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/prisma/orm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills-contrib/review-implement-phase .claude/skills/review-implement-phase && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
review-implement-phase
GitHub stars
48k
Token cost
~1.7k tokens
SKILL.md length
771 words
Files
7 (incl. scripts)
Skills in repo
20
Repo updated
First seen
Licence
Apache-2.0

At a glance

Implements triaged pull request review actions, commits focused fixes, posts status replies on GitHub and resolves the threads.

  • Works in 6 steps: Read actions JSON and select actionable… → Preflight GitHub admin capability → Always post standalone comments (never… → …
  • Applying review comments that were already triaged as will_address
  • SKILL.md covers Inputs, Preconditions, Behavior and Ownership, plus 1 more section
  • Runs JavaScript scripts from its folder; calls node, gh and python

What it does

This is the implementation step of the review-framework loop. The agent takes the will_address rows with pending or in-progress status from a review-actions.json file, changes the code, commits in logical steps, posts GitHub status updates and updates each action's status. Inputs are the PR URL and an existing review-actions.json in the output directory, with an optional output directory (derived under wip/reviews when omitted) and optional limits to specific action IDs or files.

The preconditions are strict. review-actions.json must exist and be valid v2, node and gh must be on the PATH or the agent halts and asks you to install them, and GitHub admin capability is checked with check-github-admin-ready.mjs before work starts. If it is missing, you are pointed to the fetch and triage phases first. Scripts in the skill post replies to review threads and resolve them, and a review-implementer agent file ships with it.

When your agent uses it

  • Applying review comments that were already triaged as will_address
  • Replying to and resolving review threads after fixes are made
  • Running only the implementation phase of the review loop, not fetch or triage

Example prompts

  • “Implement the triaged review actions for this PR and resolve the threads when you are done.”
  • “Run the implement phase only for the actions that touch src/client.ts.”
  • “Check whether GitHub admin access is ready before implementing the review fixes.”

Requirements

  • Node.js and the GitHub CLI (gh) on the PATH
  • A review-actions.json produced by the fetch and triage phases
  • GitHub admin capability on the pull request

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Read actions JSON and select actionable rows
  2. Preflight GitHub admin capability
  3. Always post standalone comments (never pending PR reviews)
  4. Delegate implementation to
  5. Require implementer responsibilities
  6. Render latest action markdown

What it can do on your machine

Read from SKILL.md and the folder at commit 095af7a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 4 files in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node
    • gh
    • python
    • ruby

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Review Implement Phase loads about 1.7k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 771 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from prisma/orm at commit 095af7a, republished under its Apache-2.0 licence (© prisma). 771 words, ~1,729 tokens.

Download SKILL.mdSave it as .claude/skills/review-implement-phase/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from 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:

  • node (Node.js)
  • gh (GitHub CLI)

If either is missing, halt immediately and ask the user to install it. The implement-phase scripts require only node and gh.

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: gh api graphql -f query='query($owner:String!,$repo:String!,$pr:Int!,$before:String){viewer{login} repository(owner:$owner,name:$repo){pullRequest(number:$pr){reviews(last:100,states:PENDING,before:$before){pageInfo{hasPreviousPage startCursor} nodes{id author{login}}}}}}' -F owner=<owner> -F repo=<repo> -F pr=<number> --jq '.data as $d | $d.repository.pullRequest.reviews | {mine: [.nodes[] | select(.author.login == $d.viewer.login)], pageInfo}'
      • The author.login filter matters: another user's pending review is not yours to submit or dismiss, and must not block this workflow. --jq is gh's built-in filter and needs no jq binary.
      • The filter keeps pageInfo beside the matches, because an empty mine alone cannot tell "no pending review" from "the match is on an earlier page". Read both: while mine is empty and pageInfo.hasPreviousPage is true, re-run the query with -f before=<pageInfo.startCursor>. Conclude there is no pending review only when mine is empty and hasPreviousPage is false.
      • GitHub allows one pending review per user per PR, so mine holds at most one node across all pages.
      • If one exists, halt and clean it up (submit or dismiss) before continuing.
    • After posting any "On it" / "Done" comment:
      • Re-check for a pending review authored by the acting user, with the same filtered query and the same paging rule: keep reading pageInfo until mine is non-empty or hasPreviousPage is false.
      • If one exists, the workflow is blocked until it is 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:
Show full SKILL.md (264 more words)Show less
  • ./agents/review-implementer.md
  1. 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
  2. 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]

© prisma, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (scripts) in skills-contrib/review-implement-phase of prisma/orm.

  • SKILL.md
  • agents/review-implementer.md
  • package.json
  • scripts/check-github-admin-ready.mjs
  • scripts/post-review-thread-reply.mjs
  • scripts/resolve-review-thread.mjs
  • scripts/resolve-review-thread.test.mjs

Open the folder on GitHubat commit 095af7a

Compare with similar skills

Review Implement Phase next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Review Implement Phase compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review Implement Phase this skillprisma/orm48k—~1.7kAutomated safety check: PassApache-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
PR Finalize Reviewmicrosoft/garnet12k—~3.1kAutomated safety check: PassMIT
Fastlane Pull Request Reviewfastlane/fastlane42k—~550Automated safety check: PassMIT
Pull Request Reviewer for daisyUIsaadeghi/daisyui43k—~766Automated safety check: PassMIT
PR Review Analysisbreaking-brake/cc-wf-studio5.4k1 repos~626Automated safety check: PassCustom licence

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Finalize Review

    microsoft/garnet

    Official

    Checks that a pull request's title and description match its implementation and reviews the code for Garnet best practices, reporting findings without posting them.

    12k GitHub stars~3.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Reviews a fastlane pull request against its linked issue and the project guides, separating blocking from non-blocking findings and handling vulnerabilities privately.

    42k GitHub stars~550 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Reviews open pull requests in the daisyUI repository using read-only GitHub data and isolated base-versus-PR checks, then writes a merge verdict report.

    43k GitHub stars~766 tokensUpdated 7 days ago
    DevelopmentAuto-check passed
  • PR Review Analysis

    breaking-brake/cc-wf-studio

    Fetches review comments from a GitHub pull request, checks each one against the real code, rates it valid, invalid or partial, and can reply on GitHub.

    5.4k GitHub starsUsed in 1 repo~626 tokens
    DevelopmentAuto-check passed
  • Pull Request Babysitter

    thedotmack/claude-mem

    Keeps watching a pull request, fixing real review and CI problems and resolving stale threads, until it is clean and ready to merge.

    97k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check passed

More from prisma/orm

All 20 skills in this repo
  • Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed
  • Official

    Fetches a pull request's canonical review state as JSON, validates it, and renders markdown, a text summary and triage target files from it using bundled scripts.

    48k GitHub stars~767 tokensUpdated yesterday
    Auto-check passed
  • Official

    Runs the triage step of the review-framework loop: reads fetched PR review state, builds `review-actions.json`, validates it and renders `review-actions.md`.

    48k GitHub stars~995 tokensUpdated yesterday
    Auto-check passed
  • Official

    Replaces a plain TypeScript union plus switch statements with frozen subclasses and a visitor interface when several places dispatch on the same variants.

    48k GitHub stars~830 tokensUpdated yesterday
    Auto-check passed
  • Official

    Guides an outside contributor through opening a prisma/orm pull request from a fork that follows CONTRIBUTING.md and passes review on the first round.

    48k GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed
  • Official

    Creates a GitHub pull request for the Prisma repo with a Linear-ticket-prefixed title and a decision-led narrative description, inferring the ticket from context.

    48k GitHub stars~4.6k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Review Implement Phase

What does Review Implement Phase do?

Implements triaged pull request review actions, commits focused fixes, posts status replies on GitHub and resolves the threads. This is the implementation step of the review-framework loop.json file, changes the code, commits in logical steps, posts GitHub status updates and updates each action's status.

When should I use Review Implement Phase?

Review Implement Phase fits situations like: applying review comments that were already triaged as will_address; replying to and resolving review threads after fixes are made; running only the implementation phase of the review loop, not fetch or triage.

How do I install Review Implement Phase in Claude Code?

Run `npx skills add prisma/orm --skill review-implement-phase -a claude-code`. Or copy the skill folder (skills-contrib/review-implement-phase in prisma/orm) into .claude/skills/review-implement-phase in your project. Claude Code loads it when a task matches its description.

How do I install Review Implement Phase in Codex?

Run `npx skills add prisma/orm --skill review-implement-phase -a codex`. Or copy the skill folder (skills-contrib/review-implement-phase in prisma/orm) into .agents/skills/review-implement-phase in your project. Codex loads it when a task matches its description.

Can I use Review Implement Phase in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add prisma/orm --skill review-implement-phase -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-implement-phase, .gemini/skills/review-implement-phase, .github/skills/review-implement-phase and .opencode/skills/review-implement-phase in your project.

What does Review Implement Phase need to run?

Going by SKILL.md and its folder, Review Implement Phase needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node, gh, python and ruby). Our summary lists: Node.js and the GitHub CLI (gh) on the PATH; A review-actions.json produced by the fetch and triage phases; GitHub admin capability on the pull request.

Does Review Implement Phase access the network?

SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Review Implement Phase safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Review Implement Phase use?

Review Implement Phase is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Review Implement Phase use?

About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Review Implement Phase?

Skills that share tags, products or a category with Review Implement Phase: PR Babysitter (openinterpreter/openinterpreter, 69k stars), PR Finalize Review (microsoft/garnet, 12k stars), Fastlane Pull Request Review (fastlane/fastlane, 42k stars) and Pull Request Reviewer for daisyUI (saadeghi/daisyui, 43k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review Implement Phase?

prisma (a GitHub organization, an official publisher) maintains it in prisma/orm, which has 47,701 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 6, 2026.

Source: prisma/orm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.