Agent skill

Update PR Review

by Terry-Mao in Terry-Mao/AICodingFlow

Improve repo-local PR review companion skills from human feedback on bot reviews.

MITAuto-check passedDevelopment

Install Update PR Review

skills CLI
$ npx skills add Terry-Mao/AICodingFlow --skill update-pr-review -a claude-code

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

GitHub CLI
$ gh skill install Terry-Mao/AICodingFlow update-pr-review --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/Terry-Mao/AICodingFlow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/update-pr-review .claude/skills/update-pr-review && 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
update-pr-review
GitHub stars
167
Token cost
~1.1k tokens
SKILL.md length
514 words
Files
4 (incl. scripts)
Skills in repo
30
Repo updated
First seen
Licence
MIT

At a glance

Improve repo-local PR review companion skills from human feedback on bot reviews.

  • Works in 5 steps: Read the aggregated feedback JSON… → Identify repeated human-feedback… → Convert those patterns into concise… → …
  • Updating review guidance from recent GitHub PR review feedback
  • SKILL.md covers Workflow, Output Contract, Learn And Edit and Write Routing, plus 2 more sections
  • Runs Python scripts from its folder

What it does

Update PR Review is an agent skill from Terry-Mao/AICodingFlow. Improve repo-local PR review companion skills from human feedback on bot reviews. Use when updating review guidance from recent GitHub PR review feedback.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/aggregate_review_feedback.py`, `scripts/apply_guidance_output.py` and `scripts/validate_write_surface.py`).

It sits in Development, covering Pull requests. It works with GitHub. The repository describes itself as: Setup a AI Coding Flow. The licence is MIT.

When your agent uses it

  • Updating review guidance from recent GitHub PR review feedback
  • Tasks that involve Pull requests

Example prompts

  • “/update-pr-review”

Requirements

  • Python 3

Workflow steps

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

  1. Read the aggregated feedback JSON provided by the runner.
  2. Identify repeated human-feedback patterns or stable repo preferences.
  3. Convert those patterns into concise repo-specific guidance.
  4. Write proposed local companion skill content to update-pr-review-output/.
  5. Stop; the runner validates and publishes the result.

What it can do on your machine

Read from SKILL.md and the folder at commit 7703e16. 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 3 files in scripts/ (Python), which the agent can run.

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

  • Network

    No URLs in SKILL.md.

    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

Update PR Review loads about 1.1k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 514 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 Terry-Mao/AICodingFlow at commit 7703e16, republished under its MIT licence (© Terry-Mao). 514 words, ~1,062 tokens.

Download SKILL.mdSave it as .claude/skills/update-pr-review/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
update-pr-review
description
Improve repo-local PR review companion skills from human feedback on bot reviews. Use when updating review guidance from recent GitHub PR review feedback.

update-pr-review

Use this skill to turn human feedback on bot PR reviews into concise updates to repo-local review companion skills.

This skill owns only the self-evolution logic: how to turn aggregated human feedback into local review guidance. The GitHub Actions runner owns data collection, write-surface validation, commits, pushes, and PR creation. When run inside GitHub Actions, .agents may be read-only. Write proposed changes only to update-pr-review-output/; the runner applies them.

Workflow

  1. Read the aggregated feedback JSON provided by the runner.
  2. Identify repeated human-feedback patterns or stable repo preferences.
  3. Convert those patterns into concise repo-specific guidance.
  4. Write proposed local companion skill content to update-pr-review-output/.
  5. Stop; the runner validates and publishes the result.

Output Contract

Always write update-pr-review-output/status.json:

json
{
  "status": "changed",
  "reason": "Brief evidence summary.",
  "updated_files": [".github/skills/review-pr-repo/SKILL.md"]
}

Allowed statuses:

  • changed when guidance should be updated
  • no_change when evidence is insufficient or already covered
  • error when feedback cannot be interpreted safely

Use no_change when there is no human evidence. Agent-only feedback is not enough to update guidance.

For changed, write the complete replacement content for each updated file:

  • update-pr-review-output/review-pr-repo/SKILL.md
  • update-pr-review-output/review-spec-repo/SKILL.md

Do not edit .agents directly.

Learn And Edit

Read the JSON and look for patterns worth adding to local review rules:

  • humans clearly said an agent comment was wrong
  • the finding was directionally right, but severity, scope, or line target was wrong
  • the comment was not actionable
  • reviewers repeatedly emphasized a repo-specific check
  • human-only review threads reveal stable repo preferences
  • a pattern belongs in the top-level summary instead of inline comments

Use agent_comments only as context for what the agent said. Do not update guidance from agent_comments alone. Require human evidence from human_review_comments, human conversation_comments, or human-authored review bodies/comments.

Turn concrete feedback into repo-specific guidance:

  1. Start from the specific human feedback.
  2. Find repeated patterns or stable repo preferences.
  3. Abstract the pattern into guidance that applies to future reviews.
  4. Merge it into the most relevant existing section.
  5. Keep the final wording concise.
Show full SKILL.md (195 more words)Show less

Acceptable edits:

  • add a bullet to an existing section
  • add a small section when no existing section fits
  • rewrite an existing rule to make it more accurate
  • make no change when the evidence is too weak

Do not:

  • paste raw JSON into skill files
  • write a chronological summary of PR feedback
  • add a rule for one reviewer's one-off preference
  • add a rule based only on agent comments
  • weaken correctness, security, or data-loss checks from one disagreement
  • override the core review contract

Write Routing

Use each PR's review_type:

  • code -> .github/skills/review-pr-repo/SKILL.md
  • spec -> .github/skills/review-spec-repo/SKILL.md

Skip a file when that feedback type has no useful pattern.

Boundaries

Allowed write surface:

  • .github/skills/review-pr-repo/
  • .github/skills/review-spec-repo/

Forbidden write surface:

  • .github/skills/review-pr/SKILL.md
  • .github/skills/review-spec/SKILL.md
  • other core skills or product code

Local companion skills may specialize repo preferences, but must not change the core review contract: output schema, severity labels, diff-line targeting, snapshot rules, validation rules, or safety rules.

Handoff

After writing output files, re-read the proposed skill content and keep it concise. Do not run Git commands, push branches, create PRs, edit workflow files, or edit .agents directly as part of this skill. The runner must apply output files and validate the write surface before publishing.

© Terry-Mao, MIT. 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 3 other files (scripts) in .github/skills/update-pr-review of Terry-Mao/AICodingFlow.

  • SKILL.md
  • scripts/aggregate_review_feedback.py
  • scripts/apply_guidance_output.py
  • scripts/validate_write_surface.py

Open the folder on GitHubat commit 7703e16

Compare with similar skills

Update PR Review 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.

Update PR Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Update PR Review this skillTerry-Mao/AICodingFlow167—~1.1kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Create Pull Requestcline/cline70k1 repos~1.6kAutomated safety check: PassApache-2.0
Pull Request Title and Body Writeropeninterpreter/openinterpreter69k2 repos~1.1kAutomated safety check: PassApache-2.0

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
  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed
  • Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed
  • Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed
  • Pull Request Title and Body Writer

    openinterpreter/openinterpreter

    Rewrites the title and body of one or more pull requests with gh, leading with why the change was made, then what changed, and describing only the net result.

    69k GitHub starsUsed in 2 repos~1.1k tokens
    DevelopmentAuto-check passed
  • 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
    DevelopmentAuto-check passed

More from Terry-Mao/AICodingFlow

All 30 skills in this repo
  • PR Walkthrough

    Terry-Mao/AICodingFlow

    Generate a local static interactive D3 walkthrough of a pull request.

    167 GitHub stars~2.1k tokensUpdated 7 days ago
    Auto-check passed
  • Implement Issue

    Terry-Mao/AICodingFlow

    Implement a GitHub issue in this repository by applying the local shared implement-specs workflow with repository-specific issue, spec-context, and summary-file handling.

    167 GitHub stars~2.3k tokensUpdated 7 days ago
    Auto-check passed
  • Implement Specs

    Terry-Mao/AICodingFlow

    Implement an approved feature from the repository's product and tech specs, keeping specs and code aligned in the same change as implementation evolves.

    167 GitHub stars~1.7k tokensUpdated 7 days ago
    Auto-check passed
  • Review PR

    Terry-Mao/AICodingFlow

    Review a GitHub pull request from pinned prdescription.txt, prdiff.txt, and optional speccontext.md snapshots, then write and validate review.json.

    167 GitHub stars~1k tokensUpdated 7 days ago
    Auto-check passed
  • Update Dedupe

    Terry-Mao/AICodingFlow

    Learn repo-local duplicate issue guidance from recent maintainer duplicate closures and propose updates to the dedupe companion skill.

    167 GitHub stars~1.1k tokensUpdated 7 days ago
    Auto-check passed
  • Update Triage

    Terry-Mao/AICodingFlow

    Learn repo-local issue triage guidance from recent maintainer triage corrections and propose updates to the triage companion skill or label config.

    167 GitHub stars~1.5k tokensUpdated 7 days ago
    Auto-check passed

Works with

Categories

Questions about Update PR Review

What does Update PR Review do?

Improve repo-local PR review companion skills from human feedback on bot reviews. Update PR Review is an agent skill from Terry-Mao/AICodingFlow. Improve repo-local PR review companion skills from human feedback on bot reviews.

When should I use Update PR Review?

Update PR Review fits situations like: updating review guidance from recent GitHub PR review feedback; tasks that involve Pull requests.

How do I install Update PR Review in Claude Code?

Run `npx skills add Terry-Mao/AICodingFlow --skill update-pr-review -a claude-code`. Or copy the skill folder (.github/skills/update-pr-review in Terry-Mao/AICodingFlow) into .claude/skills/update-pr-review in your project. Claude Code loads it when a task matches its description.

How do I install Update PR Review in Codex?

Run `npx skills add Terry-Mao/AICodingFlow --skill update-pr-review -a codex`. Or copy the skill folder (.github/skills/update-pr-review in Terry-Mao/AICodingFlow) into .agents/skills/update-pr-review in your project. Codex loads it when a task matches its description.

Can I use Update PR Review 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 Terry-Mao/AICodingFlow --skill update-pr-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/update-pr-review, .gemini/skills/update-pr-review, .github/skills/update-pr-review and .opencode/skills/update-pr-review in your project.

What does Update PR Review need to run?

Going by SKILL.md and its folder, Update PR Review needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Update PR Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Update PR Review 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 Update PR Review use?

Update PR Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Update PR Review use?

About 1.1k tokens (SKILL.md is roughly 4.2k 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 Update PR Review?

Skills that share tags, products or a category with Update PR Review: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars) and Create Pull Request (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Update PR Review?

Terry-Mao (a GitHub user) maintains it in Terry-Mao/AICodingFlow, which has 167 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 3, 2026.

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