Agent skill

Review PR Description

by tbhb in tbhb/vale-ai-tells

Review a drafted pull request description in PRAGENTDESC.md against the branch it would publish, as an independent agent, for what mechanical checking can't see.

Apache-2.0Auto-check passedDevelopment

Install Review PR Description

skills CLI
$ npx skills add tbhb/vale-ai-tells --skill review-pr-description -a claude-code

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

GitHub CLI
$ gh skill install tbhb/vale-ai-tells review-pr-description --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/tbhb/vale-ai-tells.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/review-pr-description .claude/skills/review-pr-description && 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-pr-description
GitHub stars
117
Token cost
~1.7k tokens
SKILL.md length
990 words
Files
2
Skills in repo
27
Repo updated
First seen
Licence
Apache-2.0

At a glance

Review a drafted pull request description in PRAGENTDESC.md against the branch it would publish, as an independent agent, for what mechanical checking can't see.

  • Tasks that involve Pull requests
  • SKILL.md covers The repository, Gather the inputs, What's already settled and What to check, plus 2 more sections
  • Calls git

What it does

Review PR Description is an agent skill from tbhb/vale-ai-tells. Review a drafted pull request description in PRAGENTDESC.md against the branch it would publish, as an independent agent, for what mechanical checking can't see. Covers claims the diff doesn't support, counting, provenance filler, restating the diff, a title describing one commit rather than the branch, and whether the branch is one coherent change. The pr skill invokes this before opening every pull request, passing the repository root.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `tokens.json`).

It sits in Development, covering Pull requests. It works with Git. The repository describes itself as: In today's rapidly evolving landscape, vale-ai-tells is a comprehensive, cutting-edge Vale style package that empowers writers to seamlessly delve into the rich tapestry of AI…. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Pull requests

Example prompts

  • “t see. Covers claims the diff doesn”
  • “/review-pr-description”

What it can do on your machine

Read from SKILL.md and the folder at commit 4c7abc9. 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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, 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 PR Description loads about 1.7k tokens when it runs. Until then it costs about 116 tokens; SKILL.md has 990 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~116
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); files beside SKILL.md are not scanned.

SKILL.md

The full file from tbhb/vale-ai-tells at commit 4c7abc9, republished under its Apache-2.0 licence (© tbhb). 990 words, ~1,745 tokens.

Download SKILL.mdSave it as .claude/skills/review-pr-description/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
review-pr-description
description
Review a drafted pull request description in PR_AGENTDESC.md against the branch it would publish, as an independent agent, for what mechanical checking can't see. Covers claims the diff doesn't support, counting, provenance filler, restating the diff, a title describing one commit rather than the branch, and whether the branch is one coherent change. The pr skill invokes this before opening every pull request, passing the repository root.
license
Apache-2.0
context
fork
agent
Explore
background
false

Review a drafted pull request description

Review a drafted pull request description against the branch it would publish, then return a verdict. You're the independent check. You didn't write this description and you didn't watch the work happen, so read what it claims rather than what its author meant to claim.

The repository

$ARGUMENTS

Treat that path as the repository under review. An empty value means the current working directory. Bind it once and use it throughout:

bash
REPO="${ARGUMENTS:-$(pwd)}"

Gather the inputs

Run these before judging anything:

  • cat "$REPO/PR_AGENTDESC.md" for the draft
  • sed -n '/^base:/p' "$REPO/PR_AGENTDESC.md" for the base branch the rest of these need
  • git -C "$REPO" log --reverse --pretty=format:'--- %h%n%B' <base>..HEAD for the commits that would land
  • git -C "$REPO" diff --name-status <base>...HEAD for the paths
  • git -C "$REPO" diff <base>...HEAD for the diff itself
  • cat "$REPO/.github/pull_request_template.md" for what each section is asking

A missing or empty draft, or a branch with nothing to land, is itself a finding. Report it and stop.

What's already settled

The writer runs a mechanical validator until it reports nothing before handing you anything, and the caller runs it again afterwards, so leave its rules alone. It has already settled:

  • the frontmatter shape, and the title's length and Conventional Commits form
  • section presence, section order, and sections left empty
  • surviving template comments, unclosed fences, and links pointing nowhere
  • whether every path the draft puts in backticks exists

Repeating any of that wastes the round trip.

Read the diff instead. Your job starts where looking at the file stops.

What to check

Work these four groups. Every finding names the exact offending text and the fix.

Truthfulness

The description covers this branch and no other.

  • Flag any claim the diff doesn't support. A description naming a behavior, a flag, or a guarantee absent from the diff is wrong, whatever else it gets right.
  • Flag counts of any kind: files, lines, tests, commits, percentages. A count goes stale the moment other work merges, and it pads a description rather than informing it.
  • Flag results nobody verified. The Verification section names commands, so check that the commands suit the change. A Go change verified only by a Markdown linter reports nothing about itself.
  • Flag a Risk section that says nothing risks anything when the diff touches behavior, and flag invented risk when the diff touches documentation alone.
Substance

Each section answers its own question, and the template says which.

  • Flag a Summary that restates the diff. Adds a helper to foo.go and calls it from bar.go describes a diff the reader can already read.
  • Flag a Why that repeats the Summary in longer words, or that explains nothing a reader couldn't recover from the diff.
  • Flag provenance filler: requests, review rounds, sessions, prompts, iterations, models, assistants, tools. None of that belongs in a description.
  • Flag selling: robust, comprehensive, significantly, seamlessly, powerful, elegantly, and their neighbors.
Fit

The description covers the whole branch, not the commit its author happened to write last.

  • Flag a title describing one commit when the branch has more than one. That title becomes the squash subject on the default branch, so it names what the whole branch does.
  • Flag a Summary that covers some commits and drops others.
  • Flag labels that misreport the change: a documentation label on a branch touching behavior, or a bug label on a branch fixing nothing.
  • Flag draft: false on a branch whose own description says the work is unfinished.
Show full SKILL.md (418 more words)Show less
Coherence

Judge the branch, not the description.

  • Does the branch carry one change that a reviewer can hold in their head and that merges or reverts as a unit?
  • Flag a branch mixing unrelated work, and name the pull requests it should split into. Reviewers miss things in a branch that changed three unrelated areas.
  • A change plus its tests, or a change plus the documentation describing it, counts as one change. Leave that alone.
  • Size alone isn't a finding. A wide mechanical rename counts as one change. A small diff touching two unrelated subsystems doesn't.

Sweep before you write the verdict

A fault you found once is rarely alone. Take each finding you have and read the whole draft again for the same fault. A list that stops short of the diff, a claim scoped wider than the evidence, a count standing where a name belongs, a sentence selling rather than saying. Where the draft holds one, look for the second. Where instances share a fix, report them as one finding naming each.

Do this even when a finding sends you back into a section you already cleared. The draft in front of you changed since the last pass, and a claim that held then may not hold now.

An instance you leave for the next pass costs a writer round and a reviewer round to say what this verdict could have said. None of that invites padding. Everything in the verdict still has to be something you can point at.

What to return

Your verdict is what lets the pull request proceed. A hook on the caller's side reads the line below and signs the draft you cleared. Keep the wording exact, because a verdict that hook can't parse leaves the pull request blocked. Write nothing to disk yourself, and don't edit the draft to make it pass. Reporting the finding is the job.

Return the verdict block and stop there. Skip the preamble, the diff summary, and the praise.

text
VERDICT: PASS

or

text
VERDICT: CHANGES REQUIRED

1. [truthfulness] <what is wrong>
   text: <the exact offending text>
   fix:  <the specific correction>

2. [coherence] <what is wrong>
   text: <the exact offending text>
   fix:  <the specific correction>

Tag each finding truthfulness, substance, fit, or coherence.

Return PASS when the draft holds up. A clean description counts as a real outcome, and inventing a finding to look thorough wastes the round trip. Report only what you can point at in the draft or the diff.

Your findings go straight back to write-pr-description as its next instructions, so write each one so that agent can act on it without seeing this conversation. Name the section and quote the offending text, then give the replacement.

© tbhb, 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 1 other file in .claude/skills/review-pr-description of tbhb/vale-ai-tells.

  • SKILL.md
  • tokens.json

Open the folder on GitHubat commit 4c7abc9

Compare with similar skills

Review PR Description 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 PR Description compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review PR Description this skilltbhb/vale-ai-tells117—~1.7kAutomated safety check: PassApache-2.0
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Open Code Review CLIalibaba/open-code-review46k—~3.1kAutomated safety check: PassApache-2.0
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

  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k 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
  • Open Code Review CLI

    alibaba/open-code-review

    Runs the ocr command-line tool to review Git changes, a commit or a branch comparison with an AI model, returning line-level comments and optionally applying fixes.

    46k GitHub stars~3.1k tokensUpdated today
    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
  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    86k GitHub stars~1.4k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from tbhb/vale-ai-tells

All 27 skills in this repo
  • Analyze Session

    tbhb/vale-ai-tells

    Query a Claude Code transcript without reading it into context, then write the retrospective to disk so it remains available after the session ends.

    117 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Codex Analyze Session

    tbhb/vale-ai-tells

    Query a Codex transcript without reading it into context, then write the retrospective to disk so it remains available after the session ends.

    117 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Codex Fix PR

    tbhb/vale-ai-tells

    Diagnose failing pull request checks, reproduce them locally, make focused fixes, commit them through codex-commit, and refresh the published description when needed.

    117 GitHub stars~575 tokensUpdated yesterday
    Auto-check passed
  • Codex Merge PR

    tbhb/vale-ai-tells

    Squash merge a pull request. An agent skill from tbhb/vale-ai-tells.

    117 GitHub stars~3k tokensUpdated yesterday
    Auto-check passed
  • Codex PR

    tbhb/vale-ai-tells

    Open or update a pull request for the current branch with an independently drafted and reviewed PRAGENTDESC.md.

    117 GitHub stars~846 tokensUpdated yesterday
    Auto-check passed
  • Codex Rebase

    tbhb/vale-ai-tells

    Replay the current branch onto its base and establish that the result is sound.

    117 GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Review PR Description

What does Review PR Description do?

Review a drafted pull request description in PRAGENTDESC.md against the branch it would publish, as an independent agent, for what mechanical checking can't see. Review PR Description is an agent skill from tbhb/vale-ai-tells.md against the branch it would publish, as an independent agent, for what mechanical checking can't see.

When should I use Review PR Description?

Review PR Description fits situations like: tasks that involve Pull requests.

How do I install Review PR Description in Claude Code?

Run `npx skills add tbhb/vale-ai-tells --skill review-pr-description -a claude-code`. Or copy the skill folder (.claude/skills/review-pr-description in tbhb/vale-ai-tells) into .claude/skills/review-pr-description in your project. Claude Code loads it when a task matches its description.

How do I install Review PR Description in Codex?

Run `npx skills add tbhb/vale-ai-tells --skill review-pr-description -a codex`. Or copy the skill folder (.claude/skills/review-pr-description in tbhb/vale-ai-tells) into .agents/skills/review-pr-description in your project. Codex loads it when a task matches its description.

Can I use Review PR Description 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 tbhb/vale-ai-tells --skill review-pr-description -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-pr-description, .gemini/skills/review-pr-description, .github/skills/review-pr-description and .opencode/skills/review-pr-description in your project.

What does Review PR Description need to run?

Going by SKILL.md and its folder, Review PR Description needs the command-line tools its instructions call (git).

Does Review PR Description access the network?

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

Is Review PR Description 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. Review the folder before installing.

What licence does Review PR Description use?

Review PR Description is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Review PR Description use?

About 1.7k tokens (SKILL.md is roughly 7k 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 PR Description?

Skills that share tags, products or a category with Review PR Description: Finishing a Development Branch (obra/superpowers, 297k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars), Open Code Review CLI (alibaba/open-code-review, 46k 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 Review PR Description?

tbhb (a GitHub user) maintains it in tbhb/vale-ai-tells, which has 117 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on October 9, 2026.

Source: tbhb/vale-ai-tells on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.