PR Finalize Review
microsoft/garnet
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.
Write or revise the pull request description in PRAGENTDESC.md, as a forked agent that reads the branch itself.
Install Write PR Description
$ npx skills add tbhb/vale-ai-tells --skill write-pr-description -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tbhb/vale-ai-tells write-pr-description --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/tbhb/vale-ai-tells.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/write-pr-description .claude/skills/write-pr-description && rm -rf skills-srcUse ~/.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/
Install the "write-pr-description" agent skill from https://github.com/tbhb/vale-ai-tells/tree/main/.claude/skills/write-pr-description into .claude/skills/write-pr-description/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-pr-description", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/tbhb/vale-ai-tells/tree/main/.claude/skills/write-pr-descriptionType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add tbhb/vale-ai-tells --skill write-pr-description -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tbhb/vale-ai-tells write-pr-description --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tbhb/vale-ai-tells.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/write-pr-description .agents/skills/write-pr-description && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "write-pr-description" agent skill from https://github.com/tbhb/vale-ai-tells/tree/main/.claude/skills/write-pr-description into .agents/skills/write-pr-description/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-pr-description", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tbhb/vale-ai-tells --skill write-pr-description -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tbhb/vale-ai-tells write-pr-description --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tbhb/vale-ai-tells.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/write-pr-description .cursor/skills/write-pr-description && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "write-pr-description" agent skill from https://github.com/tbhb/vale-ai-tells/tree/main/.claude/skills/write-pr-description into .cursor/skills/write-pr-description/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-pr-description", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/tbhb/vale-ai-tells.git --path .claude/skills/write-pr-description--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add tbhb/vale-ai-tells --skill write-pr-description -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tbhb/vale-ai-tells write-pr-description --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tbhb/vale-ai-tells.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/write-pr-description .gemini/skills/write-pr-description && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "write-pr-description" agent skill from https://github.com/tbhb/vale-ai-tells/tree/main/.claude/skills/write-pr-description into .gemini/skills/write-pr-description/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-pr-description", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install tbhb/vale-ai-tells write-pr-descriptionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add tbhb/vale-ai-tells --skill write-pr-description -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tbhb/vale-ai-tells.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/write-pr-description .github/skills/write-pr-description && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "write-pr-description" agent skill from https://github.com/tbhb/vale-ai-tells/tree/main/.claude/skills/write-pr-description into .github/skills/write-pr-description/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-pr-description", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tbhb/vale-ai-tells --skill write-pr-description -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tbhb/vale-ai-tells write-pr-description --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tbhb/vale-ai-tells.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/write-pr-description .opencode/skills/write-pr-description && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "write-pr-description" agent skill from https://github.com/tbhb/vale-ai-tells/tree/main/.claude/skills/write-pr-description into .opencode/skills/write-pr-description/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-pr-description", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
write-pr-description- GitHub stars
- 115
- Token cost
- ~1.5k tokens
- SKILL.md length
- 791 words
- Files
- 4 (incl. scripts)
- Skills in repo
- 27
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Write or revise the pull request description in PRAGENTDESC.md, as a forked agent that reads the branch itself.
- Tasks that involve Pull requests
- SKILL.md covers Arguments, Context, The shape and One question per section, plus 4 more sections
- Runs Shell scripts from its folder; calls bash
- Tasks that involve Commit messages
What it does
Write PR Description is an agent skill from tbhb/vale-ai-tells. Write or revise the pull request description in PRAGENTDESC.md, as a forked agent that reads the branch itself. Fills the frontmatter properties, a Conventional Commits title, and every section the repository's template declares, then runs the mechanical validator until it reports nothing before returning. The pr skill calls this to draft, fix-pr calls it after remediation commits arrive, and merge-pr calls it for a final pass. Every call pairs with review-pr-description afterwards.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/context.sh`, `scripts/guard-draft.sh` and `tokens.json`).
It sits in Development, covering Pull requests and Commit messages. 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
- Tasks that involve Commit messages
Example prompts
- “/write-pr-description”
Requirements
- A Bash shell
What it can do on your machine
Read from SKILL.md and the folder at commit a96c5fe. 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 2 files in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
bash
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
Write PR Description loads about 1.5k tokens when it runs. Until then it costs about 127 tokens; SKILL.md has 791 words of instructions outside code blocks.
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 tbhb/vale-ai-tells at commit a96c5fe, republished under its Apache-2.0 licence (© tbhb). 791 words, ~1,491 tokens.
Download SKILL.mdSave it as
.claude/skills/write-pr-description/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- write-pr-description
- description
- Write or revise the pull request description in PR_AGENTDESC.md, as a forked agent that reads the branch itself. Fills the frontmatter properties, a Conventional Commits title, and every section the repository's template declares, then runs the mechanical validator until it reports nothing before returning. The pr skill calls this to draft, fix-pr calls it after remediation commits arrive, and merge-pr calls it for a final pass. Every call pairs with review-pr-description afterwards.
- license
- Apache-2.0
- context
- fork
- agent
- general-purpose
- background
- false
Write a pull request description
Write PR_AGENTDESC.md at the repository root, then return. You run forked, so the branch diff sits in your context rather than the caller's. Read the material below and write from it.
Arguments
$ARGUMENTS carries the repository root, and after it whatever the caller wants addressed. A first draft arrives with nothing extra. A revision includes the findings review-pr-description returned, or a note that remediation added commits the description hasn't caught up with.
Treat any findings in the arguments as the work. Resolve each one and say so.
Context
!bash ${CLAUDE_SKILL_DIR}/scripts/context.sh
The shape
Write the file in exactly this order.
---
base: <branch this merges into>
draft: <true or false>
labels: [<one or more from the set above>]
reviewers: []
assignees: []
milestone:
---
# <type>(<scope>)?: <description>
## <first template section>
<prose>Those frontmatter keys and no others. Labels take a flow sequence and an empty one fails the validator, because nobody's filter finds an unlabelled pull request.
The title is a level 1 heading in the Conventional Commits shape. A squash merge turns it into the commit subject on the default branch, so its type has to be one the landing commits use, and it names what the whole branch does rather than what the last commit did.
Then every section the template declares, in the template's order, filled with prose. Replace each instructional comment rather than leaving it in place.
One question per section
The sections answer different questions, so don't let them repeat each other. Summary says what changes. Why says what problem made it necessary. Verification names the commands you actually ran, in backticks. Risk says what breaks if this is wrong and how to back it out. Related points at issues, or says None.
Avoid:
- Restating the diff. A reviewer reads the diff already.
- Counting. No file, line, test, or commit counts.
- Provenance filler. Nothing about requests, sessions, prompts, models, or tools.
- Claims you haven't checked, including verification nobody ran.
- Selling it. Drop
robust,comprehensive,significantly, and their neighbors. - Paths that don't exist. Every backticked path gets resolved against the tree and the diff.
Revising rather than starting over
Where a draft already exists, the context printed it earlier. Keep the sentences that still hold. A revision that rewrites untouched prose costs the caller another review round for nothing, and it loses wording an earlier review already cleared.
A finding names one instance of a fault rather than the fault itself. Fix the instance, then read the rest of the draft for the same fault, because a reviewer that found one instance finds the next one on the next round. That sweep isn't the rewriting this section warns against, since it changes a sentence only where the sentence is wrong.
Where the published description differs from the draft, the branch has moved since the last publish. Bring the draft forward rather than reverting it to what GitHub shows.
Show full SKILL.md (336 more words)Show less
Read the draft back before returning
The validator covers what a script can check. What follows is what the reviewer sends drafts back for, and the context printed earlier already holds the answer to each, so a round trip spent on one buys nothing.
Closed enumerations. A sentence naming the kinds of change on the branch claims to name every one, and a reviewer reads it that way. Walk the changed-file listing against every sentence of that shape, and confirm the sentence covers each path or that you left the path out on purpose. Where you can't confirm it, write the sentence open, so it claims only what you checked.
Scope words. only, every, never, and the one place each make a claim about the files you didn't quote. Open the file and establish the scope before writing one. A setting described as mattering on one CI slot is a claim about every other slot, and the workflow in the diff either bears that out or doesn't.
The Avoid list earlier in this document. Read the finished draft against it once. Following a rule while writing and satisfying it in the finished text are different things.
Run the validator before returning
bash .claude/skills/pr/scripts/validate-description.shRun it, fix every finding, and run it again until it prints nothing. Each finding names a line and the correction.
Returning a draft that fails the validator spends a review round on something a script settles by itself, and the caller only has to send you back, so treat this as part of writing rather than a step after it.
What to return
Return this block and stop there. Skip the preamble and the praise, and leave the description itself for the caller to read off disk.
DRAFT: WRITTEN
changed: <what you altered, one line per item, or "first draft">
addressed: <each finding from the arguments and how, or "nothing requested">or, when the branch or the repository makes drafting impossible:
DRAFT: BLOCKED
reason: <what stopped you>Blocked covers a branch with nothing to land, a missing template, and a validator finding you can't resolve without a decision the caller has to make. It doesn't cover a validator finding you simply haven't fixed yet.
© 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 3 other files (scripts) in .claude/skills/write-pr-description of tbhb/vale-ai-tells.
- SKILL.md
- scripts/context.sh
- scripts/guard-draft.sh
- tokens.json
Open the folder on GitHubat commit a96c5fe
Compare with similar skills
Write 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Write PR Description this skilltbhb/vale-ai-tells | 115 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| PR Finalize Reviewmicrosoft/garnet | 12k | — | ~3.1k | Automated safety check: Pass | MIT | |
| Git Workflow and Versioningaddyosmani/agent-skills | 102k | 2 repos | ~3.5k | Automated safety check: Notes | MIT | |
| React Router Pull Request Creatorremix-run/react-router | 57k | — | ~2.5k | Automated safety check: Pass | MIT | |
| Verdaccio Pull Request Workflowverdaccio/verdaccio | 18k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Emoji Commit ConventionsbaptisteArno/typebot.io | 11k | — | ~424 | Automated safety check: Pass | Custom licence |
Similar skills
- Official
Git Workflow and Versioning
addyosmani/agent-skills
Sets git habits for every change: short-lived branches, atomic commits with descriptive messages, clean pull requests, plus versioning, tagging and changelogs for releases.
React Router Pull Request Creator
remix-run/react-router
Packages finished React Router work into a draft pull request: branch, commit, push, a written PR body and the right GitHub labels.
Verdaccio Pull Request Workflow
verdaccio/verdaccio
Takes a change through a verdaccio pull request: branch, local checks, changeset, title and body, labels, CI and review rounds, and ports to other release lines.
Emoji Commit Conventions
baptisteArno/typebot.io
Sets the repository's convention for commit messages and pull request titles: one emoji prefix for the main intent, a concise title and clean follow-up commits.
Commit And PR Messages
superplanehq/superplane
Write Git commit messages and pull request titles/descriptions using the Chris Beams / Tim Pope conventions (subject/body split, ~50-char subject, imperative mood, why-not-how body) plus ASD-STE100…
More from tbhb/vale-ai-tells
All 27 skills in this repoAnalyze 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.
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.
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.
Codex Merge PR
tbhb/vale-ai-tells
Squash merge a pull request. An agent skill from tbhb/vale-ai-tells.
Codex PR
tbhb/vale-ai-tells
Open or update a pull request for the current branch with an independently drafted and reviewed PRAGENTDESC.md.
Codex Rebase
tbhb/vale-ai-tells
Replay the current branch onto its base and establish that the result is sound.
Related
Categories
Questions about Write PR Description
What does Write PR Description do?
Write or revise the pull request description in PRAGENTDESC.md, as a forked agent that reads the branch itself. Write PR Description is an agent skill from tbhb/vale-ai-tells.md, as a forked agent that reads the branch itself.
When should I use Write PR Description?
Write PR Description fits situations like: tasks that involve Pull requests; tasks that involve Commit messages.
How do I install Write PR Description in Claude Code?
Run `npx skills add tbhb/vale-ai-tells --skill write-pr-description -a claude-code`. Or copy the skill folder (.claude/skills/write-pr-description in tbhb/vale-ai-tells) into .claude/skills/write-pr-description in your project. Claude Code loads it when a task matches its description.
How do I install Write PR Description in Codex?
Run `npx skills add tbhb/vale-ai-tells --skill write-pr-description -a codex`. Or copy the skill folder (.claude/skills/write-pr-description in tbhb/vale-ai-tells) into .agents/skills/write-pr-description in your project. Codex loads it when a task matches its description.
Can I use Write 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 write-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/write-pr-description, .gemini/skills/write-pr-description, .github/skills/write-pr-description and .opencode/skills/write-pr-description in your project.
What does Write PR Description need to run?
Going by SKILL.md and its folder, Write PR Description needs a shell for the scripts in its folder and the command-line tools its instructions call (bash). Our summary lists: A Bash shell.
Does Write PR Description 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 Write 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Write PR Description use?
Write 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 Write PR Description use?
About 1.5k tokens (SKILL.md is roughly 6k 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 Write PR Description?
Skills that share tags, products or a category with Write PR Description: PR Finalize Review (microsoft/garnet, 12k stars), Git Workflow and Versioning (addyosmani/agent-skills, 102k stars), React Router Pull Request Creator (remix-run/react-router, 57k stars) and Verdaccio Pull Request Workflow (verdaccio/verdaccio, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Write PR Description?
tbhb (a GitHub user) maintains it in tbhb/vale-ai-tells, which has 115 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on October 7, 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.