Agent skill

Clickhouse PR Description

by ClickHouse in ClickHouse/ClickHouse

Generate PR descriptions for ClickHouse/ClickHouse that match maintainer expectations.

Apache-2.0Auto-check passedDatabases

Install Clickhouse PR Description

skills CLI
$ npx skills add ClickHouse/ClickHouse --skill clickhouse-pr-description -a claude-code

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

GitHub CLI
$ gh skill install ClickHouse/ClickHouse clickhouse-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/ClickHouse/ClickHouse.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/clickhouse-pr-description .claude/skills/clickhouse-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
clickhouse-pr-description
GitHub stars
50k
Token cost
~1.9k tokens
SKILL.md length
899 words
Files
1
Skills in repo
24
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generate PR descriptions for ClickHouse/ClickHouse that match maintainer expectations.

  • Updating PR descriptions
  • SKILL.md covers Title, Body, Changelog entry guidelines and What to avoid, plus 2 more sections
  • Calls git and gh
  • Tasks that involve Data warehousing

What it does

Clickhouse PR Description is an agent skill from ClickHouse/ClickHouse. Generate PR descriptions for ClickHouse/ClickHouse that match maintainer expectations. Use when creating or updating PR descriptions.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Databases, covering Data warehousing and Pull requests. It works with ClickHouse. The repository describes itself as: ClickHouse® is a real-time analytics database management system. The licence is Apache-2.0.

When your agent uses it

  • Updating PR descriptions
  • Tasks that involve Data warehousing
  • Tasks that involve Pull requests

Example prompts

  • “/clickhouse-pr-description”

Requirements

  • Pre-approved tools (allowed-tools): Task, Bash(gh:*), Bash(git:*), Read, Glob, Grep, AskUserQuestion

What it can do on your machine

Read from SKILL.md and the folder at commit c873902. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Task
    • Bash(gh:*)
    • Bash(git:*)
    • Read
    • Glob
    • Grep
    • AskUserQuestion

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • gh

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

  • Network

    No URLs in SKILL.md. Its commands use git and 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

Clickhouse PR Description loads about 1.9k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 899 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 ClickHouse/ClickHouse at commit c873902, republished under its Apache-2.0 licence (© ClickHouse). 899 words, ~1,942 tokens.

Download SKILL.mdSave it as .claude/skills/clickhouse-pr-description/SKILL.md (or your agent's skills folder).
name
clickhouse-pr-description
description
Generate PR descriptions for ClickHouse/ClickHouse that match maintainer expectations. Use when creating or updating PR descriptions.
allowed-tools
Task, Bash(gh:*), Bash(git:*), Read, Glob, Grep, AskUserQuestion
argument-hint
[PR-number or branch-name]
disable-model-invocation
false

ClickHouse PR Description Skill

Generate a good PR description and apply it, with optional confirmation based on user preference.

Title

Plain description of what changed. No prefix conventions like fix(): or feat():.

Exception — .claude/ changes: when the PR only touches files under .claude/ (settings, tools, skills, instructions, etc.), prefix the title with claude: . Example: claude: add fetch_ci_report.js to allowed commands.

  • Good: Change default stderr_reaction to log_last for executable UDFs
  • Good: Fix exception when inserting NULL into non-nullable column via CAST
  • Good: claude: allow fetch_ci_report.js and grep in Claude Code settings
  • Bad: fix(udf): Change default stderr_reaction — conventional commits, ClickHouse doesn't use them
  • Bad: Fuzzer fixes — too vague, tells the reviewer nothing
  • Bad: Improve error handling and enrich exit code exceptions with stderr context — too vague, doesn't say what was actually changed

Body

Read .github/PULL_REQUEST_TEMPLATE.md for the exact template structure.

A good PR description has two parts:

1. Free-form context (above the template, optional but encouraged for non-trivial changes)

Explain to a future reader: what was the problem, why did it need fixing, what approach was taken, what were the results or trade-offs. This is the right place for:

  • Motivation and background
  • Description of the approach and why it was chosen over alternatives
  • Benchmark results or measurements
  • Links to related issues, discussions, or previous attempts
  • Any caveats or known limitations

Use plain paragraphs. Headers like ## Motivation, ## Changes, ## Results are fine and helpful — they make the PR easier to navigate for reviewers. Bullet lists are fine. Be as detailed as needed.

2. Template section (mandatory)

Fill in the changelog category (delete the rest of the list) and write the changelog entry when the selected category requires one.

Example of a well-written body

From #96110:

### Changelog category (leave one):
- Backward Incompatible Change

### Changelog entry:
The semantics of the `do_not_merge_across_partitions_select_final` setting were
made more obvious. Previously, the feature could be automatically enabled when
the setting was not explicitly set in the configs. It caused confusion repeatedly
and, unfortunately, led to some issues in production. Now, the rules are simpler:
`do_not_merge_across_partitions_select_final=1` enables the functionality
unconditionally. If `do_not_merge_across_partitions_select_final=0`, then automatic
is used only if the new setting
`enable_automatic_decision_for_merging_across_partitions_for_final=1` and not used
otherwise. To preserve the old behaviour as much as possible, the defaults were set
to `do_not_merge_across_partitions_select_final=0` and
`enable_automatic_decision_for_merging_across_partitions_for_final=1`.

---

The backward-incompatible part is that if someone has
`do_not_merge_across_partitions_select_final=0` explicitly set in the configs,
it no longer protects against the use of automatics. I'm open to discussion on
whether we should conservatively default to disabled automatics.

Note: extra context after --- is fine — reviewers see it, but only the changelog entry above the blank line goes into the CHANGELOG.

Changelog entry guidelines

The entry is what ends up in the published CHANGELOG. Write it for a user who is upgrading and scanning for what affects them. The PR link and author attribution are appended automatically by tooling — do not include them.

Format: the changelog script (ci/tools/changelog.py) collects all lines after the ### Changelog entry: header up to the first blank line, then joins them with spaces into a single string. This means:

  • The entry can span multiple lines in the template — they become one paragraph
  • A blank line terminates collection — anything after it is ignored
  • Write it as a single paragraph (no bullet lists, no blank lines within)

Tense: mixed is fine and natural. "Added X", "Fix a case where...", "The X setting is now Y" are all real examples from the CHANGELOG. Don't force everything into present tense.

Length: match the impact. A small new function can be one sentence. A changed default or backward-incompatible behavior warrants as many sentences as needed, including what users must do to adapt.

Specificity: always name the exact thing that changed. Never write "Fix a bug" or "Improve performance" without saying what specifically.

For backward-incompatible changes: always explain the old behavior, the new behavior, and how to restore the old one if possible.

Real examples from the ClickHouse CHANGELOG:

One sentence, sufficient for a focused addition:

Add xxh3_128 hashing function.

One sentence with enough context:

DATE columns from PostgreSQL are now inferred as Date32 in ClickHouse (in previous versions they were inferred as Date, which led to overflow of values outside a narrow range). Allow inserting Date32 values back to PostgreSQL.

Show full SKILL.md (328 more words)Show less

Full migration instructions for a default change:

Deduplication is turned ON for all inserts by default. It was OFF before for async inserts and for MV's, but it was ON for sync inserts. The goal is to have the same defaults for both ways of inserts. If you have deduplication explicitly disabled on your cluster, you have to explicitly set deduplicate_insert='backward_compatible_choice' to keep the old behavior.

Describes new capability with enough detail to understand when to use it:

Added OPTIMIZE <table> DRY RUN PARTS <part names> query to simulate merges without committing the result part. It may be useful for testing purposes: verifying merge correctness in the new version, deterministically reproducing merge-related bugs, and reliably benchmarking merge performance.

Reference the issue if one exists: Closes #XXXXX or Fixes #XXXXX at the end.

What to avoid

These patterns make PRs harder to read or signal low effort:

  • fix(scope): / feat(): / chore(): — ClickHouse doesn't use conventional commits
  • This PR ... to start any section — just describe the change
  • Vague titles like Fuzzer fixes, Fix bug, Improvements — always say what specifically
  • Markdown tables comparing "before/after behavior" unless genuinely useful
  • Perfectly parallel sentence structure throughout — vary phrasing naturally

AI co-authorship

It's fine to mention AI assistance openly. Co-Authored-By: in commits or acknowledgements in the PR description are acceptable — ClickHouse is open about AI-assisted development.

Before creating or updating the PR, check user memory for a confirmation preference. If no preference is stored and the session is interactive, ask once: "Should I always show you the description for approval before applying it, or just go ahead every time?" Save the answer to memory and apply it from then on. If the session is non-interactive, proceed directly without asking.

Fork vs upstream

If the current repository is a fork (i.e. git remote get-url origin does not contain ClickHouse/ClickHouse), always target the upstream repository. Pass --repo ClickHouse/ClickHouse to gh pr create and set --head <fork-owner>:<branch> so the PR is opened against the canonical repo, not the fork.

© ClickHouse, 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

Just SKILL.md in .claude/skills/clickhouse-pr-description of ClickHouse/ClickHouse.

Open the folder on GitHubat commit c873902

Compare with similar skills

Clickhouse 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.

Clickhouse PR Description compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Clickhouse PR Description this skillClickHouse/ClickHouse50k—~1.9kAutomated safety check: PassApache-2.0
Code ReviewClickHouse/clickhouse-java1.6k—~290Automated safety check: PassApache-2.0
Adapter Alignmentevloghq/evlog1.9k—~1.3kAutomated safety check: PassMIT
Version Upgrade Advisorchmonitor/chmonitor299—~1.6kAutomated safety check: PassGPL-3.0
Clickhouse Logs Queriessupabase/supabase111k—~2.4kAutomated safety check: PassApache-2.0
Chdb SQLvemetric/vemetric3951 repos~1.2kAutomated safety check: PassApache-2.0

Similar skills

  • Code Review

    ClickHouse/clickhouse-java

    Review changes in clickhouse-java for correctness, compatibility, API stability, and missing tests.

    1.6k GitHub stars~290 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Adapter Alignment

    evloghq/evlog

    Twice-monthly check that evlog's drain adapters still send what each provider's own client sends.

    1.9k GitHub stars~1.3k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Version Upgrade Advisor

    chmonitor/chmonitor

    Advises whether and how to upgrade ClickHouse — versioning scheme, upgrade path, what you gain, pre/post-upgrade checklist.

    299 GitHub stars~1.6k tokensUpdated 4 days ago
    DatabasesAuto-check passed
  • Clickhouse Logs Queries

    supabase/supabase

    Official

    Write, review, and migrate Supabase logs queries against the ClickHouse-backed logs table (the logs.all.otel analytics endpoint).

    111k GitHub stars~2.4k tokensUpdated today
    DatabasesAuto-check passed
  • Chdb SQL

    vemetric/vemetric

    A skill your agent uses when the user wants to run SQL — especially analytical SQL — on local files (parquet/csv/json), URLs, S3 paths, or remote databases (Postgres, MySQL, MongoDB, ClickHouse…

    395 GitHub starsUsed in 1 repo~1.2k tokens
    DatabasesAuto-check passed
  • Write Doc Examples

    ClickHouse/clickhouse-java

    Write, rewrite, and format documentation code snippets into reusable, production-ready methods with necessary library imports and clean linting.

    1.6k GitHub stars~3.1k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from ClickHouse/ClickHouse

All 24 skills in this repo
  • Keeper Stress Analysis

    ClickHouse/ClickHouse

    Analyze ClickHouse Keeper stress-test results from play.clickhouse.com / keeperstresstests data warehouse.

    50k GitHub stars~4.7k tokensUpdated today
    Auto-check passed
  • Perf Comparison

    ClickHouse/ClickHouse

    Evaluate ClickHouse performance test results from existing CI/dashboard data or local perf.py runs.

    50k GitHub stars~3.9k tokensUpdated today
    Auto-check: notes
  • Patch Release Check

    ClickHouse/ClickHouse

    Check whether ClickHouse's supported versions (last 3 majors + latest LTS) have recent stable patch releases, diagnose why the scheduled AutoReleases pipeline failed, and identify which releases…

    50k GitHub stars~4k tokensUpdated today
    Auto-check: notes
  • Alloc Profile

    ClickHouse/ClickHouse

    Analyze a jemalloc (or other) allocation profile in collapsed stack format.

    50k GitHub stars~4.3k tokensUpdated today
    Auto-check passed
  • Bisect

    ClickHouse/ClickHouse

    Bisect a ClickHouse regression using pre-built master binaries from CI.

    50k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Codex Review

    ClickHouse/ClickHouse

    Run a local pre-push AI code review of the current branch with the OpenAI codex CLI, the same way ClickHouse CI does, and optionally iterate fix and re-review until clean.

    50k GitHub stars~1.8k tokensUpdated today
    Auto-check: notes

Works with

Questions about Clickhouse PR Description

What does Clickhouse PR Description do?

Generate PR descriptions for ClickHouse/ClickHouse that match maintainer expectations. Clickhouse PR Description is an agent skill from ClickHouse/ClickHouse. Generate PR descriptions for ClickHouse/ClickHouse that match maintainer expectations.

When should I use Clickhouse PR Description?

Clickhouse PR Description fits situations like: updating PR descriptions; tasks that involve Data warehousing; tasks that involve Pull requests.

How do I install Clickhouse PR Description in Claude Code?

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

How do I install Clickhouse PR Description in Codex?

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

Can I use Clickhouse 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 ClickHouse/ClickHouse --skill clickhouse-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/clickhouse-pr-description, .gemini/skills/clickhouse-pr-description, .github/skills/clickhouse-pr-description and .opencode/skills/clickhouse-pr-description in your project.

What does Clickhouse PR Description need to run?

Going by SKILL.md and its folder, Clickhouse PR Description needs the command-line tools its instructions call (git and gh). Its frontmatter pre-approves these tools: Task, Bash(gh:*), Bash(git:*), Read, Glob, Grep, AskUserQuestion.

Does Clickhouse PR Description access the network?

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

Is Clickhouse 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 Clickhouse PR Description use?

Clickhouse PR Description 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 Clickhouse PR Description use?

About 1.9k tokens (SKILL.md is roughly 7.8k 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 Clickhouse PR Description?

Skills that share tags, products or a category with Clickhouse PR Description: Code Review (ClickHouse/clickhouse-java, 1.6k stars), Adapter Alignment (evloghq/evlog, 1.9k stars), Version Upgrade Advisor (chmonitor/chmonitor, 299 stars) and Clickhouse Logs Queries (supabase/supabase, 111k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Clickhouse PR Description?

ClickHouse (a GitHub organization) maintains it in ClickHouse/ClickHouse, which has 50,308 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 9, 2026.

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