ClickHouse
@ClickHouse Organization
Public Skills
decompress-binary
by ClickHouse
Extract the inner ELF from a ClickHouse self-extracting clickhouse binary, including when its architecture differs from the host (e.g. to load an aarch64 CI core dump on an x86 workstation). Use when gdb/lldb needs real symbols from a downloaded CI/release binary, or when self-extraction by running the binary is not possible because of an architecture mismatch.
investigate-ci
by ClickHouse
Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL. Fetches the failed tests and their output, classifies each as flaky vs a real regression using play.clickhouse.com master history, and for every failure searches for both an existing tracking GitHub issue and an existing fix (open/merged PR) — reporting, per failure, whether an issue still needs to be created and whether a fix exists with its status (WIP, merged, already in this branch or not). Downloads and reads the harness artifacts only for failures that history does not explain, and reports a root-cause hypothesis. Read-only first pass — never commits, pushes, or edits.
perf-comparison
by ClickHouse
Evaluate ClickHouse performance test results from existing CI/dashboard data or local perf.py runs. Use to check PR performance changes, run local performance tests, compare with history, assess flakiness, inspect coverage/PR relevance, and summarize whether a result is actionable.
double-check-perf-tests
by ClickHouse
Locally reproduce ClickHouse CI performance comparison results for a given commit. Fetches the perf CI report, identifies queries categorized as "Changes in Performance", downloads both the patched and reference binaries from S3 (matching the current machine architecture), and re-runs only those queries via tests/performance/scripts/perf.py to verify whether each regression/improvement is real. Use this whenever the user wants to "double-check", "reproduce", "verify locally", or "re-run" a perf check result — even if they don't name the skill.
edit-changelog
by ClickHouse
Edit an auto-generated ClickHouse release changelog into the form that gets committed to CHANGELOG.md. Use when the user has the output of utils/changelog/changelog.py and wants it cleaned up and re-categorized for a release.
good-prs
by ClickHouse
Show a report of open ClickHouse PRs whose only non-green CI check is "CH Inc sync" (or that are fully green) — i.e. effectively ready to merge. Groups by your authored PRs, PRs assigned to you (authored by others), and PRs by tracked authors (default groeneai). Shows the CH Inc sync state and whether each PR was ever approved; excludes already-merged PRs. Use when asked for "good PRs", merge-ready PRs, or PRs blocked only on the sync job.
review
by ClickHouse
Review a ClickHouse Pull Request for correctness, safety, performance, and compliance. Use when the user wants to review a PR or diff.
continue-pr-auto
by ClickHouse
Unattended variant of continue-pr for automation (driven by utils/continue-all-prs.sh). Resolves conflicts - reworking stale features to reconcile with current master when a mechanical merge is not enough - fixes CI, addresses feedback, and pushes without ever asking the user. For interactive use, prefer continue-pr.
continue-pr
by ClickHouse
Continue work on an existing PR - resolve conflicts, fix CI failures, address reviewer feedback, and push updates. Use when the user wants to pick up and advance a pull request.
patch-release-check
by 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 must be created manually. Use when asked "are the patch releases up to date", "why did autorelease fail", "which releases are missing", "did a release get skipped", during the bi-weekly release-health check, or when investigating create_release.yml / auto_releases.yml failures. Reproduces the full investigation: supported versions from SECURITY.md, per-version staleness, classification of the last N days of AutoReleases/CreateRelease failures (version-bump-PR guard vs missing release-maker runner vs other), the Slack cross-check that reveals the blocking PR, and gated remediation (close a stale robot bump PR, dispatch CreateRelease for a missing version).
diff-review
by ClickHouse
In-browser review of pending changes before committing or opening a PR. Starts a local server on localhost:3000 that renders the working-tree diff with @pierre/diffs CodeView, opens the user's browser, and waits for their line comments — which must then be read back and addressed. Works from a browser on the same machine, or from the user's own machine through an SSH-forwarded port (the server prints the ssh -L command); where nobody opens the page within 120 s, it exits on its own. Use when the user asks for a browser review of the changes.
perf-report
by ClickHouse
Analyze CI performance comparison reports for a ClickHouse PR. Lists all regressions and improvements, cross-references with master history to distinguish real changes from flaky tests.
update-contrib
by ClickHouse
Update a ClickHouse third-party library (contrib submodule) to a new version. Handles fork management, submodule pointer bumps, CMake adaptation, and source code fixes. Use when the user wants to bump a dependency.
share
by ClickHouse
Share a Claude Code session to pastila.nl and return a viewer link. Shares the current session by default, or a session specified as a transcript path, a session id, or a project. Use when the user asks to share, publish, or get a link to this conversation or to a session/transcript.
create-worktree
by ClickHouse
Create a ClickHouse git worktree with submodules hardlinked from the main repo. Use when the user wants to create a new worktree for ClickHouse development.
fix-sync
by ClickHouse
Fix the "CH Inc sync" job in a pull request. Diagnoses the failure as one of three types — conflicts found, build failed, or tests failed — and handles each accordingly.
clickhouse-pr-description
by ClickHouse
Generate PR descriptions for ClickHouse/ClickHouse that match maintainer expectations. Use when creating or updating PR descriptions.
keeper-stress-analysis
by ClickHouse
Analyze ClickHouse Keeper stress-test results from play.clickhouse.com / keeper_stress_tests data warehouse. Use whenever the user asks about Keeper performance, validates Keeper PRs against stress dashboards, investigates regressions or improvements in Keeper nightlies, asks about specific date windows / SHAs / PR-sets in Keeper stress tests, wants per-PR or window-vs-window comparisons, asks "did this PR break Keeper", asks "what changed in Keeper between dates", or wants a summary report of Keeper stress runs. Triggers on terms like "keeper stress", "keeper PR", "keeper p99", "keeper memory", "keeper rps", "keeper nightly", "keeper-stress-tests", "keeper validation", "keeper regression", or any question referencing the keeper-stress Grafana dashboard. ALWAYS prefer this skill over re-deriving the workflow from scratch — it captures hard-learned lessons about cgroup-vs-Keeper memory, bench-harness confounds, noise floors, and per-PR attribution limits.
close-flaky-issues
by ClickHouse
Audit open "flaky test" GitHub issues and close those whose tests are no longer failing on master. Cross-references CI history from play.clickhouse.com with git log to attribute fixes.
create-test-datasets
by ClickHouse
Create test datasets (hits, visits, tpcds, tpch) from standard scripts. Ensures the server is running first.
bisect
by ClickHouse
Bisect a ClickHouse regression using pre-built master binaries from CI. Use when the user wants to find the commit that introduced a bug.
cpu-profile
by ClickHouse
Profile a ClickHouse query using the sampling query profiler and system.trace_log. Use when the user wants to find CPU hotspots, analyze where time is spent in a query, or investigate performance bottlenecks.
build
by ClickHouse
Build ClickHouse with various configurations (Release, Debug, ASAN, TSAN, etc.). Use when the user wants to compile ClickHouse.
test
by ClickHouse
Run ClickHouse stateless or integration tests. Use when the user wants to run or execute tests.
alloc-profile
by ClickHouse
Analyze a jemalloc (or other) allocation profile in collapsed stack format. Use when the user wants to analyze memory allocations, find top allocators, or understand memory usage patterns from a .collapsed profile file.
clickhouse-best-practices
by ClickHouse
MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 28 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.