Agent skill

Troubleshooting

by chmonitor in chmonitor/chmonitor

Diagnose and resolve ClickHouse issues: OOM, slow merges, stuck mutations, query failures with error codes, and systematic error clustering.

GPL-3.0Auto-check passedDatabases

Install Troubleshooting

skills CLI
$ npx skills add chmonitor/chmonitor --skill troubleshooting -a claude-code

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

GitHub CLI
$ gh skill install chmonitor/chmonitor troubleshooting --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/chmonitor/chmonitor.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/troubleshooting .claude/skills/troubleshooting && 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
troubleshooting
GitHub stars
298
Token cost
~674 tokens
SKILL.md length
245 words
Files
1
Skills in repo
53
Repo updated
First seen
Licence
GPL-3.0

At a glance

Diagnose and resolve ClickHouse issues: OOM, slow merges, stuck mutations, query failures with error codes, and systematic error clustering.

  • Tasks that involve Data warehousing
  • SKILL.md covers OOM (Out of Memory), Slow Merges, Stuck Mutations and Query Failures, plus 2 more sections
  • Calls curl

What it does

Troubleshooting is an agent skill from chmonitor/chmonitor. Diagnose and resolve ClickHouse issues: OOM, slow merges, stuck mutations, query failures with error codes, and systematic error clustering.

Its SKILL.md is about 670 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. It works with ClickHouse. The repository describes itself as: Open-source operational advisor for ClickHouse — real-time monitoring plus AI-driven index/partition/materialized-view recommendations. The licence is GPL-3.0.

When your agent uses it

  • Tasks that involve Data warehousing

Example prompts

  • “/troubleshooting”

What it can do on your machine

Read from SKILL.md and the folder at commit fc39ef0. 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:

    • curl

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

  • Network

    No URLs in SKILL.md. Its commands use curl, 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

Troubleshooting loads about 674 tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 245 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~674

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 chmonitor/chmonitor at commit fc39ef0, republished under its GPL-3.0 licence (© chmonitor). 245 words, ~674 tokens.

Download SKILL.mdSave it as .claude/skills/troubleshooting/SKILL.md (or your agent's skills folder).
name
troubleshooting
description
Diagnose and resolve ClickHouse issues: OOM, slow merges, stuck mutations, query failures with error codes, and systematic error clustering.

Troubleshooting Guide

OOM (Out of Memory)

Diagnosis: system.query_log WHERE memory_usage is high. system.metrics WHERE metric = 'MemoryTracking'.

Solutions:

  • max_memory_usage per query (e.g., 10GB), max_memory_usage_for_user per user
  • max_bytes_before_external_group_by / max_bytes_before_external_sort for spill-to-disk
  • Reduce JOIN sizes with pre-filtering; use SAMPLE for approximate aggregations

Slow Merges

Diagnosis: system.merges — check elapsed, progress, total_size_bytes_compressed. system.part_log WHERE event_type = 'MergeParts' for throughput. Too many parts: max_parts_count_for_partition in system.asynchronous_metrics.

Solutions:

  • Increase background_pool_size (default: 16)
  • Check disk I/O via system.asynchronous_metrics (ReadBufferFromFileDescriptorReadBytes)
  • Batch larger inserts to reduce frequency; avoid excessive partitioning
  • OPTIMIZE TABLE ... FINAL to force merge (expensive, off-peak only)

Stuck Mutations

Diagnosis: system.mutations WHERE is_done = 0 — check parts_to_do, latest_fail_reason. Mutations block new merges on affected parts.

Solutions:

  • KILL MUTATION WHERE mutation_id = '...' to cancel
  • Fix underlying issue (schema mismatch, disk space), then re-submit
  • Prefer INSERT + ReplacingMergeTree over UPDATE mutations

Query Failures

Diagnosis: system.query_log WHERE type = 'ExceptionWhileProcessing'. Use error clustering to find patterns:

sql
SELECT exception_code, count(), topK(10)(exception)
FROM system.query_log
WHERE type = 'ExceptionWhileProcessing'
GROUP BY exception_code ORDER BY count() DESC

For persistent errors, check system.error_log (requires error logging enabled).

Common error codes:

  • 60: table not found — verify table exists, check database name
  • 47: unknown column — use get_table_schema to check column names
  • 241: memory limit — reduce scope, add LIMIT, use SAMPLE
  • 159: timeout — add time filters, use LIMIT
  • 252: too many parts — wait for merges or OPTIMIZE

Network Connectivity

Diagnosis: Check inter-server connectivity for replication or distributed queries. Verify interserver_http_port is reachable between nodes. Test with curl http://<peer>:9009. Check firewall rules and DNS resolution.

Cross-references

  • Load the replication-guide skill for replication lag diagnosis and recovery.
  • Load the storage-optimization skill for disk recovery and tiered storage management.

© chmonitor, GPL-3.0. 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 .agents/skills/troubleshooting of chmonitor/chmonitor.

Open the folder on GitHubat commit fc39ef0

Compare with similar skills

Troubleshooting 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.

Troubleshooting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Troubleshooting this skillchmonitor/chmonitor298—~674Automated safety check: PassGPL-3.0
Clickhouse Architecture Advisorvemetric/vemetric3942 repos~791Automated safety check: PassApache-2.0
Clickhouse Ioaffaan-m/ECC274k3 repos~2.3kAutomated safety check: PassMIT
Clickhouse Ioaffaan-m/ECC274k2 repos~2.3kAutomated safety check: PassMIT
Clickhouse Ioaffaan-m/ECC274k1 repos~2.7kAutomated safety check: PassMIT
Gram Telemetry Query Dimensionsspeakeasy-api/gram272—~2.4kAutomated safety check: PassAGPL-3.0

Similar skills

  • MUST USE when designing ClickHouse architectures, selecting between ingestion or modeling patterns, or translating best practices into workload-specific system designs.

    394 GitHub starsUsed in 2 repos~791 tokens
    DatabasesAuto-check passed
  • Clickhouse Io

    affaan-m/ECC

    ClickHouse数据库模式、查询优化、分析以及高性能分析工作负载的数据工程最佳实践. An agent skill from affaan-m/ECC.

    274k GitHub starsUsed in 3 repos~2.3k tokens
    DatabasesAuto-check passed
  • Clickhouse Io

    affaan-m/ECC

    고성능 분석 워크로드를 위한 ClickHouse 데이터베이스 패턴, 쿼리 최적화, 분석 및 데이터 엔지니어링 모범 사례.

    274k GitHub starsUsed in 2 repos~2.3k tokens
    DatabasesAuto-check passed
  • Clickhouse Io

    affaan-m/ECC

    ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

    274k GitHub starsUsed in 1 repo~2.7k tokens
    DatabasesAuto-check passed
  • How to add a new attribute value (dimension) that the generic org-scoped telemetry.query analytics endpoint can group by and filter on.

    272 GitHub stars~2.4k tokensUpdated today
    DatabasesAuto-check passed
  • Clickhouse Io

    xu-xiang/everything-claude-code-zh

    ClickHouse 数据库模式、查询优化、分析以及高性能分析工作负载的数据工程最佳实践. An agent skill from xu-xiang/everything-claude-code-zh.

    2k GitHub stars~2.1k tokensUpdated 7 mo ago
    DatabasesAuto-check passed

More from chmonitor/chmonitor

All 53 skills in this repo
  • Hyperframes Creative

    chmonitor/chmonitor

    Non-animation creative direction for HyperFrames videos. An agent skill from chmonitor/chmonitor.

    298 GitHub starsUsed in 5 repos~1.3k tokens
    Auto-check passed
  • Hyperframes Media

    chmonitor/chmonitor

    Audio and media assets for HyperFrames compositions, produced by one shared audio engine (scripts/audio.mjs) — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), background music + sound…

    298 GitHub starsUsed in 1 repo~2.8k tokens
    Auto-check: notes
  • Remotion To Hyperframes

    chmonitor/chmonitor

    Port an existing Remotion (React) composition to HyperFrames HTML.

    298 GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed
  • Music To Video

    chmonitor/chmonitor

    A skill your agent uses when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to hard-hitting.

    298 GitHub starsUsed in 1 repo~4k tokens
    Auto-check: notes
  • Hyperframes Animation

    chmonitor/chmonitor

    All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus…

    298 GitHub starsUsed in 2 repos~1.8k tokens
    Auto-check passed
  • Faceless Explainer

    chmonitor/chmonitor

    turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video, up to ~3 min (sweet spot 30-90s), where every visual is invented (typography, abstract graphics…

    298 GitHub stars~4.5k tokensUpdated yesterday
    Auto-check: notes

Works with

Categories

Questions about Troubleshooting

What does Troubleshooting do?

Diagnose and resolve ClickHouse issues: OOM, slow merges, stuck mutations, query failures with error codes, and systematic error clustering. Troubleshooting is an agent skill from chmonitor/chmonitor. Diagnose and resolve ClickHouse issues: OOM, slow merges, stuck mutations, query failures with error codes, and systematic error clustering.

When should I use Troubleshooting?

Troubleshooting fits situations like: tasks that involve Data warehousing.

How do I install Troubleshooting in Claude Code?

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

How do I install Troubleshooting in Codex?

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

Can I use Troubleshooting 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 chmonitor/chmonitor --skill troubleshooting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/troubleshooting, .gemini/skills/troubleshooting, .github/skills/troubleshooting and .opencode/skills/troubleshooting in your project.

What does Troubleshooting need to run?

Going by SKILL.md and its folder, Troubleshooting needs the command-line tools its instructions call (curl).

Does Troubleshooting access the network?

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

Is Troubleshooting 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 Troubleshooting use?

Troubleshooting is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Troubleshooting use?

About 674 tokens (SKILL.md is roughly 2.7k 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 Troubleshooting?

Skills that share tags, products or a category with Troubleshooting: Clickhouse Architecture Advisor (vemetric/vemetric, 394 stars), Clickhouse Io (affaan-m/ECC, 274k stars), Clickhouse Io (affaan-m/ECC, 274k stars) and Clickhouse Io (affaan-m/ECC, 274k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Troubleshooting?

chmonitor (a GitHub organization) maintains it in chmonitor/chmonitor, which has 298 GitHub stars. The repository holds 53 skills in this directory. The repository was last updated on October 5, 2026.

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