mcpbeat Sign in

Diagnose Clickhouse Errors Agent Skill

Diagnose ClickHouse runtime query failures when the user wants database-level cause and fix guidance from an error or numeric error code, not source-code root cause analysis.

2k tokens
context cost
the whole folder, loaded on every use
6
files
instructions only
0
copies elsewhere
how many repositories repackaged it
325
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/FrankChen021/datastoria --skill diagnose-clickhouse-errors

The instruction itself

3 sections, as written by the author

When Not To Use

Do not use this skill when the user's primary goal is:

  • investigating application or repository source code
  • tracing where failing SQL was constructed in code
  • finding code paths that produced the ClickHouse error

In those cases, prefer source-code-inspection. Do not start this skill's error-code intake flow unless the user is asking for database-level diagnosis.

Workflow

  • Determine whether the user is asking for database-level diagnosis or source-code investigation. If the primary goal is source-code investigation or file-cited code analysis, stop and prefer source-code-inspection.
  • Extract the numeric ClickHouse error code from the conversation or error text (e.g. Code: 60).
  • If no numeric error code is detected and the user is asking for database-level diagnosis, call ask_user_question with exactly one question. Do NOT reply with natural-language text before the tool call.
  • header: Please provide a ClickHouse error code for diagnosis
  • options: [ { "id": "error_code", "label": "error code", "input": "text" } ]
  • Treat the returned value as the numeric error code and continue.
  • Load references/<code>.md with skill_resource (e.g. references/60.md) and follow its workflow.
  • If the orchestrator provides database context facts, use them when they materially change the cause or fix.
  • If skill_resource returns nothing, use your ClickHouse knowledge to provide a best-effort response.

Response format

  • Section 1 (Cause) — One short sentence explaining why the error occurred.
  • Section 2 (Fix) — Bullet list of concrete steps.
  • Section 3 (Example) — A single fenced SQL block with the corrected query; omit if not applicable.

Heading rules:

  • Default (English): use headings ## Cause, ## Fix, and optional ## Example.
  • If a response language is specified by system policy or user message (Response language (BCP-47): …), localize the heading text to that language while keeping the same 3-section structure.
  • Keep SQL, codes, and identifiers as-is.

Keep answers brief and action-first. Do not repeat the raw error verbatim. Do not add extra headings.

Other skills for the same job

different authors, same section of the catalogue
Biorxiv Database
by christophacham
×4

Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.

9k tokens scripts
Brenda Database
by christophacham
×4

Access BRENDA enzyme database via SOAP API. Retrieve kinetic parameters (Km, kcat), reaction equations, organism data, and substrate-specific enzyme information for biochemical research and metabolic pathway analysis.

36k tokens scripts
Clinpgx Database
by christophacham
×4

Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions.

13k tokens scripts
Clinvar Database
by christophacham
×4

Query NCBI ClinVar for variant clinical significance. Search by gene/position, interpret pathogenicity classifications, access via E-utilities API or FTP, annotate VCFs, for genomic medicine.

10k tokens
Cosmic Database
by christophacham
×4

Access COSMIC cancer mutation database. Query somatic mutations, Cancer Gene Census, mutational signatures, gene fusions, for cancer research and precision oncology. Requires authentication.

6k tokens scripts
Ensembl Database
by christophacham
×4

Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.

8k tokens scripts
Fda Database
by christophacham
×4

Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.

32k tokens scripts
Gene Database
by christophacham
×4

Query NCBI Gene via E-utilities/Datasets API. Search by symbol/ID, retrieve gene info (RefSeqs, GO, locations, phenotypes), batch lookups, for gene annotation and functional analysis.

13k tokens scripts

How to use it

Copy the folder

Take frankchen021/diagnose-clickhouse-errors from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.