data-workflows: Skill for Claude Code

.claude/skills/job-troubleshooting/SKILL.md

job-troubleshooting is a skill for Claude Code from boettiger-lab/data-workflows. It costs 88 tokens per session (2,698 once invoked), scanned A, original, BSD-3-Clause.

A guide to diagnosing stuck or failed Kubernetes jobs and DuckDB errors when reading Parquet files, a column-based data format. It covers problems such as out-of-memory kills, storage limits, missing files, map tiles, and a remote-reader crash on very large data chunks.

In plain words
What is it for?
Use it to investigate pod failures, evictions, scratch storage, quotas, conversion errors, blank PMTiles maps, and DuckDB reads from remote Parquet files.
Why use it?
It helps identify the underlying cause before repeating a failed job. That avoids rerunning the same broken configuration and distinguishes bad data from limits or bugs in the tools reading it.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is boettiger-lab/data-workflows's own configuration. It tells Claude Code how to work on data-workflows itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything data-workflows configures →

Reuse

Borrowing it

Nothing to install: this file belongs to boettiger-lab/data-workflows. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/boettiger-lab/data-workflows/main/.claude/skills/job-troubleshooting/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/boettiger-lab/data-workflows

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for job-troubleshooting

README.md
[![agentmods](https://agentmods.dev/badge/skills/boettiger-lab/data-workflows/job-troubleshooting.svg)](https://agentmods.dev/skills/boettiger-lab/data-workflows/job-troubleshooting)
Your own site
<a href="https://agentmods.dev/skills/boettiger-lab/data-workflows/job-troubleshooting"><img src="https://agentmods.dev/badge/skills/boettiger-lab/data-workflows/job-troubleshooting.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,698 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00088 $0.02698
Opus 5 $0.00044 $0.01349
Sonnet 5 $0.00018 $0.00540
Haiku 4.5 $0.00009 $0.00270

Measured 8d ago against content hash 1da01a89f9cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

job-troubleshooting scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**404 on convert → verify source URLs** with `curl -I` and directory listings (most common failure — always verify BEFORE generating YAMLs).
.claude/skills/job-troubleshooting/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Job Troubleshooting

Diagnose before resubmitting — a failing job re-run unchanged fails the same way.

⛔ Serialization standard: DuckDB httpfs stoi crash on oversized column chunks

The MCP can abort with SQL Error: stoi when reading GeoParquet over S3/httpfs. The root cause is a DuckDB httpfs bug on large Parquet column chunks — not the CRS tag, writer, or geometry content. Fully diagnosed in datasets #106.

What triggers it

A single Parquet column chunk in the ~2.8–2.88 GB compressed / ~3.73–3.84 GB uncompressed range causes the httpfs reader to abort with stoi. No spatial function needed — SELECT COUNT(geom) (which decodes the column) is sufficient to crash; SELECT COUNT(*) (footer only, no decode) is fine. Local file reads always work — this is exclusively an httpfs path bug.

SELECT COUNT(*)  FROM read_parquet('https://…/repro-100000.parquet');   -- ✅ OK
SELECT COUNT(geom) FROM read_parquet('https://…/repro-100000.parquet'); -- ❌ stoi

The crash appears "plan-dependent" because queries that skip decoding the geometry column (e.g. filtered reads that never touch the oversized chunk) avoid it. Every individual row is valid; the data is not corrupt.

What does NOT matter

Hypothesis Verdict
creator: geopandas ❌ cng-convert-written file crashes identically
OGC:CRS84 vs EPSG:4326 CRS tag ❌ re-tagging as EPSG:4326 still crashes
Plain DuckDB COPY re-write ❌ still crashes
A single pathological geometry ❌ local read of same file returns all rows

Prevention (the real fix)

Keep row groups small enough that no single geometry column chunk exceeds ~1 GB compressed. For large-feature geometry (complex multipolygons, national-scale data), the default --row-group-size 100000 can pack a single chunk well past the 2.8 GB cliff. Use --row-group-size 2000 as a safe default for geometry-heavy datasets, or estimate avg(octet_length(ST_AsWKB(geom))) on a sample and size accordingly. Tracked in cng-datasets #106.

Read the full file on GitHub · 120 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 120 lines · 88 tokens per session scan A 1da01a89f9cb

Subscribe to this mod's changes

job-troubleshooting is a skill published in the GitHub repository boettiger-lab/data-workflows (5 stars, last pushed today), licensed BSD-3-Clause. It adds 88 tokens to every session and 2,698 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

polar-local-environment

This skill should be used when setting up or managing Polar local development environment with Docker.

fcakyon/claude-codex-settings · 22 tokens

qdrant-deployment-options

Guides Qdrant deployment selection. Use when someone asks 'how to deploy Qdrant', 'Docker vs Cloud', 'local mode', 'embedded Qdrant', 'Qdrant EDGE', 'which deployment option', 'self-hosted vs cloud', or 'need lowest latency deployment'. Also use when choosing between deployment types for a new project.

qdrant/skills · 79 tokens

azuresql-db-container

Runs the Azure SQL Database container (the Azure SQL Database engine) locally (Private Preview): the real PaaS engine where SERVERPROPERTY('EngineEdition') returns 5 and Edition is 'SQL Azure'. This is NOT the SQL Server image mcr.microsoft.com/mssql/server. Use when a user wants to "run Azure SQL locally", "add a…

microsoft/azure-sql-database-container · 212 tokens

azuresql-db-from-sql-server

Migrates a local SQL Server setup to the Azure SQL Database container for Azure-faithful local development. Use when a project already uses mcr.microsoft.com/mssql/server, mssql/server, an sqlcmd plus SA password docker setup, a "SQL Server in docker" or "local mssql container", or a docker-compose with the…

microsoft/azure-sql-database-container · 200 tokens

azuresql-db-schema-migration

Runs database schema migrations against the local Azure SQL Database container so the same migrations apply identically on the local engine and in the Azure cloud. Use when asked to "run my migrations against the local SQL", "apply schema to the container", "apply EF Core / dotnet ef database update", "Prisma migrate…

microsoft/azure-sql-database-container · 151 tokens

cnpg

Create and operate CloudNativePG (CNPG) Postgres databases on Kubernetes the GitOps/Flux way - on managed cloud (GKE + GCS via Workload Identity) OR self-hosted (K3s/bare-metal + any S3-compatible store via a credentials secret). Covers Cluster + ScheduledBackup manifests, barman WAL archiving, pgvector, PITR…

vanducng/skills · 155 tokens