CtrlK
BlogDocsLog inGet started
Tessl Logo

chdb-datastore

Use when the user has tabular data (pandas DataFrame, parquet, csv, Arrow, json) and wants to filter, group, aggregate, join, or speed up slow pandas. Provides chDB DataStore — same pandas API, ClickHouse engine underneath. Also handles reading from S3, MySQL, PostgreSQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake as DataFrames and joining across sources. TRIGGER when: user mentions DataFrame, parquet, csv, "fast pandas", "speed up pandas", or cross-source DataFrame joins; user imports `chdb.datastore` or `from datastore import DataStore`. SKIP this skill for raw SQL syntax (use chdb-sql instead), ClickHouse server administration, or non-Python DataStore API work.

76

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

90%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, actionable overview with strong code examples and clean progressive disclosure to real reference files. Its main weakness is a missing referenced file (examples/examples.md) and the absence of explicit validation checkpoints, though the latter is largely optional for this read-only analysis skill.

Suggestions

Add the missing examples/examples.md file (referenced in the decision tree, the join section, and the References list) or remove/redirect those links to avoid a broken navigation path.

For the Writing Data section, add a brief validation checkpoint (e.g., verify row counts or call to_sql() before .execute()) to give the only mutating workflow an explicit feedback loop.

Fix the troubleshooting path 'python agent/skills/chdb-datastore/scripts/verify_install.py' to match the actual bundle location (scripts/verify_install.py) so the command is runnable as written.

DimensionReasoningScore

Conciseness

Lean and well-organized — the one-line import swap, decision tree, and compact code blocks assume Claude's competence with no padding about what pandas or a DataFrame is; every section earns its place.

5 / 5

Actionability

Provides copy-paste-ready, executable code for connection, filtering, selection, sorting, groupby, joins, and writing data, covering the common cases with concrete method calls.

5 / 5

Workflow Clarity

The numbered decision tree routes users to the right approach and the troubleshooting table offers a debug path via to_sql(), but there are no explicit validation checkpoints or feedback loops; this sits above 3 because sequencing is clear and the skill is primarily read-only analysis rather than destructive.

4 / 5

Progressive Disclosure

Good overview structure with a dedicated References section and clearly signaled one-level-deep links to api-reference.md, connectors.md, and verify_install.py (all present), but examples/examples.md is referenced three times and does not exist in the bundle — a minor but real navigation gap keeping it below 5.

4 / 5

Total

18

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: third-person voice, concrete actions, natural trigger terms with synonyms, explicit when-guidance, and clear disambiguation from a sibling skill. It satisfies every anchor at the top of the scale.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'filter, group, aggregate, join, or speed up slow pandas' plus reading from S3, MySQL, PostgreSQL, MongoDB, Iceberg, Delta Lake and joining across sources — giving comprehensive coverage rather than vague language.

5 / 5

Completeness

Explicitly answers both 'what' ('Provides chDB DataStore — same pandas API, ClickHouse engine underneath') and 'when' ('Use when...', 'TRIGGER when:'), with concrete trigger phrases and a SKIP clause.

5 / 5

Trigger Term Quality

Covers natural terms users would say — 'DataFrame, parquet, csv, "fast pandas", "speed up pandas", cross-source DataFrame joins' — including synonyms and file extensions, matching the comprehensive anchor.

5 / 5

Distinctiveness Conflict Risk

Clear niche (ClickHouse-backed pandas replacement) with distinct triggers plus explicit boundary guidance ('SKIP this skill for raw SQL syntax (use chdb-sql instead), ClickHouse server administration'), minimizing conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
chdb-io/chdb
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.