CtrlK
BlogDocsLog inGet started
Tessl Logo

chdb-datastore

Drop-in pandas replacement with ClickHouse performance. Use `import chdb.datastore as pd` (or `from datastore import DataStore`) and write standard pandas code — same API, 10-100x faster on large datasets. Supports 16+ data sources (MySQL, PostgreSQL, S3, MongoDB, ClickHouse, Iceberg, Delta Lake, etc.) and 10+ file formats (Parquet, CSV, JSON, Arrow, ORC, etc.) with cross-source joins. Use this skill when the user wants to analyze data with pandas-style syntax, speed up slow pandas code, query remote databases or cloud storage as DataFrames, or join data across different sources — even if they don't explicitly mention chdb or DataStore. Do NOT use for raw SQL queries, ClickHouse server administration, or non-Python languages.

72

Quality

90%

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

80%

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

The body is concise, highly actionable, and well-structured with a clear decision tree and copy-paste examples. It loses points on workflow_clarity for lacking an explicit validation checkpoint before destructive write/execute operations, and on progressive_disclosure because the referenced examples/examples.md bundle file is missing.

Suggestions

Add an explicit validate-before-execute checkpoint to the Writing Data workflow (e.g., inspect `target.to_sql()` or run a dry-run before calling `.execute()`), since it performs batch/destructive writes.

Create the missing examples/examples.md bundle file (referenced by the decision tree, the join section, and the References list) or remove/fix the broken links to it.

Consider a short validation step in the cross-source join example (e.g., assert key types match / call .to_sql() before relying on results) to turn the troubleshooting hint into an inline feedback loop.

DimensionReasoningScore

Conciseness

The body is lean and code-heavy, assuming Claude's competence — it never explains what pandas or ClickHouse is, and every section (decision tree, connect pattern, API snippet, join example, writing data, troubleshooting table) earns its tokens. Not a 2 because there is no padded explanation to trim; the only time-sensitive value ('version: 4.1') lives in frontmatter, not the body.

3 / 3

Actionability

Provides fully executable, copy-paste-ready code with real arguments — `import chdb.datastore as pd`, `DataStore.from_file("sales.parquet")`, `from_mysql(host=..., database=..., table=..., user=..., password=...)`, and a complete cross-source join pipeline. Not a 2 because the examples are concrete and complete rather than pseudocode or abstract direction.

3 / 3

Workflow Clarity

The decision tree sequences approach selection and the connect→analyze→join flow is clear, but the Writing Data section and cross-source joins perform destructive/batch operations via `.execute()` with no explicit validate-before-execute checkpoint or feedback loop, only a troubleshooting `to_sql()` hint. Per the rubric, missing validation in batch/database operations caps this at 2; it is not a 1 because steps are present and ordered.

2 / 3

Progressive Disclosure

The body is a well-organized overview pointing one level deep to real files (references/api-reference.md, references/connectors.md, scripts/verify_install.py), but it repeatedly references examples/examples.md which does not exist in the bundle — a broken navigation path. It is not a 3 because of that dangling reference, and not a 1 because real references are clearly signaled and appropriately split.

2 / 3

Total

10

/

12

Passed

Description

100%

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 excellent: it states concrete capabilities, gives natural trigger terms, answers both 'what' and 'when' with explicit positive and negative triggers, and is clearly distinct from sibling skills. No changes needed.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('analyze data with pandas-style syntax', 'speed up slow pandas code', 'query remote databases or cloud storage as DataFrames', 'join data across different sources') plus enumerated sources and file formats, matching the 'lists multiple specific concrete actions' anchor. It is not a 2 because coverage is comprehensive rather than partial, and it stays in third person.

3 / 3

Completeness

Explicitly answers both 'what' ('Drop-in pandas replacement with ClickHouse performance... same API, 10-100x faster') and 'when' ('Use this skill when the user wants to analyze data with pandas-style syntax...'), with explicit positive and negative triggers. Not a 2 because the 'Use when' clause is present and explicit rather than implied.

3 / 3

Trigger Term Quality

Includes natural terms users would actually say ('pandas', 'speed up slow pandas code', 'query remote databases', 'cloud storage', 'join data across different sources'), giving good coverage of common variations. Not a 2 because it covers multiple natural phrasings rather than a single relevant keyword.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (ClickHouse-backed pandas replacement) with distinct triggers and an explicit negative-trigger list ('Do NOT use for raw SQL queries, ClickHouse server administration, or non-Python languages') that separates it from a sibling chdb-sql skill. Not a 2 because the boundary is explicit and unlikely to overlap.

3 / 3

Total

12

/

12

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
MapleTechLabs/maple
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.