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.

68

Quality

84%

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

76%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.

A well-structured, highly actionable library-usage skill: executable examples throughout, a useful decision tree, and a real reference bundle. The main gaps are a missing validation checkpoint after batch writes (capping workflow clarity) and a dangling reference to a nonexistent examples/examples.md file.

Suggestions

Add a validation checkpoint after the Writing Data `.execute()` step (e.g., re-read the target DataStore and verify row counts or sample rows), since batch database writes currently lack any feedback loop.

Create the missing examples/examples.md file that the body references three times, or remove/fix those references — a dangling link breaks navigation and the promised 'runnable examples with expected output'.

De-duplicate the `from_mysql(...)` connection boilerplate that appears verbatim in three sections; define it once and reference it, tightening the token budget.

DimensionReasoningScore

Conciseness

The body is lean and code-first with no explanations of concepts Claude already knows, but there is minor repetition: the full `from_mysql(host="db:3306", database="shop", table="orders", user="root", password="pass")` boilerplate appears verbatim in the Connect, Cross-Source Join, and Writing Data sections. This fits the 4 anchor (efficient with minor instances that could be trimmed) better than the 5 anchor's "every token earns its place".

4 / 5

Actionability

All examples are copy-paste-ready executable code covering the common cases: connection patterns for files/databases/S3/URIs, the full pandas API surface, a complete cross-source join pipeline, a write pipeline, and a troubleshooting table with concrete fixes (e.g., "Include port in host: `host=\"db:3306\"` not `host=\"db\"`"). This matches the top anchor: fully executable, specific examples covering common cases.

5 / 5

Workflow Clarity

The Decision Tree gives a clear selection sequence and troubleshooting provides debug tools (`.to_sql()`, `python scripts/verify_install.py`), but the Writing Data workflow ends in `.execute()` — a batch database/file write — with no validation checkpoint or feedback loop (e.g., verify row counts or re-read the target). Per the rubric's cap for database/batch operations lacking validation, workflow clarity cannot exceed 3; it is above the 2 anchor because sequences and debug guidance are present.

3 / 5

Progressive Disclosure

The body is a genuine overview with well-signaled, one-level-deep references: [connectors.md](references/connectors.md), [api-reference.md](references/api-reference.md), and [scripts/verify_install.py](scripts/verify_install.py) all exist in the bundle. However, [examples.md](examples/examples.md) is referenced three times (decision tree, join section, References list) but the file does not exist — a broken navigation link that goes beyond the 5 anchor's "easy navigation", landing on the 4 anchor's "minor organization gaps".

4 / 5

Total

16

/

20

Passed

Description

92%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.

A strong description: concrete capabilities with named sources and formats, explicit third-person trigger guidance covering both positive and negative cases, and clear boundaries against adjacent skills. The only weakness is a handful of missing natural synonyms (e.g., file extensions, "data analysis").

DimensionReasoningScore

Specificity

The description lists multiple concrete actions with named technologies: "Use `import chdb.datastore as pd`... same API, 10-100x faster", "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". This matches the anchor for multiple specific concrete actions with comprehensive coverage; a 4 would require minor gaps, but the what/how coverage here is broad and concrete throughout.

5 / 5

Completeness

It 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, speed up slow pandas code... even if they don't explicitly mention chdb or DataStore"), plus negative triggers ("Do NOT use for raw SQL queries, ClickHouse server administration, or non-Python languages"). This is a clear match for the top anchor with concrete trigger phrases in third-person voice.

5 / 5

Trigger Term Quality

Natural trigger phrases are strong: "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 format/source names users actually say. It falls just short of the 5 anchor because a few natural synonyms are missing (e.g., "data analysis", file extensions like .parquet/.csv); it is well above the 3 anchor since keyword coverage goes well beyond "some relevant keywords".

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (pandas-compatible analysis backed by ClickHouse) and explicitly de-conflicts from adjacent skills via "Do NOT use for raw SQL queries, ClickHouse server administration", which separates it from a companion chdb-sql skill. Overlap with plain pandas usage is intentional (drop-in replacement) and the explicit trigger guidance keeps conflict risk minimal, matching the 5 anchor rather than the 4 anchor's "minor overlap risk".

5 / 5

Total

19

/

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.

Validation — 15 / 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.