CtrlK
BlogDocsLog inGet started
Tessl Logo

tinybird-python-sdk-guidelines

Tinybird Python SDK for defining datasources, pipes, and queries in Python. Use when working with tinybird-sdk, Python Tinybird projects, or data ingestion and queries in Python.

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/tinybird-python-sdk-guidelines/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 itself is exemplary in token efficiency and offers concrete CLI commands, but it is an index whose substance lives entirely in 11 rules files that are absent from the bundle, leaving the core SDK task with no executable guidance. Additionally, the dev→build→deploy workflow has no sequencing or validation checkpoints despite deploy targeting production.

Suggestions

Ship the 11 referenced rules/*.md files with the bundle, or if they cannot be included, inline minimal working examples for defining a datasource and a pipe in Python so the skill is usable standalone.

Convert the Quick Reference into an explicitly sequenced workflow (init → dev → build → deploy) with a validation step before deploy, e.g., verifying build output or running tests before "tinybird deploy" targets production.

Make the rule file references actionable when present — one line per file describing when to consult it (e.g., "rules/connections.md — Kafka/S3/GCS connection setup") so Claude knows which file to open for which task.

DimensionReasoningScore

Conciseness

The body is lean bullets and a command list with zero concept over-explanation or padding — no "what is Tinybird" prose, no filler. Every line carries information, matching the "every token earns its place" anchor; there is at most one redundant intro line, not enough to drop to anchor 4.

5 / 5

Actionability

The Quick Reference gives copy-paste-ready commands ("pip install tinybird-sdk", "tinybird init", "tinybird dev/build/deploy/preview/migrate"), but the body contains no Python code for the skill's core task — defining datasources, pipes, or endpoints — and the files that would carry those examples are missing from the bundle. Concrete commands with gaps in the primary use case fits anchor 4 better than the fully-executable anchor 5.

4 / 5

Workflow Clarity

The Quick Reference lists commands in rough lifecycle order (install → init → dev → build → deploy) but presents them as an unsequenced reference list, and there are no validation or verification checkpoints anywhere — notably "tinybird deploy" targets production with no pre-deploy check. Sequence present but checkpoints missing matches anchor 3; it is too defined for anchor 2 and lacks any validation for anchor 4.

3 / 5

Progressive Disclosure

The structure is nominally ideal — a short overview with 11 clearly signaled one-level-deep rules/*.md references — but checking the actual bundle shows none of the referenced rule files exist (no rules/ directory at all). Every reference dangles, so progressive disclosure fails at its purpose: the SKILL.md is a well-organized index to content that is not there. This broken disclosure chain pulls it down to anchor 3 despite good nominal structure.

3 / 5

Total

15

/

20

Passed

Description

70%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 solid description with an explicit third-person "what" plus a "Use when" trigger clause, clearly anchored to a distinct product niche. Its main weaknesses are incomplete action coverage relative to the skill's full scope and a "when" clause that reuses the "what" phrasing instead of adding new concrete triggers.

Suggestions

Broaden the capability list to match the skill's actual scope, e.g., "defining datasources, pipes, and endpoints; creating clients; configuring connections; and running build/deploy workflows".

Add concrete trigger terms users would naturally say, such as ".datasource/.pipe files", "tinybird CLI", "materialized views", or "Tinybird ingestion".

DimensionReasoningScore

Specificity

"defining datasources, pipes, and queries" names the domain plus about three concrete actions, but the description omits endpoints, connections, materialized views, migration, and deployment that the skill body itself claims to cover. The gaps are more than minor, so this fits anchor 3 rather than anchor 4.

3 / 5

Completeness

Both parts are present: a clear "what" ("Tinybird Python SDK for defining datasources, pipes, and queries in Python") and an explicit "Use when working with..." clause. The "when" clause largely mirrors the "what" phrasing and could name more concrete trigger situations, so it sits at anchor 4 rather than 5.

4 / 5

Trigger Term Quality

Triggers "tinybird-sdk", "Python Tinybird projects", and "data ingestion and queries in Python" give good natural keyword coverage of the product and package names. A few natural terms users would say are missing (e.g., ".datasource"/".pipe" files, "endpoints", "materialized views"), which matches anchor 4 rather than the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

"tinybird-sdk" and "Python Tinybird projects" establish a clear, distinct niche with minimal conflict risk. However, the generic trigger "data ingestion and queries in Python" could fire for non-Tinybird data work, creating minor overlap with general data-engineering skills — anchor 4, not the minimal-conflict anchor 5.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.