rill-connector

Detailed instructions and examples for developing connector resources in Rill

Quality

46%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/rill-connector/SKILL.md

Quality

Content

43%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 skill is a well-organized, highly actionable connector catalog with strong copy-paste YAML examples, but it is weighed down by a massive inlined JSON schema, lacks a sequenced develop-and-validate workflow, and uses no progressive disclosure into separate reference files.

Suggestions

Move the full JSON schema (and optionally the per-driver reference) into a separate reference file (e.g. references/connector-schema.json) and link to it from SKILL.md to recover token budget and improve progressive disclosure.

Add an explicit numbered workflow for developing a connector (create connectors/<name>.yaml, set driver + credentials, run a validate/test command, then iterate) with a validation checkpoint before relying on the connection.

Trim the inlined schema block or summarize only the most-used properties per driver inline, keeping the exhaustive property list in the external reference.

Dimension	Reasoning	Score
Conciseness	Although the prose sections are efficient and Rill-specific, roughly 1150 lines of a verbatim JSON schema are inlined directly in SKILL.md, a large token cost that matches anchor 2's 'noticeably verbose; several unnecessary... padded sections'.	2 / 5
Actionability	The body provides many copy-paste-ready YAML examples covering all common drivers and properties, but there is no validate/test CLI command or end-to-end runnable workflow, leaving the minor gaps of anchor 4.	4 / 5
Workflow Clarity	There is no explicit sequenced 'develop a connector' workflow and no validation/test checkpoint, despite a managed-provisioning billing risk; only a rough implicit sequence is inferable from the examples, matching anchor 2.	2 / 5
Progressive Disclosure	The content has good structure (clear headers and a navigation TOC), but the full JSON schema and driver catalog that clearly belong in separate reference files are inlined with no external bundle, matching anchor 3's 'some structure... content that should be separate is inline'.	3 / 5
	Total	11 / 20 Passed

Description

48%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 clearly identifies its Rill-connector niche in third person but is thin on concrete actions and entirely lacks a 'Use when' trigger clause, capping completeness. It is distinguishable but would benefit from listing specific capabilities and explicit trigger guidance.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when creating or configuring Rill connectors, connecting to data sources, or setting up OLAP drivers'.

Replace the generic 'developing connector resources' with specific actions such as 'define credentials, configure OLAP/SQL/object-store drivers, and set up dev/prod connector environments'.

Include natural synonyms and file extensions users might say, such as 'connectors/*.yaml', 'data source', or specific driver names (S3, DuckDB, ClickHouse).

Dimension	Reasoning	Score
Specificity	The phrase 'developing connector resources in Rill' names a concrete domain but offers only a single generic action ('developing'), while 'Detailed instructions and examples' describes the artifact rather than listing concrete capabilities; this is below anchor 3, which expects 1-2 concrete actions.	2 / 5
Completeness	It clearly states the 'what' ('developing connector resources in Rill') but provides no 'Use when...' trigger clause, so per the boundary guidance completeness is capped at 3.	3 / 5
Trigger Term Quality	'Rill' and 'connector' are the natural terms a user would say, matching anchor 3's 'some relevant keywords but missing common variations or synonyms'; it omits synonyms like 'data source', specific driver names, and '.yaml'.	3 / 5
Distinctiveness Conflict Risk	'Rill' pins a clear niche with minimal conflict risk, but 'connector' is still somewhat generic, leaving minor overlap risk with related data-tooling skills, matching anchor 4.	4 / 5
	Total	12 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1660 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: rilldata/agent-skills
Path: skills/rill-connector/SKILL.md
Commit: 84f7d7c

Reviewed: about 5 hours ago

Table of Contents

Discovery Implementation Validation

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.