Detailed instructions and examples for developing connector resources in Rill
36
32%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/rill-connector/SKILL.mdQuality
Discovery
22%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is too vague and lacks the specificity needed for effective skill selection. It fails to enumerate concrete actions involved in developing connector resources and entirely omits a 'Use when...' clause. The mention of 'Rill' provides some domain anchoring, but the description needs significantly more detail about capabilities and trigger conditions.
Suggestions
Add a 'Use when...' clause specifying trigger conditions, e.g., 'Use when the user asks about configuring data sources, creating connector YAML files, or setting up database connections in Rill.'
Replace 'detailed instructions and examples' with specific concrete actions, e.g., 'Configures connector resources in Rill including database connections, cloud storage sources, and API integrations using YAML definitions.'
Include natural trigger terms users would say, such as 'data source', 'database connection', 'connector YAML', 'Rill connector', and specific connector types like 'PostgreSQL', 'BigQuery', 'S3'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'detailed instructions and examples' without listing any concrete actions. It does not specify what developing connector resources entails (e.g., configuring data sources, writing YAML definitions, setting up authentication). | 1 / 3 |
Completeness | The description only vaguely addresses 'what' (developing connector resources) and completely lacks any 'when' clause or explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | It includes 'connector resources' and 'Rill' which are relevant domain-specific keywords, but misses natural variations users might say such as 'data source', 'database connection', 'Rill connector YAML', or specific connector types. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Rill' and 'connector resources' provides some specificity, but 'developing connector resources' is broad enough to potentially overlap with other Rill-related skills or general connector/integration skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at providing concrete, executable YAML examples for every connector type, making it highly actionable. However, it is severely bloated — the inline JSON schema alone accounts for roughly half the content and duplicates the driver-specific sections. The lack of any file decomposition or progressive disclosure means this skill consumes far more context window than necessary, and the absence of validation/troubleshooting workflows limits its practical utility beyond initial configuration.
Suggestions
Extract the full JSON schema into a separate REFERENCE.md file and link to it from the main skill, reducing the body by ~50%.
Consolidate the driver-specific notes and examples sections — currently each driver is described twice (once in notes, once in examples). Merge into a single section per driver with a brief note and one example.
Add a workflow section with explicit steps: 1) Create connector YAML, 2) Add secrets to .env, 3) Validate connection (e.g., `rill env validate` or equivalent), 4) Troubleshoot common errors.
Remove the Introduction section's explanatory content about what connectors are and driver capabilities — Claude can infer this from the examples. Replace with a 2-line summary at most.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~800+ lines. The introduction explains basic concepts Claude already knows (what connectors are, what drivers do). The massive JSON schema reference at the end duplicates information already covered in the driver-specific notes and examples sections. Much of this content could be dramatically condensed. | 1 / 3 |
Actionability | The skill provides numerous complete, copy-paste ready YAML examples for every driver type, with proper secret templating and realistic configuration values. Each example includes file path comments and all required properties. | 3 / 3 |
Workflow Clarity | The skill covers connector configuration well but lacks explicit workflow steps for creating/validating connectors. There's no guidance on how to verify a connector works after creation, no troubleshooting steps for common connection failures, and no validation checkpoints despite connectors involving external system connections that can fail. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files. The full JSON schema (~400+ lines) is inlined when it should be in a separate reference file. Driver-specific notes, examples, and the schema could all be split into separate files with clear navigation from a concise overview. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1592 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
65ccd1f
Table of Contents
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.