In `extract*` helpers under `internal/provider/**/resource_*.go` that feed `Replace*`/`Update*` SDK calls, never collapse `IsNull()` and `IsUnknown()` into one branch. Null = clear; unknown = omit.
69
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
67%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 excels at specificity and distinctiveness, clearly defining a narrow coding convention for Terraform provider development. Its main weaknesses are the lack of an explicit 'Use when...' clause and limited natural language trigger terms that a user might employ when encountering this issue. The technical precision is excellent but discoverability could be improved.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when writing or reviewing extract* helper functions in Terraform provider resource files, or when handling null vs unknown Terraform attribute values.'
Include broader natural language trigger terms such as 'Terraform provider', 'null vs unknown handling', 'terraform attribute extraction', 'plan modifier behavior' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists very specific concrete actions: distinguishing IsNull() vs IsUnknown() in extract helpers, specifying the file pattern (internal/provider/**/resource_*.go), the SDK calls (Replace*/Update*), and the semantic meaning (Null = clear; unknown = omit). | 3 / 3 |
Completeness | The 'what' is clearly stated (never collapse IsNull and IsUnknown into one branch), but there is no explicit 'Use when...' clause. The 'when' is only implied by the file path pattern and function names, not explicitly stated as a trigger condition. | 2 / 3 |
Trigger Term Quality | It includes some relevant technical keywords like 'extract helpers', 'IsNull()', 'IsUnknown()', 'Replace', 'Update', 'SDK calls', and file path patterns. However, these are highly technical and a user might describe the problem differently (e.g., 'terraform provider', 'null handling', 'resource extraction'). Missing broader natural language variations. | 2 / 3 |
Distinctiveness Conflict Risk | This is an extremely narrow and specific skill targeting a particular coding pattern in Terraform provider resource files. It is highly unlikely to conflict with other skills due to its very specific file path pattern, function names, and the precise behavioral rule it encodes. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent, tightly scoped skill. It identifies a specific anti-pattern, provides an executable fix with clear semantics for each branch, and explains the consequence concisely. It's a model of token efficiency for a single-purpose corrective skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every token earns its place. No explanation of what null/unknown means in general, no background on Terraform's type system—just the trigger, the fix, and the minimal 'why' needed to understand the consequence. Extremely lean. | 3 / 3 |
Actionability | Provides a concrete, copy-paste-ready Go code pattern showing exactly how to handle each branch, with clear comments explaining the semantic difference (omit key vs. explicit empty). The trigger condition is specific enough to identify the anti-pattern in code. | 3 / 3 |
Workflow Clarity | This is a simple, single-purpose skill (pattern recognition + fix). The sequence is unambiguous: identify the trigger pattern, apply the two-branch fix. No multi-step or destructive workflow requiring validation checkpoints. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines with a single focused task and no need for external references, the content is well-organized with clear sections (Trigger, Fix, Why). No bundle files are needed. | 3 / 3 |
Total | 12 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
f197371
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.