Guide for running acceptance tests for a Terraform provider. Use this when asked to run an acceptance test or to run a test with the prefix `TestAcc`.
99
87%
Does it follow best practices?
Impact
100%
2.17xAverage score across 16 eval scenarios
Passed
No known issues
Quality
Discovery
89%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 is a solid, focused description that clearly identifies its niche (Terraform provider acceptance tests) and provides explicit trigger conditions including the specific 'TestAcc' prefix convention. Its main weakness is that the 'what' portion is somewhat thin—it says 'guide for running' but doesn't elaborate on what specific guidance or actions it provides beyond just running tests.
Suggestions
Expand the capability description with more specific actions, e.g., 'Guide for running acceptance tests for a Terraform provider, including environment setup, test selection, and debugging failures.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Terraform provider acceptance tests) and one action (running tests), but doesn't list multiple concrete actions like configuring test environments, debugging failures, or interpreting results. | 2 / 3 |
Completeness | Clearly answers both 'what' (guide for running acceptance tests for a Terraform provider) and 'when' (when asked to run an acceptance test or to run a test with the prefix TestAcc), with explicit trigger conditions. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'acceptance tests', 'Terraform provider', 'run a test', 'TestAcc' prefix. These are terms users would naturally use when needing this skill, covering both the general concept and the specific naming convention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Terraform provider acceptance tests with the specific 'TestAcc' prefix. This is unlikely to conflict with general testing skills or other Terraform-related skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise skill that clearly covers three related workflows for Terraform acceptance testing. Its main weakness is that commands aren't presented as fully copy-paste-ready examples (e.g., complete shell commands with environment variables inline). The diagnostic escalation ladder and flip procedure are particularly well-designed with clear sequencing and feedback loops.
Suggestions
Add a complete, copy-paste-ready shell command example for the basic run, e.g., `TF_ACC=1 go test -run=TestAccFeatureHappyPath ./path/to/package`
Include a brief concrete code example for the 'flip' procedure showing what editing a TestCheckFunc value looks like in practice
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every sentence provides actionable, non-obvious information specific to Terraform acceptance testing. No unnecessary explanations of Go testing, Terraform, or basic concepts. The content is lean and assumes Claude's competence. | 3 / 3 |
Actionability | Provides specific commands, environment variables, and flags, but lacks fully copy-paste-ready command examples (e.g., a complete `TF_ACC=1 go test -run=TestAccFeatureHappyPath ./...` one-liner). The 'flip' procedure is concrete but the instruction to 'edit the value of one of the TestCheckFuncs' is somewhat vague without a code example. | 2 / 3 |
Workflow Clarity | Three distinct workflows (running, diagnosing, flipping) are clearly sequenced with numbered steps. The diagnosis workflow is explicitly cumulative, and the flip workflow includes a validation/feedback loop (expect failure, undo if successful, report outcome). | 3 / 3 |
Progressive Disclosure | The skill is under 50 lines and covers a single focused task domain. Content is well-organized into three logical sections (running, diagnosing, flipping) without needing external references. Structure is clear and navigable. | 3 / 3 |
Total | 11 / 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.
a4e097d
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.