provider-resources

Implement Terraform Provider resources and data sources using the Plugin Framework. Use when developing CRUD operations, schema design, state management, and acceptance testing for provider resources.

1.33x

Quality

82%

Does it follow best practices?

Impact

96%

1.33x

Average score across 16 eval scenarios

Securityby

Passed

No known issues

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, code-rich reference that scores well on concrete guidance but is held back by its monolithic ~590-line form and the absence of an explicit sequenced workflow with validation checkpoints. Splitting detail into reference files would notably improve it.

Suggestions

Move the heavier reference material (full schema/state/testing code catalogs, documentation standards template) into files under references/ and link to them one level deep, leaving SKILL.md as a concise overview with quick-start patterns.

Add an explicit step-by-step "Implementing a resource" workflow with validation checkpoints (e.g., compile → run acceptance test → verify import → check destroyed state) rather than presenting patterns only as a topical catalog.

Trim redundancy by picking one framework variant as the primary path and deferring the other (SDKv2 vs Plugin Framework) to a reference, reducing the inline token load.

Dimension	Reasoning	Score
Conciseness	The body is code-heavy rather than prose-padded, but at ~590 lines it is very long, inlining both SDKv2 and Plugin Framework patterns plus documentation templates and a checklist that could be deferred to references.	2 / 3
Actionability	Provides complete, executable Go code for every CRUD operation plus schema, state, testing, and error-handling patterns, along with copy-paste bash commands — fully actionable.	3 / 3
Workflow Clarity	Content is organized by topic and ends with a pre-submission checklist, but there is no explicit end-to-end sequenced workflow with validation checkpoints for the destructive CRUD operations, capping clarity at 2.	2 / 3
Progressive Disclosure	Sections are well-organized, but the entire 590-line reference is inline in SKILL.md with no bundle files or one-level-deep references, so content that should be split remains monolithic.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 strong, concise description that names concrete capabilities and provides an explicit "Use when" trigger in third person. It cleanly answers both what the skill does and when to invoke it within a distinct, low-conflict niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Implement Terraform Provider resources and data sources", "developing CRUD operations, schema design, state management, and acceptance testing" — matching the level-3 anchor of several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ("Implement Terraform Provider resources and data sources using the Plugin Framework") and when ("Use when developing CRUD operations, schema design, state management, and acceptance testing") with an explicit "Use when" trigger.	3 / 3
Trigger Term Quality	Uses natural developer terms ("Terraform Provider", "Plugin Framework", "CRUD operations", "acceptance testing") that a user would actually say, in third person, giving good keyword coverage.	3 / 3
Distinctiveness Conflict Risk	Clearly niched to Terraform Provider Plugin Framework resource development with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (600 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: hashicorp/agent-skills
Commit: bde3ed3

Reviewed: about 2 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.