CtrlK
BlogDocsLog inGet started
Tessl Logo

provider-resources

Implement Terraform Provider resources and data sources using the Plugin Framework: CRUD operations, schema design, plan modifiers and validators, not-found handling, waiters for eventually consistent APIs, import support, resource design principles, and required acceptance test coverage. Use when adding or changing a resource or data source, deciding whether an API concept should be a resource, wiring a resource to the provider's configured client, handling drift or resource-not-found, or reviewing a resource implementation before submission.

71

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A high-quality, dense reference for Framework resource implementation: fully executable code for every operation, real one-level-deep bundle references, and a closing pre-submission checklist. The workflow is implicit in section order rather than explicitly sequenced, and a couple of edge-case paragraphs (mux detection, legacy docs trees) could be trimmed or moved to a reference.

DimensionReasoningScore

Conciseness

Nearly every token is load-bearing: executable Go for each CRUD operation, schema, finder, waiter, and acceptance test, plus an attribute-type table and a checklist — no padding explaining what Terraform or CRUD is. Minor trimmable material exists (the muxing/go.mod detection paragraph and the note about legacy website/docs trees in older providers), keeping it just below the lean level-5 anchor.

4 / 5

Actionability

The guidance is copy-paste ready: complete, compilable Framework code for Configure, Schema, Create/Read/Update/Delete, ImportState, finders with typed not-found errors, a StateChangeConf waiter, and a full TestAccWidget_basic test with config helper. Specific tooling commands (tfplugindocs, go generate ./...) and concrete naming grammar cover the common cases exactly as the level-5 anchor requires.

5 / 5

Workflow Clarity

The body follows a coherent implementation order — check design principles "before implementing", file structure, resource skeleton, CRUD, testing, docs — and closes with an explicit Pre-Submission Checklist that serves as a validation checkpoint, plus error-recovery guidance (not-found → remove from state, already-deleted → success). The sequence is conveyed by section ordering rather than explicit step numbering, and there is no validate-then-proceed loop mid-workflow, so it matches level 4 rather than the fully explicit level-5 anchor.

4 / 5

Progressive Disclosure

The skill is a clear overview with well-signaled, one-level-deep references: an up-front "References (load when needed)" block naming references/design-principles.md and references/retries-and-waiters.md, both of which exist in the bundle, reinforced by inline pointers at the point of need ("full treatment in references/design-principles.md", "read it whenever the API is asynchronous or eventually consistent"). Deep material is correctly split out of SKILL.md, matching the level-5 anchor.

5 / 5

Total

18

/

20

Passed

Description

88%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.

A strong description: it states what the skill does through a comprehensive list of concrete capabilities and pairs it with an explicit, multi-trigger "Use when" clause using natural phrasing. Voice is correct third-person imperative with no fluff or over-claims; the only weakness is a few natural trigger scenarios (import, acceptance-test authoring, schema-only work) not mirrored in the when-clause.

DimensionReasoningScore

Specificity

The description lists eight concrete, specific actions — "CRUD operations, schema design, plan modifiers and validators, not-found handling, waiters for eventually consistent APIs, import support, resource design principles, and required acceptance test coverage" — which comprehensively covers the domain with no vague filler. It matches the level-5 anchor (multiple specific concrete actions, comprehensive) and exceeds level 4, which allows coverage gaps.

5 / 5

Completeness

Both halves are explicit: the what-clause enumerates concrete capabilities, and an explicit "Use when adding or changing a resource or data source, deciding whether an API concept should be a resource, wiring a resource to the provider's configured client, handling drift or resource-not-found, or reviewing a resource implementation before submission" gives multiple concrete trigger phrases. This is a direct match for the level-5 anchor; level 4 would require the when-clause to be less explicit or specific.

5 / 5

Trigger Term Quality

Triggers include natural phrases users would say — "adding or changing a resource or data source", "handling drift or resource-not-found", "reviewing a resource implementation" — with synonym variation. A few natural entry points are missing from the when-clause (e.g., implementing import, writing acceptance tests, or schema/plan-modifier work without an existing resource), so it sits at level 4 rather than comprehensive level-5 coverage.

4 / 5

Distinctiveness Conflict Risk

The niche is clear — implementing resources/data sources in a Terraform provider on the Plugin Framework — and distinct from adjacent concerns (provider configuration, migration). Minor overlap risk remains with closely related skills the body itself references (provider-test-patterns for acceptance-test coverage, provider-framework-migration for SDKv2 changes), placing it at level 4 rather than the minimal-conflict level 5.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (522 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
hashicorp/agent-skills
Reviewed

Table of Contents

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.