`terraform-tidy-before-import`: extract from `terraform-search-import` by bbasata · Pull Request #66 · hashicorp/agent-skills

bbasata · 2026-04-17T11:40:10Z

github-actions · 2026-04-17T18:22:28Z

Tessl Skill Review Results

Skill	Status	Review Score	Change
`terraform/code-generation/skills/terraform-search-import`	✅ PASSED	92%
`terraform/code-generation/skills/terraform-tidy-before-import`	✅ PASSED	92%

Detailed Review

terraform/code-generation/skills/terraform-search-import — 92% (PASSED)

  Description: 92%
    \(.key): \(.value.score)/3 - \(.value.reasoning)
    \(.key): \(.value.score)/3 - \(.value.reasoning)
    \(.key): \(.value.score)/3 - \(.value.reasoning)
    \(.key): \(.value.score)/3 - \(.value.reasoning)

    Assessment: This is a well-structured description that clearly communicates both what the skill does and when to use it. The 'Use when...' clause provides three distinct trigger scenarios. The main weakness is that the capability description could be more specific about concrete actions beyond discover and import (e.g., generating configuration blocks, updating state files).

  Content: 92%
    \(.key): \(.value.score)/3 - \(.value.reasoning)
    \(.key): \(.value.score)/3 - \(.value.reasoning)
    \(.key): \(.value.score)/3 - \(.value.reasoning)
    \(.key): \(.value.score)/3 - \(.value.reasoning)

    Assessment: This is a well-structured, highly actionable skill that provides concrete executable examples for Terraform Search and bulk import workflows. The decision tree and progressive complexity of examples are strong points. The main weakness is moderate redundancy between sections (discovery commands repeated, some obvious best practices) that could be tightened to save tokens.

Suggestions:

Add more specific concrete actions to the capability portion, e.g., 'generate Terraform configuration blocks, update state files, reconcile drift' to improve specificity.
Remove the 'Prerequisites > Discover Available List Resources' subsection since it duplicates the 'Check Provider Support First' section above it, or consolidate them into one section.
Remove or condense the 'Supported List Resources' section which contains no actual content beyond telling the user to run the discovery script (already covered twice).

terraform/code-generation/skills/terraform-tidy-before-import — 92% (PASSED)

  Description: 92%
    \(.key): \(.value.score)/3 - \(.value.reasoning)
    \(.key): \(.value.score)/3 - \(.value.reasoning)
    \(.key): \(.value.score)/3 - \(.value.reasoning)
    \(.key): \(.value.score)/3 - \(.value.reasoning)

    Assessment: This is a strong skill description that clearly defines a specific niche (Terraform import preparation) with concrete actions and explicit trigger conditions. The 'Use this before...' clause effectively communicates when the skill should be selected. The main weakness is that trigger term coverage could be broader to capture more natural user phrasings.

  Content: 92%
    \(.key): \(.value.score)/3 - \(.value.reasoning)
    \(.key): \(.value.score)/3 - \(.value.reasoning)
    \(.key): \(.value.score)/3 - \(.value.reasoning)
    \(.key): \(.value.score)/3 - \(.value.reasoning)

    Assessment: This is a well-structured, actionable skill that clearly guides Claude through a complex multi-step Terraform code tidying process. Its strengths are the explicit validation checkpoints, concrete before/after examples, and appropriate use of progressive disclosure. Minor verbosity in the preamble paragraphs about preserving built-in arguments could be tightened, but the domain-specific guidance is valuable and well-organized.

Suggestions:

Add common user-facing variations like 'terraform import', 'tf import', 'HCL cleanup', or 'infrastructure as code' to improve trigger term coverage for how users naturally phrase requests.

Checks: frontmatter validity, required fields, body structure, examples, line count.
Review score is informational — not used for pass/fail gating.

Document that terraform-tidy-before-import removes only computed attributes that are not optional, and preserves computed+optional attributes unless they are explicitly set to null. Assisted-by: Copilot <[email protected]> Co-authored-by: Copilot <[email protected]>

ansgarm · 2026-04-28T10:58:58Z

+  value            = null # sensitive
+  value_wo         = null # sensitive


curious: is the # sensitive generated by Terraform?

It is not. It was likely generated by an agent/model that assisted in writing this. Maybe it's better to remove it.

ansgarm · 2026-04-28T11:02:55Z

+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Tidy the generated Terraform in aws_thorough_before_cleanup.tf so it is ready for import and safe to commit. Use the default thoroughness level, keep valid import blocks intact, preserve Terraform language meta-arguments and nested language blocks, and organize the finished configuration into appropriate Terraform files before you wrap up. Keep terraform.tf in any terraform working directories for base provider configuration. Make a best effort: if the final file does not validate or does not meet all criteria, the computer should still present it as output for evaluation.",


How much instruction normally goes into the prompt vs into the skill?
How does it perform if this was just Tidy the generated Terraform config in aws_thorough_before_cleanup.tf?

Right on, super helpful feedback. I think this prompt needs to be lighter. Agent fatigue. Time to edit.

ansgarm · 2026-04-28T11:25:18Z

I can't seem to find a schema for this filetype?
I looked at the docs of tessl, which is used in a Github Action of this repo, and I can only find different files: https://docs.tessl.io/evaluate/evaluating-your-codebase#file-formats

How to run this eval?

Yes, spot-on observation! 😃 I took a speculative leap in this pull request.

For the eval, I chose the format described on agentskills.io. I ran it locally (WORKS ON MY MACHINE 😃) with the skill-creator skill from anthropics/skills.

It would be Really Useful to include some output, would it not? 🙃

ansgarm · 2026-04-28T12:43:26Z

+      "expected_output": "A cleaned AWS configuration as close to aws_thorough_after_cleanup.tf as possible. Expect absence of provider-defined computed attributes and top-level timeout blocks while preserving valid import blocks, lifecycle/meta-arguments, and connection timeouts.",
+      "files": [
+        "evals/files/aws_thorough_before_cleanup.tf",
+        "evals/files/aws_thorough_after_cleanup.tf",


As Anthropic denotes these files as input files, do we need to somehow assert that the agent (while using the skill) does not read this file? Else it might be relatively easy to get to this result 🥷

bbasata and others added 4 commits April 16, 2026 15:15

terraform-search-import: more tidying before import

762046a

terraform-tidy-for-import: extract from terraform-search-import

ac3aebd

validate first

dbdc026

Merge branch 'main' into mitosis

79b5f30

bbasata and others added 2 commits April 17, 2026 17:29

make it right

5226a51

bbasata mentioned this pull request Apr 18, 2026

terraform-search-import: more tidying before import #65

Closed

bbasata added 5 commits April 21, 2026 15:01

terraform-tidy-before-import: first pass at evals

63f925c

Revise eval expectations

ab8ec92

tidy

def59e5

refactor skill

3f3d77a

refine description

0a46e86

bbasata changed the title ~~terraform-tidy-for-import: extract from terraform-search-import~~ terraform-tidy-before-import: extract from terraform-search-import Apr 22, 2026

bbasata added 3 commits April 21, 2026 20:54

tidy

20f9441

tidy

7d0004d

tidy

3fa17b2

bbasata marked this pull request as ready for review April 22, 2026 01:01

bbasata requested a review from a team as a code owner April 22, 2026 01:01

ansgarm reviewed Apr 28, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

`terraform-tidy-before-import`: extract from `terraform-search-import`#66

`terraform-tidy-before-import`: extract from `terraform-search-import`#66
bbasata wants to merge 14 commits intomainfrom
mitosis

bbasata commented Apr 17, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Apr 17, 2026 •

edited

Loading

Uh oh!

ansgarm Apr 28, 2026

Uh oh!

bbasata Apr 28, 2026

Uh oh!

ansgarm Apr 28, 2026

Uh oh!

bbasata Apr 28, 2026

Uh oh!

ansgarm Apr 28, 2026

Uh oh!

bbasata Apr 28, 2026 •

edited

Loading

Uh oh!

ansgarm Apr 28, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

bbasata commented Apr 17, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions Bot commented Apr 17, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Tessl Skill Review Results

Detailed Review

Uh oh!

ansgarm Apr 28, 2026

Choose a reason for hiding this comment

Uh oh!

bbasata Apr 28, 2026

Choose a reason for hiding this comment

Uh oh!

ansgarm Apr 28, 2026

Choose a reason for hiding this comment

Uh oh!

bbasata Apr 28, 2026

Choose a reason for hiding this comment

Uh oh!

ansgarm Apr 28, 2026

Choose a reason for hiding this comment

Uh oh!

bbasata Apr 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

ansgarm Apr 28, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

bbasata commented Apr 17, 2026 •

edited

Loading

github-actions Bot commented Apr 17, 2026 •

edited

Loading

bbasata Apr 28, 2026 •

edited

Loading