aws-ami-builder

Build Amazon Machine Images (AMIs) with Packer using the amazon-ebs builder. Use when creating custom AMIs for EC2 instances.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%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 tight, example-driven reference whose code is immediately executable and covers the standard cases (single-region, multi-region, auth, troubleshooting). The main improvements are removing the duplicated Ubuntu filter block and duplicated reference link, and connecting the 'Common Issues' hints into an explicit build-fail feedback loop.

Suggestions

Delete the verbatim repeat of the Ubuntu source_ami_filter block from 'Common Source AMI Filters' (or from the basic template) and keep the EBS builder link in only one place, since the duplication is pure token cost.

Link the 'Common Issues' entries back into the build workflow (e.g., 'if packer build times out on SSH, check security group port 22 and subnet internet access') to make the validate-and-recover feedback loop explicit.

Centralize the version-sensitive pins (Packer plugin '~> 1.3', Ubuntu 22.04 jammy, Amazon Linux 2023) — for example as variables or a single noted block — so stale dated versions are easy to spot and update.

Dimension	Reasoning	Score
Conciseness	The body is dominated by executable HCL and shell with almost no explanation of concepts Claude already knows (no 'what is an AMI/Packer' padding), earning at least a 4. It misses 5 because the Ubuntu source_ami_filter block is repeated verbatim in 'Basic AMI Template' and 'Common Source AMI Filters', and the EBS builder link appears twice (top and 'References').	4 / 5
Actionability	Guidance is fully copy-paste ready: a complete template including the packer required_plugins block, per-distro source_ami_filter examples with owner IDs, multi-region ami_regions usage, credential setup, and the concrete command sequence 'packer init .', 'packer validate .', 'packer build -var "region=us-east-1" .'. These cover the common cases exactly as the anchor-5 example does.	5 / 5
Workflow Clarity	A clear ordered sequence exists — 'packer init .' → 'packer validate .' → 'packer build .' — with an explicit validation checkpoint, and 'Common Issues' covers SSH timeout, duplicate AMI names, and volume size. It is not 5 because the troubleshooting section is not wired back into the workflow as an explicit feedback loop (no 'if validate/build fails, check X and retry' step), leaving recovery implicit.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and all content is inline, but the ~165-line body is well sectioned (template, filters, multi-region, auth, commands, issues) with the only outward links being official docs at one level. It is not 5 because the duplicated filter/reference material should be consolidated, and a 'Common Source AMI Filters' catalog of this size is the natural candidate for a separate reference file.	4 / 5
	Total	17 / 20 Passed

Description

82%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 concise, third-person description with an explicit 'Use when' trigger clause and strong niche focus. Its main limitation is that it advertises only one capability (building), underrepresenting what the body actually covers.

Suggestions

Add one or two more concrete capabilities to the description (e.g., multi-region AMI copying, template validation, troubleshooting failed builds) so specificity lists several actions rather than the single 'build' verb.

Include natural synonyms users might say such as 'golden image', 'base image', or 'bake an image' to broaden trigger-term coverage toward comprehensive.

Dimension	Reasoning	Score
Specificity	"Build Amazon Machine Images (AMIs) with Packer using the amazon-ebs builder" names the domain plus the single concrete action of building AMIs, but no other capabilities (multi-region copying, validation, troubleshooting) appear in the description. It is not a 4 because only one action is listed rather than several; it exceeds 2 because 'build AMIs with Packer via the amazon-ebs builder' is concrete, not generic.	3 / 5
Completeness	Both halves are explicit: the what is "Build Amazon Machine Images (AMIs) with Packer using the amazon-ebs builder" and the when is the concrete trigger clause "Use when creating custom AMIs for EC2 instances". This matches the anchor-5 pattern of clearly answering both what and when with concrete trigger phrases, so 4 (a merely adequate 'when') underrates it.	5 / 5
Trigger Term Quality	Good natural keyword coverage — "AMIs", "Packer", "amazon-ebs", "custom AMIs", "EC2 instances" — phrases a user needing this skill would actually say. It falls short of 5 because common synonyms and extensions (golden image, base image, bake an image, .pkr.hcl) are absent; it beats 3 because more than the bare domain term is covered.	4 / 5
Distinctiveness Conflict Risk	The Packer/AMI/EC2 niche is narrow and the triggers ("Packer", "amazon-ebs", "custom AMIs") would not plausibly fire a different skill, matching the clear-niche anchor. There is no overlap with generic infrastructure or Docker-image skills worth a 4.	5 / 5
	Total	17 / 20 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: hashicorp/agent-skills
Path: plugins/packer/skills/aws-ami-builder/SKILL.md
Commit: 516354c

Reviewed: 1 day 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.