aws-iam-best-practices

IAM policy review, hardening, and least privilege implementation

Quality

63%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-aws-iam-best-practices/SKILL.md

Quality

Content

61%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.

Strong actionability with executable examples, but the skill is monolithic and its destructive/batch operations lack validation checkpoints, capping workflow_clarity at 3. Splitting templates and scripts into bundle files with clear navigation would meaningfully improve the score.

Suggestions

Move the Python hardening script and policy JSON templates into scripts/ and references/ files, linking to them from a concise overview section.

Add explicit validate-before-act checkpoints for destructive ops (e.g. 'simulate the policy before deactivating keys; only delete after confirming no breakage').

Trim redundant sections (the bash and Python variants cover overlapping MFA/key-rotation checks) to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable snippets, but it inlines substantial material (four policy JSON templates, a full Python script, multiple bash loops) that pads the body and could be trimmed or split out.	3 / 5
Actionability	Provides copy-paste-ready bash and Python commands plus concrete JSON policy templates covering the common IAM hardening cases.	5 / 5
Workflow Clarity	Checks are grouped by category but lack a sequenced workflow with validation checkpoints; destructive/batch ops like deactivating then deleting access keys have no explicit validate-first feedback loop, capping this at 3 per the rubric.	3 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent); the skill is a monolithic single file with templates and scripts inlined rather than split into clearly signaled one-level-deep references.	2 / 5
	Total	13 / 20 Passed

Description

66%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.

The description is specific and on-niche but omits any 'Use when...' trigger guidance, which the rubric caps at 3 for completeness. Adding an explicit when-clause with natural trigger phrases would lift the weakest dimension.

Suggestions

Append a 'Use when...' clause naming concrete triggers, e.g. 'Use when reviewing IAM policies, auditing permissions, or hardening AWS access control'.

Add user-natural synonyms/variants such as 'audit IAM', 'over-permissive roles', or 'MFA enforcement' to broaden trigger coverage.

Tighten specificity by listing one or two concrete outputs (e.g. 'generate a hardening report', 'replace wildcard permissions').

Dimension	Reasoning	Score
Specificity	Names the domain (IAM policy) and several concrete actions ('review', 'hardening', 'least privilege implementation'), though each action is high-level rather than enumerating specific operations.	4 / 5
Completeness	Has a clear 'what' but no 'when'/'Use when...' clause; per the judging guidelines, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('IAM policy review', 'hardening', 'least privilege') but omits common synonyms and concrete trigger phrases like 'audit permissions' or 'find over-permissive roles'.	4 / 5
Distinctiveness Conflict Risk	The AWS IAM niche is fairly distinct with low conflict risk, though it could overlap with a generic 'AWS security' or 'cloud access-control' skill.	4 / 5
	Total	15 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: boisenoise/skills-collections
Path: skills/antigravity-aws-iam-best-practices/SKILL.md
Commit: 19c310e

Reviewed: about 18 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.