CtrlK
BlogDocsLog inGet started
Tessl Logo

drift-detector

Detect infrastructure drift between Terraform state and actual cloud resources. Identifies unmanaged resources, manual changes, and configuration drift. Use when: - User asks to check for infrastructure drift - User wants to find unmanaged cloud resources - User mentions "drift detection" or "Terraform drift" - User asks to compare cloud state to IaC - User wants to audit infrastructure changes

68

Quality

82%

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

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, well-sequenced body held back by progressive-disclosure defects (broken and orphaned file references plus inline duplication of the reference file) and missing validation feedback loops around destructive remediation steps.

Suggestions

Fix cross-file navigation: create or remove the referenced SERVICES.md and EXAMPLES.md, and link the existing references/drift-remediation.md from Phase 4 instead of duplicating its import/revert content inline.

Add an explicit validation feedback loop to Phase 4 — e.g. after each destructive step, re-run 'snyk iac describe --json' and confirm the finding is gone before proceeding — to lift workflow clarity past the destructive-operations cap.

Remove the hardcoded 'Scan Date: 2024-01-15' from the example report template and de-duplicate remediation detail against references/drift-remediation.md to tighten the body.

DimensionReasoningScore

Conciseness

The body is action-oriented without explaining concepts Claude already knows, but Phase 4 (Remediation) duplicates import/revert patterns that also live in references/drift-remediation.md, and the report template hardcodes a stale 'Scan Date: 2024-01-15' — mostly efficient but could be tightened, so it sits at 2 rather than the lean 3.

2 / 3

Actionability

Dense copy-paste-ready commands throughout — 'snyk iac describe --from=tfstate://terraform.tfstate', 'aws sts get-caller-identity', 'terraform import aws_s3_bucket.manual_bucket prod-logs-manual' — matching the 'fully executable code/commands; copy-paste ready' anchor rather than the incomplete/pseudocode anchor at 2.

3 / 3

Workflow Clarity

Five phases are clearly sequenced, but Phase 4 performs destructive operations ('aws s3 rb s3://unauthorized-bucket --force', 'aws ec2 terminate-instances', 'terraform apply') with no explicit validation checkpoint or validate-fix-retry feedback loop in the body — only a vague 'After verification' — so per the rubric's destructive-operations rule workflow clarity is capped at 2 rather than reaching 3.

2 / 3

Progressive Disclosure

The body has clear section structure, but it references 'SERVICES.md' and 'EXAMPLES.md' that do not exist in the bundle, while the actual bundle file 'references/drift-remediation.md' is never referenced from the body, and remediation detail that belongs in that reference is duplicated inline in Phase 4 — 'references present but not clearly signaled; content that should be separate is inline' fits 2 better than the monolithic/deeply-nested 1 anchor.

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 description: concrete capabilities, natural trigger terms, explicit use-when guidance, and a distinct niche. No over-claims or padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Detect infrastructure drift', 'Identifies unmanaged resources, manual changes, and configuration drift' — in third person, matching the 'lists multiple specific concrete actions' anchor; no vague fluff to drop it to 2.

3 / 3

Completeness

Explicitly answers both 'what' (detect/identify drift between Terraform state and cloud) and 'when' (a literal 'Use when:' list of triggers), satisfying the 'both what AND when with explicit triggers' anchor; not capped at 2 since the Use-when clause is present.

3 / 3

Trigger Term Quality

Natural phrases a user would say are well covered — 'check for infrastructure drift', 'drift detection', 'Terraform drift', 'audit infrastructure changes' — matching the 'good coverage of natural terms' anchor rather than the partial-coverage anchor at 2.

3 / 3

Distinctiveness Conflict Risk

Clear niche (Terraform-vs-cloud drift via Snyk) with distinct, specific triggers unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor; not generic enough to be a 2.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
snyk/studio-recipes
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.