detecting-infrastructure-drift
This skill enables Claude to detect infrastructure drift from a desired state. It uses the `drift-detect` command to identify discrepancies between the current infrastructure configuration and the intended configuration, as defined in infrastructure-as-code tools like Terraform. Use this skill when the user asks to check for infrastructure drift, identify configuration changes, or ensure that the current infrastructure matches the desired state. It is particularly useful in DevOps workflows for maintaining infrastructure consistency and preventing configuration errors. Trigger this skill when the user mentions "drift detection," "infrastructure changes," "configuration drift," or requests a "drift report."
75
48%
Does it follow best practices?
Impact
92%
1.02xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./backups/skills-migration-20251108-070147/plugins/devops/infrastructure-drift-detector/skills/infrastructure-drift-detector/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured skill description with explicit 'what' and 'when' clauses and strong, domain-specific trigger terms. Its main weakness is that the capability description could be more specific about the concrete actions performed beyond just 'detecting discrepancies.' The description is somewhat verbose and could be more concise while retaining the same information.
Suggestions
List more specific concrete actions beyond 'detect discrepancies' — e.g., 'compares Terraform state files, lists changed resources, generates drift reports with specific resource differences.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (infrastructure drift detection) and mentions the `drift-detect` command and Terraform, but the actual concrete actions are limited — it mostly describes 'detecting discrepancies' without listing multiple distinct operations (e.g., generating reports, comparing state files, listing changed resources). | 2 / 3 |
Completeness | Clearly answers both 'what' (detects infrastructure drift using drift-detect command, identifies discrepancies between current and intended configuration) and 'when' (explicit trigger clause with 'Use this skill when...' and specific trigger terms listed). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'drift detection,' 'infrastructure changes,' 'configuration drift,' 'drift report,' 'Terraform,' 'infrastructure drift,' and 'configuration changes.' These cover a good range of terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | The skill occupies a clear niche — infrastructure drift detection with specific tooling (drift-detect, Terraform). The trigger terms are highly specific to this domain and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is almost entirely descriptive rather than instructive. It repeatedly explains what drift detection is and when to use it, but never provides the actual command syntax, expected arguments, output format, or error handling guidance that Claude would need to execute the task. The content reads like marketing copy or a product description rather than an actionable skill definition.
Suggestions
Replace abstract descriptions with the actual `drift-detect` command syntax, including all required flags, arguments, and environment setup (e.g., `drift-detect --env production --config terraform.tfstate`).
Add a concrete example of expected output format so Claude knows how to parse and present results to the user.
Remove the 'When to Use This Skill', 'Best Practices', and 'Integration' sections entirely—these describe concepts Claude already knows and add no actionable value.
Add error handling guidance: what to do when the command fails, common error codes, and how to interpret ambiguous results.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive padding. Explains concepts Claude already knows (what drift detection is, what version control is, what Ansible/Puppet do). The 'When to Use This Skill' section repeats the description. 'How It Works' describes obvious steps. 'Best Practices' and 'Integration' sections provide generic DevOps advice that adds no actionable value. | 1 / 3 |
Actionability | No concrete commands, code, or executable guidance anywhere. 'Execute the drift-detect command' is mentioned repeatedly but never shown with actual syntax, flags, arguments, or expected output format. The examples describe what the skill will do in abstract terms rather than providing concrete instructions Claude can follow. | 1 / 3 |
Workflow Clarity | The workflow is entirely abstract ('execute the command, present a report') with no actual command syntax, no validation steps, no error handling, and no feedback loops. There's no guidance on what to do if drift is detected, how to interpret results, or how to handle failures. | 1 / 3 |
Progressive Disclosure | The content has clear section headers and some organizational structure, but it's a monolithic document with no references to external files. Content that could be split out (e.g., detailed command reference, output format documentation) is neither inline nor referenced—it simply doesn't exist. | 2 / 3 |
Total | 5 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Commit
c8a915c
- 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.