infrastructure-maintainer
Expert infrastructure specialist focused on system reliability, performance optimization, and technical operations management. Maintains robust, scalable infrastructure supporting business operations with security, performance, and cost efficiency.
24
7%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./support-infrastructure-maintainer/skills/SKILL.mdQuality
Discovery
0%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 description reads like a job title or resume summary rather than a functional skill description. It lacks concrete actions, natural trigger terms, explicit usage guidance, and any distinguishing specificity. It would be nearly impossible for Claude to reliably select this skill from a pool of even a few related skills.
Suggestions
Replace abstract language with specific concrete actions, e.g., 'Configures servers, sets up monitoring and alerting, manages load balancers, troubleshoots deployment failures, optimizes database queries.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about server setup, deployment issues, infrastructure provisioning, CI/CD pipelines, Docker, Kubernetes, or cloud resource management.'
Narrow the scope to a distinct niche (e.g., Kubernetes management, AWS infrastructure, or monitoring/observability) to reduce conflict risk with other infrastructure-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'system reliability', 'performance optimization', and 'technical operations management' without listing any concrete actions. There are no specific tasks such as 'configure load balancers', 'set up monitoring alerts', or 'manage Kubernetes clusters'. | 1 / 3 |
Completeness | The description vaguely addresses 'what' with abstract concepts but provides no explicit 'when' guidance. There is no 'Use when...' clause or equivalent trigger guidance, and even the 'what' is too abstract to be useful. | 1 / 3 |
Trigger Term Quality | The terms used are broad buzzwords ('infrastructure', 'reliability', 'scalable', 'security', 'cost efficiency') that are unlikely to match natural user queries. Users would more likely say things like 'set up a server', 'fix deployment', 'configure DNS', or 'optimize database performance'. | 1 / 3 |
Distinctiveness Conflict Risk | The description is extremely generic and could overlap with virtually any DevOps, cloud, security, performance, or systems administration skill. Terms like 'infrastructure', 'security', and 'performance' are so broad they would conflict with many other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a persona/personality definition masquerading as infrastructure guidance. It is extremely verbose, mixing generic motivational content (identity, communication style, success metrics, learning patterns) with some concrete but generic infrastructure code examples. The actual workflow guidance is vague and lacks the validation checkpoints and rollback procedures that infrastructure operations critically require.
Suggestions
Remove all persona/personality sections (identity, communication style, learning & memory, success metrics) - these waste tokens and don't provide actionable infrastructure guidance.
Extract the Prometheus config, Terraform config, backup script, and report template into separate referenced files, keeping SKILL.md as a concise overview with clear navigation links.
Replace the vague 4-step workflow with specific, sequenced procedures that include explicit validation checkpoints (e.g., 'terraform plan' before 'terraform apply', health check verification after deployment).
Focus the skill on specific infrastructure tasks Claude wouldn't already know (e.g., organization-specific configurations, custom tooling, or non-obvious patterns) rather than generic cloud architecture concepts.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 400+ lines. Massive amounts of content Claude already knows: personality descriptions, communication style examples, success metrics, 'learning & memory' sections, and extensive report templates that are generic boilerplate. The Terraform and Prometheus configs, while concrete, are generic examples not specific to any particular infrastructure task. The emoji-laden section headers and motivational framing waste tokens. | 1 / 3 |
Actionability | Contains some executable code (Prometheus YAML, Terraform HCL, bash backup script) which is concrete and copy-paste ready. However, much of the skill is abstract guidance ('assess current infrastructure health', 'analyze resource utilization') rather than specific instructions. The workflow steps in particular are vague comments rather than executable commands. | 2 / 3 |
Workflow Clarity | The 4-step workflow process is extremely vague with steps like 'Assess current infrastructure health and performance' as bash comments with no actual commands. There are no validation checkpoints, no rollback procedures despite mentioning them, and no feedback loops for error recovery. The backup script has good error handling internally, but the overall infrastructure management workflow lacks clear sequencing and validation gates. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with everything inline - the Prometheus config, Terraform config, backup script, report template, communication style, success metrics, and advanced capabilities are all dumped into a single file. No references to external files for detailed configs or templates. The final line vaguely references 'core training' which is not a real file reference. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (616 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- OpenRoster-ai/awesome-openroster
- Commit
09aef5d
- 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.