pulumi-best-practices
Best practices for writing reliable Pulumi programs. Covers Output handling, resource dependencies, component structure, secrets management, safe refactoring with aliases, and deployment workflows.
Install with Tessl CLI
npx tessl i github:pulumi/agent-skills --skill pulumi-best-practices69
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
32%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 identifies Pulumi as the target domain and lists relevant topic areas, providing moderate specificity. However, it lacks explicit trigger guidance ('Use when...') which is critical for skill selection, and the topics are framed as coverage areas rather than concrete actions Claude would perform. The description reads more like a table of contents than actionable selection criteria.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios like 'Use when writing Pulumi code, debugging infrastructure deployments, or when the user mentions Pulumi, TypeScript/Python infrastructure, or cloud resource provisioning.'
Reframe topic areas as concrete actions: 'Writes reliable Pulumi programs, handles async Outputs correctly, structures reusable components, manages secrets safely, and guides safe resource refactoring.'
Include common user trigger terms like 'infrastructure as code', 'IaC', 'Pulumi stack', 'cloud provisioning', or specific cloud providers (AWS, Azure, GCP) if applicable.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Pulumi) and lists several specific topics (Output handling, resource dependencies, component structure, secrets management, aliases, deployment workflows), but these are topic areas rather than concrete actions Claude would perform. | 2 / 3 |
Completeness | Describes what the skill covers (best practices for Pulumi) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'Pulumi' as a key trigger term and technical concepts like 'Output handling', 'secrets management', 'aliases', but misses common user phrases like 'infrastructure as code', 'IaC', 'cloud resources', or 'Pulumi stack'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Pulumi' is a distinct technology that reduces conflict risk, but the broad 'best practices' framing and topics like 'secrets management' and 'deployment workflows' could overlap with general DevOps or other IaC skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill with excellent actionability through concrete code examples and clear wrong/right patterns. The workflow clarity is good with explicit validation steps and a useful checklist. Minor verbosity in explanatory sections (e.g., 'Why' blocks explaining concepts Claude knows) prevents a perfect conciseness score, but overall this skill effectively teaches Pulumi best practices.
Suggestions
Trim the 'Why' explanations to be more terse - Claude understands concepts like DAGs and dependency chains without detailed explanation
Consider removing the 'What qualifies as a secret' list since Claude already knows what constitutes sensitive data
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-organized but includes some unnecessary explanations that Claude would already know (e.g., explaining what a DAG is, what qualifies as a secret). The 'Why' sections add value but could be more terse in places. | 2 / 3 |
Actionability | Excellent executable code examples throughout with clear wrong/right patterns. Every practice includes copy-paste ready TypeScript code, specific CLI commands, and concrete detection signals for identifying problems. | 3 / 3 |
Workflow Clarity | Clear sequences with explicit validation steps, especially in Practice 7 (preview before deploy) and the CI/CD integration example. The validation checklist provides explicit checkpoints, and the alias lifecycle (add → deploy → remove) shows proper feedback loops. | 3 / 3 |
Progressive Disclosure | Well-structured with quick reference table, validation checklist, and clear pointers to related skills (pulumi-component, pulumi-automation-api, pulumi-esc) for deeper topics. External references are one level deep and clearly signaled. | 3 / 3 |
Total | 11 / 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 (501 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 | |
- 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.