pulumi-automation-api
Load this skill when a user asks how to run Pulumi programmatically, embed Pulumi in an application, orchestrate multiple stacks in code, build a self-service infrastructure portal, replace pulumi CLI shell scripts with code, or use the Pulumi Automation API (LocalWorkspace, createOrSelectStack, inline programs). Also load for questions about multi-stack sequencing, parallel deployments, or passing outputs between stacks via code.
85
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that clearly defines its niche around the Pulumi Automation API and programmatic infrastructure management. It provides rich trigger terms covering both high-level use cases and specific API constructs, making it easy for Claude to select appropriately. The only minor note is that it lacks a brief 'what it does' summary before the trigger guidance — it jumps straight into 'when to load' — but the trigger scenarios themselves implicitly convey the capabilities well.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: run Pulumi programmatically, embed Pulumi in an application, orchestrate multiple stacks, build a self-service infrastructure portal, replace CLI shell scripts with code, and names specific API constructs (LocalWorkspace, createOrSelectStack, inline programs). | 3 / 3 |
Completeness | The description clearly answers both 'what' (Pulumi Automation API usage, programmatic Pulumi, multi-stack orchestration, etc.) and 'when' with explicit trigger guidance ('Load this skill when a user asks how to...' followed by detailed trigger scenarios). The 'Also load for...' clause adds additional trigger conditions. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Pulumi Automation API', 'LocalWorkspace', 'createOrSelectStack', 'inline programs', 'multi-stack', 'parallel deployments', 'passing outputs between stacks', 'self-service infrastructure portal', 'replace pulumi CLI shell scripts'. These are highly natural phrases a user working with Pulumi automation would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — focuses specifically on the Pulumi Automation API and programmatic infrastructure orchestration, which is a clear niche. The mention of specific API constructs (LocalWorkspace, createOrSelectStack, inline programs) and use cases (multi-stack sequencing, parallel deployments) makes it very unlikely to conflict with general Pulumi skills or other IaC skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with excellent executable code examples covering the key Automation API patterns. Its main weaknesses are verbosity (explanatory prose that Claude doesn't need, like describing what Automation API is and listing obvious use cases) and missing validation checkpoints in the multi-stack workflow, which is a destructive/complex operation that warrants explicit error recovery loops between steps.
Suggestions
Remove or drastically shorten the 'What is Automation API' and 'When to Use / When NOT to Use' sections — Claude can infer these from context; focus on the how, not the why.
Integrate error handling and validation directly into the multi-stack orchestration workflow (e.g., check result.summary.result after each stack.up() before proceeding to the next stack, with a rollback or abort path).
Move the 'Architecture Choices' and 'Best Practices' sections to a separate reference file and link to them, keeping SKILL.md focused on the quick-start and common patterns.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanations Claude would already know (e.g., 'What is Automation API' section explaining what programmatic access means, the 'When NOT to Use' section with obvious points, and verbose descriptions of use cases like 'Applications that provision their own infrastructure'). The content could be tightened by ~30% while preserving all actionable information. | 2 / 3 |
Actionability | The skill provides fully executable TypeScript code examples throughout — createOrSelectStack, multi-stack orchestration, configuration setting, output reading, error handling, and parallel deployments are all copy-paste ready with real imports and proper async/await patterns. | 3 / 3 |
Workflow Clarity | The multi-stack orchestration pattern shows clear sequencing (deploy in order, destroy in reverse), but lacks explicit validation checkpoints between stack deployments. For multi-stack operations where a failed intermediate stack could leave infrastructure in a bad state, there should be validation/rollback steps between deployments. The error handling section exists but is separate from the workflow rather than integrated into it. | 2 / 3 |
Progressive Disclosure | The skill references related skills and external documentation, but the body itself is quite long (~200+ lines) with substantial inline content that could be split. The architecture choices and best practices sections could be separate files, with the main skill focusing on quick-start patterns and a reference table. The quick reference table at the end is helpful for navigation. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- pulumi/agent-skills
- Commit
b6214ca
- 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.