CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

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

68%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable content with comprehensive executable code examples and clear organization, weakened by redundant trigger sections and missing validation checkpoints in the destructive multi-stack workflows.

Suggestions

Consolidate the duplicate 'When to Use This Skill' and 'Good Use Cases' trigger lists into a single section to reduce redundancy and token cost.

Add explicit validation checkpoints in the multi-stack orchestration example (e.g., check each stack's up() result before proceeding to the next, and verify destroy succeeded) to lift workflow clarity above the destructive/batch cap of 3.

Integrate the error-handling pattern directly into the multi-stack deploy loop rather than presenting it as a separate standalone snippet.

DimensionReasoningScore

Conciseness

Mostly efficient code-first content, but it duplicates trigger guidance across two 'When to Use' sections (top list and 'Good Use Cases') and includes some explanatory prose that assumes less than Claude's competence, so it could be tightened.

3 / 5

Actionability

Provides multiple complete, copy-paste-ready TypeScript examples covering the common cases (createOrSelectStack, up/destroy, setConfig, outputs, error handling, parallel Promise.all) — fully executable guidance.

5 / 5

Workflow Clarity

The multi-stack deploy/destroy loops give a clear sequence (deploy in order, destroy in reverse) but lack validation checkpoints between stacks; the standalone error-handling block is not integrated, so this batch/destructive workflow is capped at 3 per the rubric.

3 / 5

Progressive Disclosure

Good structure with well-organized sections (When to Use, Architecture Choices, Common Patterns, Best Practices) and a Quick Reference table, plus a clearly signaled References list; minor gaps only since all material is inline with no bundle files to split into.

4 / 5

Total

15

/

20

Passed

Description

96%Weight 40%Scale 1-5

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, specific description with concrete actions, natural trigger terms, and explicit 'load when' guidance covering both what and when. The only minor weakness is potential overlap with the related pulumi-best-practices skill.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('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)') — comprehensive coverage of concrete capabilities, not vague language.

5 / 5

Completeness

Explicitly answers both 'what' (the enumerated programmatic Pulumi actions) and 'when' via the concrete 'Load this skill when a user asks how to...' trigger clause and the 'Also load for questions about...' extension.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ('run Pulumi programmatically', 'replace pulumi CLI shell scripts with code', 'parallel deployments', 'passing outputs between stacks') plus concrete API terms (LocalWorkspace, createOrSelectStack, inline programs), giving comprehensive keyword coverage.

5 / 5

Distinctiveness Conflict Risk

Targets a clear Pulumi Automation API niche with distinct triggers, but a closely related skill (pulumi-best-practices) exists, creating minor overlap risk rather than minimal conflict risk.

4 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
pulumi/agent-skills
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.