CtrlK
BlogDocsLog inGet started
Tessl Logo

pulumi-best-practices

Load when the user is writing, reviewing, or debugging Pulumi TypeScript/Python programs; asks about Output<T> or apply() usage; wants to create ComponentResource classes; needs to refactor resources without destroying them (aliases); is setting up secrets or config; or is configuring a pulumi preview/up CI workflow. Also load for questions about resource dependency order, parent/child resource relationships, or pulumi.interpolate.

72

Quality

91%

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

82%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.

A strong, actionable reference: concrete Wrong/Right code, detection signals, and a validation checklist grounded in preview-before-deploy as the destructive-operation checkpoint. It is slightly verbose and monolithic, with room to split detail into reference files.

Suggestions

Tighten the 'Why' paragraphs and enumerated benefit lists (e.g. 'What parent: this provides', 'What qualifies as a secret') to one line each — the Wrong/Right examples already carry the lesson.

Move the full GitHub Actions yaml and the alias edge-case examples into a references/ file, keeping inline only the minimal snippet and a clearly signaled link, to improve progressive disclosure.

Add an explicit top-of-file workflow header (orient → detect signals → apply fix → preview to validate) so the seven practices read as one sequenced review process rather than a flat list.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Pulumi competence rather than explaining generic concepts, but at ~500 lines some 'Why' rationales and enumerated sub-lists (e.g. 'What qualifies as a secret', 'What parent: this provides') could be trimmed without losing actionable value.

4 / 5

Actionability

Every practice provides copy-paste-ready Wrong/Right code pairs plus concrete commands ('pulumi config set --secret', 'pulumi preview', 'esc env set … --secret') and a runnable GitHub Actions yaml, covering the common cases.

5 / 5

Workflow Clarity

Sequences are clear with checkpoints — the alias lifecycle (add → pulumi up on all stacks → remove) and the preview→review→up flow with an explicit validation checklist — but the skill is a collection of practices rather than one coherent multi-step workflow, leaving minor sequencing gaps.

4 / 5

Progressive Disclosure

Well-organized into seven numbered practices, a Quick Reference table, a Validation Checklist, and a Related Skills section that clearly signals one-level-deep routing ('Use skill pulumi-component'); no bundle files exist so content is self-contained, though some detail (full CI yaml, alias edge cases) could be offloaded to reference files.

4 / 5

Total

17

/

20

Passed

Description

100%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.

The description is exemplary: third-person imperative voice, explicit 'Load when' trigger clauses, and a comprehensive list of concrete Pulumi-specific actions and natural trigger terms. It cleanly answers both what the skill does and when to invoke it with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'writing, reviewing, or debugging Pulumi TypeScript/Python programs', 'create ComponentResource classes', 'refactor resources without destroying them (aliases)', 'setting up secrets or config', 'configuring a pulumi preview/up CI workflow' — with comprehensive coverage of the skill's surface.

5 / 5

Completeness

Explicitly answers both what (the enumerated Pulumi tasks) and when via two explicit trigger clauses — 'Load when the user is…' and 'Also load for questions about…' — with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers the natural terms a Pulumi user would actually say — 'Output<T>', 'apply()', 'ComponentResource', 'aliases', 'secrets or config', 'pulumi preview/up', 'parent/child resource relationships', 'pulumi.interpolate' — including API-level synonyms users mention.

5 / 5

Distinctiveness Conflict Risk

The niche is clearly Pulumi IaC with distinct, product-specific triggers (Output<T>, apply(), ComponentResource, aliases, pulumi.interpolate), giving minimal overlap risk with non-Pulumi skills.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (502 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

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.