CtrlK
BlogDocsLog inGet started
Tessl Logo

apollo-multi-env-setup

Configure Apollo.io multi-environment setup. Use when setting up development, staging, and production environments, or managing multiple Apollo configurations. Trigger with phrases like "apollo environments", "apollo staging", "apollo dev prod", "apollo multi-tenant", "apollo env config".

61

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/apollo-pack/skills/apollo-multi-env-setup/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%Weight 40%Scale 1-3

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

The body is highly actionable with complete, executable code, but it suffers from a monolithic structure and an orphaned, never-linked reference file. Workflow sequencing is present but lacks explicit validation feedback loops for risky deploy operations.

Suggestions

Link references/implementation-guide.md from the body (e.g., a "## Implementation guide" section with "See [implementation-guide.md](references/implementation-guide.md)") so the bundle file is discoverable and well-signaled.

Move the full per-environment config objects and k8s YAML into the reference file, keeping the body as an overview pointing to it, to reduce inline bulk and improve progressive disclosure.

Add an explicit validate-then-proceed checkpoint (e.g., run the verify script and only apply secrets/roll out when verification passes) for the k8s and deploy steps.

DimensionReasoningScore

Conciseness

The body avoids explaining what Apollo/Zod/Kubernetes are and is code-dense, but ~207 lines of full per-environment config objects, k8s YAML, and a verify script are largely inline material that lives in code files; much could be tightened or externalized, and it overlaps the orphaned implementation-guide.md.

2 / 3

Actionability

Fully executable TypeScript (Zod schema, per-env configs, client factory with feature-gate interceptors, verify script) and YAML with explicit file paths — copy-paste ready, not pseudocode.

3 / 3

Workflow Clarity

Five numbered steps are sequenced and Step 5 provides a verification script, but there is no explicit validate-then-proceed feedback loop and no validation gate before destructive/batch operations like k8s secret apply or per-environment deploys.

2 / 3

Progressive Disclosure

A bundle file references/implementation-guide.md exists but is never linked or signaled from the body (no "See implementation-guide.md"), and the body itself is monolithic with all config inline — the worst-case the rubric calls out of un-signaled references and inline content that should be separate.

1 / 3

Total

8

/

12

Passed

Description

90%Weight 40%Scale 1-3

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 clearly states both what the skill does and when to use it, with a strong set of Apollo-specific trigger phrases. It is slightly weak on enumerating concrete capabilities, listing the domain and a couple of actions rather than a full set of specifics.

Suggestions

Add one or two concrete capability specifics (e.g., isolated API keys, environment-specific rate limits, Kubernetes secret management) to lift the specificity score.

Consider whether "Trigger with phrases like" framing can be folded more naturally into the Use-when clause.

DimensionReasoningScore

Specificity

"Configure Apollo.io multi-environment setup" and "setting up development, staging, and production environments, or managing multiple Apollo configurations" name the domain and a couple of actions, but don't enumerate concrete specifics like isolated keys, rate limits, or secrets.

2 / 3

Completeness

Both "what" (Configure Apollo.io multi-environment setup) and "when" (Use when setting up development, staging, and production environments, or managing multiple Apollo configurations) are explicitly stated.

3 / 3

Trigger Term Quality

Five phrases — "apollo environments", "apollo staging", "apollo dev prod", "apollo multi-tenant", "apollo env config" — give good coverage of natural terms a user would say, including common variations.

3 / 3

Distinctiveness Conflict Risk

The Apollo-specific niche and distinct triggers like "apollo multi-tenant" make it unlikely to fire for the wrong skill.

3 / 3

Total

11

/

12

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-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.