apollo-deploy-integration
Deploy Apollo.io integrations to production. Use when deploying Apollo integrations, configuring production environments, or setting up deployment pipelines. Trigger with phrases like "deploy apollo", "apollo production deploy", "apollo deployment pipeline", "apollo to production".
77
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/apollo-pack/skills/apollo-deploy-integration/SKILL.mdQuality
Discovery
89%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 reasonably well-structured skill description with strong trigger terms and clear 'when' guidance. Its main weakness is that the 'what' portion is somewhat generic—it says 'deploy' and 'configure' but doesn't enumerate specific concrete actions or outputs (e.g., CI/CD configuration, environment variable setup, health checks). The explicit trigger phrases and Apollo.io specificity make it highly distinctive.
Suggestions
Add more specific concrete actions to the description, e.g., 'Configures CI/CD pipelines, sets environment variables, runs health checks, and manages Apollo.io API key rotation for production deployments.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Apollo.io integrations deployment) and mentions some actions like 'configuring production environments' and 'setting up deployment pipelines', but lacks concrete specific actions (e.g., what deployment steps, what configuration details, what pipeline tools). | 2 / 3 |
Completeness | Clearly answers both 'what' (deploy Apollo.io integrations to production) and 'when' (explicit 'Use when...' clause with triggers and a 'Trigger with phrases like...' section providing concrete examples). | 3 / 3 |
Trigger Term Quality | Includes explicit trigger phrases like 'deploy apollo', 'apollo production deploy', 'apollo deployment pipeline', 'apollo to production' which are natural terms a user would say. Good coverage of variations around the deployment theme. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche combining Apollo.io with production deployment. The combination of 'Apollo' and 'deploy/production' makes it highly unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, copy-paste-ready deployment configurations for three platforms with good error handling documentation. However, it suffers from poor progressive disclosure — cramming three alternative deployment paths into one file creates unnecessary length. The workflow sequencing is misleading, presenting alternatives as sequential steps and placing pre-deploy validation after the deploy steps.
Suggestions
Split platform-specific deployments (GCP, Vercel, K8s) into separate referenced files and keep SKILL.md as an overview with the health check pattern and pre-deploy validation only.
Reorder steps so pre-deploy validation comes before any deployment, and clarify that GCP/Vercel/K8s are alternatives (not sequential steps) — use a 'Choose your platform' section instead of numbered steps.
Add an explicit post-deploy verification step: 'After deploy, curl /health and confirm 200. If 503, check error table below. Only consider deployment complete when health check passes.'
Trim the health check and pre-deploy code to essential patterns — Claude can generate Express routers and axios calls from brief specifications without full boilerplate.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes three full deployment platform configurations (GCP, Vercel, K8s) inline, making it quite long. The health check code and pre-deploy script are largely boilerplate that Claude could generate from brief instructions. The overview section is concise, but the body could be significantly tightened by summarizing patterns and letting Claude fill in platform-specific details. | 2 / 3 |
Actionability | All code examples are fully executable and copy-paste ready: complete TypeScript files, working Dockerfiles, valid YAML manifests, and concrete CLI commands with real flags. The pre-deploy validation script is a complete runnable program. Every step has specific, concrete guidance. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered but the sequencing is odd — Steps 2-4 are alternative deployment targets (not sequential), yet they're numbered as if sequential. The pre-deploy validation (Step 5) logically should come before deployment steps. There's no explicit 'validate after deploy' step or feedback loop (e.g., 'hit /health after deploy, if 503 then...'). The error handling table partially compensates but lacks a structured recovery workflow. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content with ~150+ lines of inline code across three deployment platforms. The three platform-specific deployments should each be in separate referenced files (e.g., DEPLOY-GCP.md, DEPLOY-VERCEL.md, DEPLOY-K8S.md). No bundle files exist to offload this content, and the skill doesn't reference any supporting files except a vague 'Next Steps' pointer. | 1 / 3 |
Total | 8 / 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 |
|---|---|---|
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 | 9 / 11 Passed | |
- Commit
3a2d27d
- 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.