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".
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
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 vague—it says 'deploy Apollo.io integrations' but doesn't enumerate specific concrete actions involved in the deployment process. The explicit trigger phrases and narrow domain focus are strengths.
Suggestions
Add more specific concrete actions to the description, e.g., 'Configures environment variables, sets up CI/CD pipelines, manages API key rotation, and validates production readiness for Apollo.io integrations.'
| 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
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, highly actionable skill with complete executable configurations for three deployment platforms. Its main weaknesses are structural: the pre-deploy validation should precede deployment steps, the three platform configs bloat the file and would benefit from being split into separate references, and there's no explicit deploy-then-verify feedback loop. The content is mostly efficient but could be leaner by splitting platform-specific details.
Suggestions
Move Step 5 (Pre-Deploy Validation) to Step 2, before any deployment, and add an explicit post-deploy verification step (e.g., 'curl /health and confirm 200 before considering deploy complete').
Split each deployment target (GCP, Vercel, K8s) into separate referenced files (e.g., DEPLOY_GCP.md, DEPLOY_VERCEL.md, DEPLOY_K8S.md) and keep only a brief summary with links in the main skill.
Add an explicit feedback loop: 'Run pre-deploy check → fix failures → re-run → deploy → verify health endpoint → rollback if unhealthy'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill provides substantial executable content but is quite long (~150 lines of config/code). Some sections could be tightened — e.g., the three deployment targets (Vercel, GCP, K8s) are all fully inlined rather than referenced separately, and the health check code is verbose for what Claude could generate from a brief spec. However, there's minimal explanatory fluff. | 2 / 3 |
Actionability | Highly actionable with complete, executable TypeScript code, Dockerfiles, bash commands, Kubernetes YAML, and Vercel config. Every deployment target has copy-paste-ready configurations with specific CLI commands and secret management steps. | 3 / 3 |
Workflow Clarity | Steps are numbered and sequenced, and there's a pre-deploy validation script (Step 5). However, the validation step comes AFTER the deployment steps rather than before, which is counterintuitive. There's no explicit feedback loop like 'run pre-deploy check → fix issues → re-check → then deploy → verify health endpoint'. The error handling table helps but doesn't constitute an integrated validation workflow. | 2 / 3 |
Progressive Disclosure | The skill has clear sections and a summary output list, plus external resource links and a pointer to the next skill. However, the three full deployment configurations (GCP, Vercel, K8s) are all inlined, making this a long monolithic file. These would be better as separate referenced files with just a brief overview in the main skill. | 2 / 3 |
Total | 9 / 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
3e83543
- 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.