apollo-prod-checklist
Execute Apollo.io production deployment checklist. Use when preparing to deploy Apollo integrations to production, doing pre-launch verification, or auditing production readiness. Trigger with phrases like "apollo production checklist", "deploy apollo", "apollo go-live", "apollo production ready", "apollo launch checklist".
80
77%
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-prod-checklist/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 well-structured description with excellent trigger terms and clear 'what/when' guidance. Its main weakness is that the capabilities described are somewhat high-level — 'execute checklist' doesn't convey what specific checks or actions the skill performs. Adding 2-3 concrete checklist items would strengthen the specificity.
Suggestions
Add specific concrete actions the checklist covers, e.g., 'Verifies API authentication, validates webhook configurations, checks rate limit settings, confirms data sync mappings' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Apollo.io production deployment) and a general action ('execute checklist', 'pre-launch verification', 'auditing production readiness'), but doesn't list specific concrete actions like 'verify API keys, check rate limits, validate webhook endpoints'. The actions remain at a high level. | 2 / 3 |
Completeness | Clearly answers both 'what' (execute Apollo.io production deployment checklist) and 'when' (preparing to deploy, pre-launch verification, auditing production readiness) with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger phrases like 'apollo production checklist', 'deploy apollo', 'apollo go-live', 'apollo production ready', 'apollo launch checklist'. These are terms users would naturally say when needing this skill, with good variation coverage. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific niche combining Apollo.io with production deployment checklists. The 'apollo' qualifier plus 'production deployment' makes it very 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, actionable production checklist skill with executable TypeScript code covering key deployment concerns. Its main weaknesses are the repetitive inline code that could be more concise or extracted to a separate file, and the lack of an explicit fix-and-revalidate feedback loop in the workflow. The content is well-organized but would benefit from being leaner in the SKILL.md with the full script referenced externally.
Suggestions
Add an explicit feedback loop step: after listing failures, instruct to fix issues and re-run the checklist until all checks pass before proceeding to deploy.
Extract the full TypeScript script to a referenced file (e.g., `scripts/prod-checklist.ts`) and keep only a concise summary checklist and run command in SKILL.md.
Condense the repetitive `results.push` + `fileContains` patterns into a data-driven table to reduce token usage while preserving clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some structural overhead and verbose inline comments that could be tightened. The code blocks are long and repetitive (many similar `results.push` + `fileContains` patterns), which could be condensed into a table-driven approach. However, it doesn't over-explain concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides fully executable TypeScript code that can be assembled into a single script file. Each check is concrete with specific grep patterns, API calls, and a report generator with exit codes. The CI gate example is copy-paste ready. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced (Auth → Resilience → Observability → Credits → Report), and the final report acts as a validation checkpoint with pass/fail and exit code. However, there's no explicit feedback loop for fixing failures and re-running — the error handling table lists resolutions but doesn't instruct to re-validate after fixes. For a deployment gate involving production operations, this gap is notable. | 2 / 3 |
Progressive Disclosure | The skill has reasonable structure with sections and a resources/next steps section pointing to external references. However, the bulk of the content is a long inline script that could be split into a referenced file, with the SKILL.md providing a concise overview and checklist summary. The inline code makes the skill feel monolithic. | 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.