apollo-debug-bundle
Collect Apollo.io debug evidence for support. Use when preparing support tickets, documenting issues, or gathering diagnostic information for Apollo problems. Trigger with phrases like "apollo debug", "apollo support bundle", "collect apollo diagnostics", "apollo troubleshooting info".
56
66%
Does it follow best practices?
Impact
—
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-debug-bundle/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 solid skill description with excellent trigger terms, clear 'when' guidance, and strong distinctiveness due to the specific Apollo.io domain. Its main weakness is the lack of specific concrete actions beyond the general 'collect debug evidence' — listing what specific artifacts or steps are involved would improve specificity.
Suggestions
Add specific concrete actions such as 'capture API logs, export configuration settings, gather error messages, collect browser console output' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Apollo.io debug evidence) and a general action (collect), but doesn't list specific concrete actions like 'capture logs, export configuration, screenshot error states, gather API response codes'. The actions remain at a high level. | 2 / 3 |
Completeness | Clearly answers both 'what' (collect Apollo.io debug evidence for support) and 'when' (preparing support tickets, documenting issues, gathering diagnostic information) with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'apollo debug', 'apollo support bundle', 'collect apollo diagnostics', 'apollo troubleshooting info', plus contextual phrases like 'support tickets', 'documenting issues', 'diagnostic information'. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Apollo.io debug evidence collection. The specific product name and debug/diagnostics context make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%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, executable TypeScript code and useful curl diagnostics for Apollo.io debugging, but it is far too verbose for a SKILL.md body. The entire TypeScript implementation should be extracted into a bundle script file with the skill body reduced to invocation instructions, output interpretation, and the error handling table. The workflow lacks validation checkpoints (e.g., verifying axios is installed, checking the API key is set before running).
Suggestions
Extract the TypeScript code into a bundle file (e.g., `src/scripts/debug-bundle.ts`) and replace the inline code with a single invocation command like `npx ts-node src/scripts/debug-bundle.ts`.
Add a prerequisite validation step: check that `APOLLO_API_KEY` is set and `axios` is installed before running the collector, with explicit error messages if not.
Remove the `## Output` section since the code's console output already makes this obvious, and trim the `## Overview` to a single sentence.
Add a verification step after bundle generation (e.g., 'Confirm the JSON file was created and contains non-empty endpointTests array') to improve workflow clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is very verbose at ~150+ lines. The full TypeScript implementation could be a referenced script file rather than inline. The `## Current State` shell commands, the `## Overview` section explaining what the bundle does, and the `## Output` section listing what the code already clearly produces are all redundant. The interface definition and extensive inline code bloat the skill when a script file + invocation command would suffice. | 1 / 3 |
Actionability | The code is fully executable TypeScript with concrete API endpoints, specific headers, real URLs, and a complete main() function. The curl one-liners in Examples are copy-paste ready. The error handling table maps specific symptoms to specific actions. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered (1-4) with a logical sequence, but there are no explicit validation checkpoints between steps. There's no verification that the bundle was generated correctly, no feedback loop for partial failures, and no guidance on what to do if the script itself fails to compile or run (e.g., missing axios dependency). | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of code that should be split into a script file referenced by the skill. Over 100 lines of TypeScript are inline when the skill body should just explain how to run the collector and interpret results. No bundle files are provided despite the content clearly warranting a separate script file. | 1 / 3 |
Total | 7 / 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
4801da6
- 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.