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".
74
70%
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-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 well-structured skill description with excellent trigger terms and clear 'what/when' guidance. Its main weakness is the lack of specificity about what concrete actions the skill performs beyond the general 'collect debug evidence' — listing specific artifacts gathered (logs, configs, error states, etc.) would strengthen it.
Suggestions
Add specific concrete actions like 'capture logs, export configurations, gather error traces, compile system state' to improve specificity beyond the general 'collect debug evidence'.
| 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', etc. It stays at a high level of 'collect debug evidence'. | 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 listed. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'apollo debug', 'apollo support bundle', 'collect apollo diagnostics', 'apollo troubleshooting info', plus contextual terms like 'support tickets', 'documenting issues', 'diagnostic information'. These are phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Apollo.io-specific debug/diagnostics collection. The specific product name and debug context make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%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 code with real API endpoints and useful diagnostic curl one-liners, but it is far too verbose for a skill file — most of the TypeScript boilerplate is code Claude could generate from a concise specification. The workflow lacks validation checkpoints (e.g., checking API key presence before running, verifying bundle completeness), and the entire script should be extracted to a bundle file with the SKILL.md serving as a concise overview.
Suggestions
Extract the TypeScript code into a bundle file (e.g., src/scripts/debug-bundle.ts) and replace inline code with a brief description of what the script does, its inputs, and expected output format.
Add a pre-flight validation step checking that APOLLO_API_KEY is set and non-empty before running any API calls, and add a post-collection verification that the bundle contains expected fields.
Reduce the SKILL.md to ~40 lines: endpoint list, key type detection rules, output JSON schema, curl one-liners, and error table — Claude can generate the full script from these specifications.
Add a feedback loop: if connectivity test fails, skip endpoint tests and output a minimal bundle with the failure reason rather than proceeding with guaranteed failures.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is excessively verbose at ~150+ lines of TypeScript that Claude could generate on its own. The interface definitions, axios boilerplate, and step-by-step code splitting are unnecessary — a concise skill would provide the endpoint list, key detection logic, and output format without spelling out every line. The 'Current State' shell commands and explanations of what the bundle contains add further bloat. | 1 / 3 |
Actionability | The code is fully executable TypeScript with concrete endpoints, specific header names, real API URLs, and copy-paste ready curl commands. The error handling table provides specific diagnostic steps for each failure mode. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced (create collector → test connectivity → test endpoints → output), but there are no validation checkpoints or feedback loops. There's no verification that the generated bundle is valid/complete, no retry logic for transient failures, and no explicit check that APOLLO_API_KEY is set before proceeding. | 2 / 3 |
Progressive Disclosure | The content is monolithic — all TypeScript code is inline when it could be a referenced script file. The references to external resources (status page, docs) are good, and the 'Next Steps' pointer to apollo-rate-limits is helpful, but the bulk of the code should be in a separate file with the SKILL.md providing just the overview, usage, and output interpretation. | 2 / 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.