instantly-debug-bundle
Collect Instantly.ai debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or auditing campaign/account state. Trigger with phrases like "instantly debug", "instantly support ticket", "instantly diagnostic", "instantly audit", "collect instantly evidence".
64
77%
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/instantly-pack/skills/instantly-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 and completeness. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., what types of evidence are collected, what outputs are produced). The distinctiveness is strong due to the niche platform focus.
Suggestions
Add specific concrete actions to improve specificity, e.g., 'Captures API response logs, exports campaign metrics, screenshots account settings, and compiles diagnostic reports for Instantly.ai support tickets.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Instantly.ai debug evidence) and mentions some actions like 'collect debug evidence', 'preparing support tickets', 'auditing campaign/account state', but doesn't list specific concrete actions (e.g., export logs, capture API responses, screenshot dashboards). | 2 / 3 |
Completeness | Clearly answers both 'what' (collect Instantly.ai debug evidence for support tickets and troubleshooting) and 'when' (encountering persistent issues, preparing support tickets, auditing campaign/account state), with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger phrases like 'instantly debug', 'instantly support ticket', 'instantly diagnostic', 'instantly audit', 'collect instantly evidence'. These are specific and cover multiple natural variations a user might say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific platform (Instantly.ai) and the narrow use case (debug evidence collection for support). The trigger terms are unique and 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 debug skill with executable TypeScript and bash examples covering multiple Instantly API endpoints. Its main weaknesses are the monolithic inline code that inflates the token footprint and the lack of explicit validation/feedback loops between steps. Splitting the code into bundle files and adding verification checkpoints would significantly improve it.
Suggestions
Extract the TypeScript debug bundle code and bash diagnostic script into separate bundle files (e.g., scripts/collect-debug-bundle.ts and scripts/quick-diagnostic.sh), keeping only usage summaries and invocation commands in SKILL.md.
Add an explicit validation step after Step 2 that checks the errors array and guides Claude on whether to retry failed endpoints or proceed with a partial bundle.
Consolidate Steps 1-3 into a clearer decision flow: collect bundle → check for errors → if account issues detected, run vitals deep dive → save final report.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long with extensive inline code that could be more compact. The TypeScript interface definition and verbose try/catch blocks add bulk, though there's minimal unnecessary explanation of concepts Claude already knows. | 2 / 3 |
Actionability | Provides fully executable TypeScript and bash code with specific API endpoints, query parameters, and response handling. Both the TypeScript bundle collector and the curl-based quick diagnostic are copy-paste ready with concrete examples. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced (collect → save/analyze → deep dive → quick diagnostic), but there's no explicit validation checkpoint or feedback loop. For a diagnostic/debug operation, there should be guidance on verifying the bundle is complete or what to do when the errors array is non-empty before proceeding. | 2 / 3 |
Progressive Disclosure | The content is largely monolithic with ~150 lines of inline code that could be split into referenced files. The error handling table and resources section are well-organized, but the bulk of the executable code would benefit from being in separate script files with the SKILL.md serving as an overview. | 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
a04d1a2
- 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.