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".
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/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., capturing API responses, logging campaign metrics, exporting account configurations). The distinctiveness is excellent due to the narrow Instantly.ai focus.
Suggestions
Add more specific concrete actions to the capability description, e.g., 'Captures API responses, logs campaign metrics, exports account configurations, and compiles error traces for Instantly.ai debug evidence.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Instantly.ai debug evidence) and some actions (collect evidence, troubleshooting, auditing campaign/account state), but doesn't list multiple specific concrete actions like what evidence is collected, what diagnostics are run, or what outputs are produced. | 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 | Excellent trigger term coverage with explicit phrases like 'instantly debug', 'instantly support ticket', 'instantly diagnostic', 'instantly audit', 'collect instantly evidence'. These are natural terms a user would say and cover multiple variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific tool (Instantly.ai) with specific use cases (debug evidence, support tickets, diagnostics). Very unlikely to conflict with other skills due to the narrow, well-defined niche. | 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 debug skill with complete executable code in both TypeScript and bash, covering multiple Instantly API endpoints comprehensively. Its main weaknesses are verbosity (the full inline code could be more concise or split into referenced files) and the lack of explicit validation checkpoints in the workflow. The error handling table and resource links are good additions.
Suggestions
Consider moving the full TypeScript implementation to a referenced file and keeping only a concise summary with key API endpoints and the bash quick diagnostic inline in SKILL.md.
Add an explicit validation step after bundle collection, e.g., 'Verify bundle.errors is empty before submitting to support; if errors exist, retry failed endpoints or note scope limitations.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long with extensive TypeScript code blocks that include verbose type annotations and interface definitions. The `unknown` types and some boilerplate (like the full DebugBundle interface) add tokens without much value since Claude could infer these. However, it doesn't waste time explaining basic concepts. | 2 / 3 |
Actionability | The skill provides fully executable TypeScript and bash code that is copy-paste ready. It includes specific API endpoints, query parameters, HTTP methods, and concrete output formatting. Both the TypeScript and curl approaches are complete and runnable. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced (collect → save/analyze → deep dive → quick diagnostic), but there are no explicit validation checkpoints or feedback loops. For a diagnostic/data-collection workflow, there's no verification that the bundle is complete or valid before proceeding, and the error handling is passive (just collecting errors into an array) rather than providing retry guidance. | 2 / 3 |
Progressive Disclosure | The content is mostly inline with a large amount of code in a single file. The error handling table and resources section are well-structured, and there's a reference to `instantly-common-errors` for next steps. However, the extensive code blocks could benefit from being split into referenced files rather than being fully inline. | 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
70e9fa4
- 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.