instantly-common-errors
Diagnose and fix Instantly.ai API v2 common errors and exceptions. Use when encountering Instantly errors, debugging failed requests, or troubleshooting campaign/account/lead issues. Trigger with phrases like "instantly error", "instantly 401", "instantly 429", "instantly api failed", "instantly debug", "instantly troubleshoot".
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-common-errors/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-crafted skill description with strong trigger terms, clear 'when' guidance, and excellent distinctiveness due to its focus on a specific third-party API. The main weakness is that the capability description could be more specific about what concrete actions the skill performs beyond the general 'diagnose and fix' framing. Overall, it would perform well in a multi-skill selection scenario.
Suggestions
Add more specific concrete actions, e.g., 'parse error response codes, handle rate limiting (429), resolve authentication failures (401), validate API key configuration' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Instantly.ai API v2) and some actions (diagnose, fix, debug, troubleshoot), but doesn't list specific concrete actions like 'parse error responses, retry rate-limited requests, validate authentication tokens'. The actions remain somewhat general. | 2 / 3 |
Completeness | Clearly answers both 'what' (diagnose and fix Instantly.ai API v2 common errors and exceptions) and 'when' (encountering Instantly errors, debugging failed requests, troubleshooting campaign/account/lead issues), with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including specific error codes ('instantly 401', 'instantly 429'), common phrases ('instantly error', 'instantly api failed', 'instantly debug', 'instantly troubleshoot'), and domain-specific terms (campaign/account/lead issues). These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific third-party API (Instantly.ai API v2) with specific error codes and product-specific terminology. 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 diagnostic reference with excellent actionability—concrete code examples, status code tables, and a ready-to-use health check script. The main weaknesses are some redundancy between the detailed sections and the summary error handling table, and the lack of an overarching troubleshooting workflow that guides Claude through a systematic diagnostic process. The content would benefit from being trimmed and restructured with a clear decision tree at the top.
Suggestions
Remove or consolidate the 'Error Handling' summary table at the bottom, as it largely duplicates information already covered in detail in the sections above.
Add a top-level diagnostic decision tree or flowchart (e.g., 'Got a 4xx? → Check status code table. Campaign won't activate? → Run diagnoseCampaign. Accounts unhealthy? → Run fixUnhealthyAccounts') to provide a clear troubleshooting workflow with sequenced steps.
Consider moving the longer TypeScript diagnostic functions into a separate referenced file (e.g., `instantly-error-scripts.md`) and keeping only the tables and quick-reference content in the main SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with good use of tables and code examples, but there's some redundancy—the 'Error Handling' table at the bottom repeats information already covered in detail above (401, 403, 422, bounce protect). The diagnostic script and code examples earn their place, but the skill could be tightened by removing the duplicate summary table. | 2 / 3 |
Actionability | Provides fully executable TypeScript and bash code examples for diagnosing campaigns, fixing unhealthy accounts, handling rate limits, and preventing duplicate leads. The diagnostic bash script is copy-paste ready with concrete curl commands and jq processing. | 3 / 3 |
Workflow Clarity | Individual diagnostic functions have clear steps (e.g., fixUnhealthyAccounts: get accounts → test vitals → pause broken ones), but there's no overarching diagnostic workflow that sequences the troubleshooting process. The 'Quick Diagnostic Script' is a good start but lacks validation checkpoints or a decision tree for what to do based on results. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and tables, but it's quite long (~200 lines of substantive content) and could benefit from splitting detailed code examples into separate files. The references to 'instantly-install-auth' and 'instantly-debug-bundle' are good, but the inline content is heavy for a SKILL.md 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
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.