instantly-observability
Set up monitoring, alerting, and dashboards for Instantly.ai integrations. Use when implementing campaign health monitoring, account health alerts, or building analytics dashboards from Instantly data. Trigger with phrases like "instantly monitoring", "instantly dashboard", "instantly alerts", "instantly observability", "monitor instantly campaigns".
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-observability/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 strong completeness and distinctiveness. It clearly identifies the domain (Instantly.ai), provides explicit trigger phrases, and answers both what and when. The main weakness is that the specific capabilities could be more granular—listing concrete actions like specific metrics tracked, alert types, or dashboard components rather than staying at the category level.
Suggestions
Add more specific concrete actions such as 'track bounce rates and reply rates', 'configure threshold-based alerts for account warmup', or 'build campaign performance dashboards with send/open/reply metrics' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Instantly.ai integrations) and some actions (monitoring, alerting, dashboards), but doesn't list specific concrete actions like 'track bounce rates', 'set up Slack alerts for failed sends', or 'create campaign performance charts'. The actions remain at a category level rather than detailing specific capabilities. | 2 / 3 |
Completeness | The description clearly answers both 'what' (set up monitoring, alerting, and dashboards for Instantly.ai integrations) and 'when' (implementing campaign health monitoring, account health alerts, or building analytics dashboards), with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | The description includes a dedicated trigger phrase section with natural terms users would say: 'instantly monitoring', 'instantly dashboard', 'instantly alerts', 'instantly observability', 'monitor instantly campaigns'. It also includes domain-specific terms like 'campaign health monitoring', 'account health alerts', and 'analytics dashboards from Instantly data'. | 3 / 3 |
Distinctiveness Conflict Risk | The description is highly specific to Instantly.ai integrations, which is a distinct niche. The combination of 'Instantly' with monitoring/alerting/dashboards creates clear, unique triggers that are unlikely to conflict with generic monitoring skills or other email platform 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 skill with executable TypeScript code covering campaign health, warmup monitoring, webhook tracking, and alerting. Its main weaknesses are the monolithic structure (all code inline rather than split across files) and the lack of explicit validation checkpoints to verify the monitoring setup is working before relying on it. The content is moderately concise but could be tightened by removing some redundancy between code comments and the summary table.
Suggestions
Add an explicit validation step (e.g., 'Run a single health check manually and verify Slack alert delivery before enabling cron') to improve workflow clarity.
Extract the individual health check functions into referenced bundle files (e.g., `health-checks/campaign.ts`, `health-checks/warmup.ts`) and keep SKILL.md as a concise overview with one short example, improving both progressive disclosure and conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long with extensive code blocks that could be more concise. However, most content is actionable rather than explanatory. Some redundancy exists (e.g., the dashboard metrics table largely repeats threshold info already embedded in the code comments), and the code could be tightened, but it doesn't over-explain concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides fully executable TypeScript code with concrete threshold values, specific API endpoints, typed interfaces, and copy-paste ready implementations for health checks, alerting, and scheduling. The dashboard metrics table and error handling table add concrete reference value. | 3 / 3 |
Workflow Clarity | The steps are clearly sequenced (health checks → alerting pipeline → scheduling), but there are no explicit validation checkpoints between steps. There's no guidance on verifying that the monitoring setup itself is working correctly (e.g., sending a test alert, confirming webhook connectivity) before relying on it. The error handling for the monitor failing is good but reactive rather than a validation step. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a summary table, but it's quite monolithic at ~200+ lines of inline code. The individual health check functions could be referenced as separate files. The reference to `instantly-incident-runbook` in Next Steps is good, but no bundle files exist to support progressive disclosure. The overview-to-detail ratio is skewed toward inline detail. | 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.