instantly-cost-tuning
Optimize Instantly.ai costs through plan selection, account management, and usage monitoring. Use when analyzing Instantly billing, reducing per-campaign costs, or choosing between Instantly pricing tiers. Trigger with phrases like "instantly cost", "instantly pricing", "instantly billing", "reduce instantly cost", "instantly plan comparison".
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-cost-tuning/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, clearly targeting Instantly.ai cost optimization with explicit trigger terms and use-when guidance. The main weakness is that the capability actions could be more concrete and specific—terms like 'account management' and 'usage monitoring' are somewhat generic. Overall it performs well for skill selection purposes.
Suggestions
Replace vague actions like 'account management' and 'usage monitoring' with more concrete capabilities, e.g., 'calculate cost-per-lead by plan tier', 'recommend optimal sending account allocation', or 'audit monthly usage against plan limits'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Instantly.ai costs) and some actions (plan selection, account management, usage monitoring), but the actions are somewhat generic and not deeply concrete—e.g., 'account management' is vague. It doesn't list specific concrete outputs like 'compare plan pricing tables' or 'calculate cost-per-lead by tier'. | 2 / 3 |
Completeness | Clearly answers both 'what' (optimize Instantly.ai costs through plan selection, account management, usage monitoring) and 'when' (explicit 'Use when' clause with specific scenarios plus a 'Trigger with phrases' section listing concrete trigger terms). | 3 / 3 |
Trigger Term Quality | Includes a strong set of natural trigger phrases users would actually say: 'instantly cost', 'instantly pricing', 'instantly billing', 'reduce instantly cost', 'instantly plan comparison'. These cover common variations well and match real user language. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive—targets a specific SaaS product (Instantly.ai) and a specific concern (cost optimization/billing). Very unlikely to conflict with other skills given the narrow, product-specific 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 well-structured, highly actionable skill with executable TypeScript code covering the full cost optimization workflow for Instantly.ai. Its main weaknesses are verbosity (all code inline in a single file making it token-heavy) and missing validation/confirmation steps before destructive actions like removing accounts. The time-sensitive pricing data (2026) is presented without deprecation context.
Suggestions
Add explicit validation/confirmation checkpoints before destructive actions (e.g., 'Verify account is truly unused before removal' with a check step), especially in Step 4.
Move the large code blocks to separate referenced files (e.g., audit-utilization.ts, campaign-efficiency.ts) and keep only concise summaries and key API endpoints in the main SKILL.md.
Mark the pricing table with a note about when it was last verified, or move it to a separate PRICING.md that can be updated independently.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes substantial executable code which is useful, but is quite long (~200 lines of code). Some console.log messages are verbose, and the pricing table includes time-sensitive 2026 data inline. The overview paragraph explains obvious concepts like 'Instantly's pricing is based on sending accounts and features, not per-email' which Claude could infer from the pricing table. | 2 / 3 |
Actionability | Provides fully executable TypeScript code for each step — account auditing, campaign efficiency analysis, plan right-sizing, and cost reduction. Code includes specific API endpoints, type annotations, and concrete calculations like cost-per-reply. The checklist and error handling table add further concrete guidance. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced (audit → analyze → right-size → optimize), but there are no explicit validation checkpoints or feedback loops between steps. For cost optimization involving account removal and campaign changes (potentially destructive operations), there should be confirmation/validation steps before taking action. | 2 / 3 |
Progressive Disclosure | The skill is quite long with all code inline rather than referenced from separate files. The pricing table, four large code blocks, checklist, error table, and resources are all in one file. The code examples could be referenced as separate files. The 'Next Steps' reference to 'instantly-reference-architecture' is good but the main content would benefit from splitting. | 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.