interview-scheduling
Find the most active users in Amplitude, check your Google Calendar for open slots, and create personalised Gmail drafts inviting them to a research interview. Never sends — always saves as drafts for your review. Use when planning a user research sprint.
73
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./product-skills/skills/interview-scheduling/SKILL.mdQuality
Discovery
85%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 strong description that clearly articulates a specific multi-step workflow across three named tools (Amplitude, Google Calendar, Gmail) with an explicit safety constraint and a clear 'Use when' trigger. The main weakness is that trigger terms could be broader to capture more natural user phrasings like 'schedule user interviews', 'recruit research participants', or 'UX research outreach'.
Suggestions
Expand trigger terms to include common variations users might say, such as 'recruit participants', 'schedule user interviews', 'UX research outreach', or 'research recruitment'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: finding most active users in Amplitude, checking Google Calendar for open slots, and creating personalized Gmail drafts. Also specifies a constraint (never sends, saves as drafts). | 3 / 3 |
Completeness | Clearly answers both what (find active users in Amplitude, check calendar availability, create Gmail drafts for research interviews) and when ('Use when planning a user research sprint') with an explicit trigger clause. | 3 / 3 |
Trigger Term Quality | Includes some natural keywords like 'Amplitude', 'Google Calendar', 'Gmail drafts', 'research interview', and 'user research sprint', but misses common variations a user might say such as 'schedule interviews', 'recruit participants', 'outreach', 'UX research', or 'user interviews'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific combination of Amplitude + Google Calendar + Gmail drafts for user research recruitment. This is a very clear niche workflow unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a prompt template with surrounding documentation than an actionable skill for Claude. It provides good high-level workflow structure and important safety guardrails (never send, only draft), but lacks concrete tool invocations, validation checkpoints, and executable specificity. The framing prose adds unnecessary tokens without improving Claude's ability to execute the task.
Suggestions
Replace vague instructions like 'Go to Amplitude and identify the top N users' with specific MCP tool calls or API queries that Claude should execute, e.g., the exact Amplitude query or endpoint to use.
Add validation checkpoints: after pulling Amplitude data, verify user count and email availability before proceeding; after checking calendar, confirm slots with the user before drafting emails.
Remove the introductory narrative paragraph ('You want to talk to real users...') — it explains the motivation which Claude doesn't need; start directly with the workflow.
Specify error handling: what should Claude do if Amplitude returns fewer than N users, if Google Calendar API fails, or if Gmail draft creation encounters an error?
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary framing ('without lifting a finger', 'takes hours') and explanatory prose that Claude doesn't need. The prompt template itself is reasonably efficient, but the surrounding narrative adds tokens without adding actionable value. | 2 / 3 |
Actionability | The skill provides a structured prompt template with clear steps and placeholder variables, but it lacks concrete executable code or specific API calls/MCP tool invocations. It describes what to do at a high level ('Go to Amplitude and identify...') rather than specifying exact tool calls, queries, or commands. It's more of a prompt template than an executable skill. | 2 / 3 |
Workflow Clarity | The three-step sequence is clearly laid out and the 'do NOT send' safety constraint is explicit. However, there are no validation checkpoints — no step to verify Amplitude data quality, confirm calendar slots are correct, or review drafts before proceeding. The 'if no email, skip' rule is good but there's no feedback loop for error recovery. | 2 / 3 |
Progressive Disclosure | The content is organized into logical sections (prompt template, setup, placeholders, tips) which is helpful. However, the prompt template is quite long and inline — it could benefit from being a separate referenced file. There are no bundle files, and the reference to 'craft-discovery-synthesis' is mentioned but not linked. For a skill of this length, the structure is adequate but not optimal. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- amplitude/builder-skills
- Commit
221ffaa
- 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.