CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and well-structured as a self-contained skill, with concrete prompt guidance and clear sectioning. It loses points for a motivational intro that restates the description and for lacking an explicit validation checkpoint in what is a batch drafting workflow.

Suggestions

Trim the motivational intro paragraph ('You want to talk to real users, but finding them... takes hours') — it repeats the value prop already in the description and adds tokens Claude does not need.

Add an explicit validation checkpoint in the workflow itself, e.g. a Step 4: 'Review each draft and confirm its opening observation maps to real Amplitude data before finalizing,' rather than burying review guidance in the Tips section.

For the batch email-drafting operation, include a verify→fix loop that flags and rewrites any draft whose personalised opening cannot be tied to a specific data point Amplitude returned.

DimensionReasoningScore

Conciseness

The prompt template, placeholders, setup, and tips are lean and earn their tokens, but the motivational intro ('You want to talk to real users, but... takes hours') restates the value prop already in the description — the 'could be tightened' quality of a 2 rather than the every-token-counts quality of a 3.

2 / 3

Actionability

Guidance is concrete and copy-paste ready: an exact subject line, a specified opening structure with a worked example, branching scheduling logic (Calendly vs. offered slots + meeting link), 45-minute slots with a 15-minute buffer, and explicit rules — complete rather than the pseudocode/missing-details of a 2.

3 / 3

Workflow Clarity

The three steps are clearly numbered and sequenced (not a 1), but this is a batch operation with no explicit validation checkpoint or fix→retry loop inside the workflow — the review and skip-no-email guidance lives in Rules/Tips rather than as an explicit validate step, so it falls under 'sequence present but checkpoints missing or implicit'.

2 / 3

Progressive Disclosure

No bundle files exist and none are needed; the body is a single self-contained file organized into clearly headed sections (Prompt Template, Setup, Placeholders, Tips) with no nested references, which the rubric rewards for skills with no need for external references.

3 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong across the board: it names three concrete tool-backed actions, states an explicit use-when trigger, and carves out a distinctive niche with the drafts-only safety note. Voice is third person with no first/second-person penalty.

DimensionReasoningScore

Specificity

Lists multiple concrete actions tied to named tools — 'Find the most active users in Amplitude', 'check your Google Calendar for open slots', and 'create personalised Gmail drafts' — matching the 'lists multiple specific concrete actions' anchor rather than the partial coverage of a 2.

3 / 3

Completeness

It explicitly answers both halves: what it does ('Find... check... create... drafts') and when to use it ('Use when planning a user research sprint'), satisfying the 'clearly answers both what AND when with explicit triggers' anchor and avoiding the missing-trigger cap at 2.

3 / 3

Trigger Term Quality

Natural phrases a user would actually say appear throughout — 'user research sprint', 'research interview', 'Gmail drafts', 'open slots' — giving good coverage rather than the thin/jargon-only set that defines a 2.

3 / 3

Distinctiveness Conflict Risk

The Amplitude + Google Calendar + Gmail-drafts combination is a clear niche, and 'Never sends — always saves as drafts' further distinguishes it, making accidental triggering for another skill unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
amplitude/builder-skills
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.