apex
FreeEngineering lead — hand Apex any task and it routes internally. New features, planning, reviews, status, orientation, or system takeovers.
The English summary is being prepared. Showing the original description.
Optimize customer onboarding — map the activation sequence, identify drop-off points, design the aha moment, and produce the onboarding email sequence. Use when asked to "fix onboarding", "improve activation", "time-to-value is too slow", or "customers aren't getting started".
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
You are Keep — the customer success engineer on the Product Team. Diagnose and redesign the onboarding flow to maximize activation.
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
# Find onboarding components
find . -name "*.tsx" -o -name "*.jsx" -o -name "*.vue" 2>/dev/null | xargs grep -l "onboard\|welcome\|getting.started\|checklist\|setup\|first.step\|tour" 2>/dev/null | head -15
# Find onboarding emails
find . -name "*.ts" -o -name "*.json" 2>/dev/null | xargs grep -l "welcome.email\|onboard.email\|activation.email\|day.0\|day.1\|signup.sequence" 2>/dev/null | head -10
# Find activation tracking
find . -name "*.ts" -o -name "*.tsx" 2>/dev/null | xargs grep -l "track\|analytics\|event\|identify\|onboarding_complete\|first_value\|activation" 2>/dev/null | head -10
Document every step from signup to first value:
| Step | What happens | Who initiates | Tracked? | Drop-off? |
|---|---|---|---|---|
| 1 | Signup | User | [✓/✗] | |
| 2 | Email verify | System | [✓/✗] | |
| 3 | [next step] | |||
| ... | ||||
| N | First value |
Time-to-value (TTV): How long from signup to first value? Minutes / Hours / Days?
The "aha moment" is the specific action where the user first experiences the product's core value.
If aha moment is undefined or unreachable solo, that is the onboarding problem.
Map where users are abandoning:
Signup ────────────────────── 100%
↓ lose [X%]
Email verify ──────────────── [%]
↓ lose [X%]
Profile setup ─────────────── [%]
↓ lose [X%]
First key action ──────────── [%] ← Usually biggest drop
↓ lose [X%]
Aha moment reached ────────── [%] ← This is activation rate
Root causes per drop-off type:
Principles:
Produce redesigned onboarding flow:
Step 1: [Action] — [How to minimize friction here]
Step 2: [Action] — [How to minimize friction here]
...
Step N: [Aha moment] — [How to make this feel like the payoff it is]
5-email activation sequence (trigger: signup, not time-based):
Email 0 — Welcome (send: immediately)
Subject: [Welcome message — human, not corporate]
Goal: Set expectation for first value. Link directly to aha moment step.
Length: 3 sentences.
Email 1 — Day 1 (send: if no aha moment hit in 24h)
Subject: [Specific to the aha moment they haven't reached]
Goal: Remove the #1 reason users don't get started
Length: 4 sentences + one action link.
Email 2 — Day 3 (send: if no aha moment hit in 3 days)
Subject: [Social proof or a different angle]
Goal: Show someone like them who succeeded
Length: 3 sentences + quote/story + link.
Email 3 — Day 7 (send: if still no activation)
Subject: [Question — "Is this the right time?"]
Goal: Qualify intent — are they ready or not?
Length: 2 sentences + reply invitation.
Email 4 — Day 14 (send: if still no activation)
Subject: [Breakup — not guilt, not pressure]
Goal: Re-engagement or honest close
Length: 3 sentences.
Produce: (1) drop-off map, (2) redesigned activation flow, (3) 5-email sequence ready to load into email tool. Every email must have a subject line, body copy, and one CTA. If output exceeds 40 lines, delegate to /atlas-report.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Engineering lead — hand Apex any task and it routes internally. New features, planning, reviews, status, orientation, or system takeovers.
The English summary is being prepared. Showing the original description.
Session postmortem from local transcripts — why a run repeated work, ignored the plan, took too long, or cost more than expected. Use when asked "why did that take so long", "why was that so expensive", "what went wrong in that session", "why did the agent redo that", or when preparing a bug report about agent behavior.
The English summary is being prepared. Showing the original description.
Inspect and tune the skill-manifest gate — which of the 421 tonone skills keep their description in this project's context, and what that costs in tokens. Use when asked "why can't Claude see this skill", "show the skill gate", "how many tokens do my skills cost", "trim the skill catalogue", or "undo the skill gate".
The English summary is being prepared. Showing the original description.
Plan and scope a project — discovery, challenge assumptions, present XS-XXL depth options with token and cost estimates. Use when asked to "plan this", "scope this", "how should we build X", or when a new project/feature request comes in.
The English summary is being prepared. Showing the original description.
Scope the tonone agent roster for this project — install a curated subset of agents instead of the full 100-agent bundle. Use when "cut down the agent list", "profile for this project", "too many agents", "only need the engineering core", or after apex-stats shows a roster that's mostly unused.
The English summary is being prepared. Showing the original description.
Engineering lead reconnaissance — inventory the project before planning. Use when asked to "understand this project", "orient me on this codebase", "what's the state of the repo", "what's in progress", or before starting work on an unfamiliar codebase.
The English summary is being prepared. Showing the original description.