What does this skill do, and when should you use it?
This is a single launch/research skill from Aaron Marketing Skills for designing a waitlist→concept→alpha→beta→GA progression. It defines each stage’s purpose, entry action, access scope, and quantified graduation criteria, then adds cohort gating, invite throttling, tester recruitment, feedback notifications, and referral mechanics. It fits product teams that need a structured beta program, but it does not own acquisition, signup capture, consent records, the canonical launch stage record, or referral economics.
Reads the product, current stage, audience, launch goal, waitlist and tester data, and any existing launch-registry stage record; for mobile launches, it also uses official App Store Connect or Play Console beta-track constraints. Produces the five-stage ladder, quantified graduation criteria, cohort-gating and invite-throttling plan, tester recruitment and launch-day social-proof preparation, feedback status loop, and invite-code/link mechanics with anti-abuse controls. Stage definitions are submitted to launch-registry through an authorized operation: propose request to registry-events.py; the skill does not write the canonical stage record directly.
- A product lead has a waitlist and needs staged alpha and beta invitations sized to support capacity.
- A launch team needs measurable beta graduation gates for core-flow completion, structured feedback, and error tolerance.
- A mobile product team must design cohorts around TestFlight or Play testing-track constraints.
- A growth or community lead needs referral invites with codes, attribution, and anti-abuse controls.
- A launch team needs status-change notifications and compliant testimonial preparation before GA.
How do you install this skill?
- Do not treat Estimated thresholds as industry benchmarks; calibrate them against the product's own historical data.
- Confirm authorization before memory writes or registry proposals, and review waitlist and tester data for personal information.
- The skill requires notification on every status change but does not provide a reproducible notification implementation, failure path, or rollback procedure.
- Reconcile the 18.0.0 version with the security policy's supported-version statement and verify access to the required official store documentation.
- Shell / CLI
- Local filesystem
Install the repository and use the skill at its documented path. In Claude Code: /plugin marketplace add aaron-he-zhu/aaron-marketing-skills, then /plugin install aaron-marketing@aaron. On other Agent Skills-compatible hosts: npx skills add aaron-he-zhu/aaron-marketing-skills, or clone it with git clone https://github.com/aaron-he-zhu/aaron-marketing-skills. The target file is launch/research/early-access-designer/SKILL.md; the source does not document a standalone install command for this skill.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/aaron-he-zhu/aaron-marketing-skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/launch/research/early-access-designer" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Use a compatible host with: Design an early access program for [product]. Current stage: [waitlist / private beta / none]. Goal: GA by [date]. You can also use: Define graduation criteria for our beta — here is what testers can do today, plus our activation data export. Provide real waitlist, tester-count, and activation data; label thresholds Estimated until they are validated against the product’s own trailing data.
What are this skill's strengths and limitations?
- Covers the full waitlist-to-GA ladder and requires explicit opt-in and opt-out semantics.
- Combines graduation criteria, cohort gating, invite throttling, feedback notifications, and referral mechanics in one handoff-ready design.
- Separates Measured, User-provided, and Estimated evidence instead of inventing industry benchmarks.
- Respects the sole-writer model by proposing stage definitions to launch-registry rather than editing its canonical record.
- Does not replace waitlist acquisition, compliant capture-flow, or signup-page design.
- Does not record consent, maintain the canonical stage record, or model referral economics.
- Requires waitlist, tester, and activation data; without them it cannot establish a reliable baseline.
- Depends on the repository’s registry proposal protocol and local memory/event structure for formal handoff.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Early Access Designer this page | 57 · Use with care | ★ 3k | 12d ago | Apache-2.0 |
| Launch Pricing & Packaging Planner | 61 · Recommended | ★ 3k | 12d ago | Apache-2.0 |
| Launch Feedback Synthesizer | 56 · Use with care | ★ 3k | 12d ago | Apache-2.0 |
| Launch Window Planner | 57 · Use with care | ★ 3k | 12d ago | Apache-2.0 |
| Launch Tier Planner | 63 · Recommended | ★ 3k | 12d ago | Apache-2.0 |
Compared with list-growth-designer, this skill designs the stage ladder and operating mechanics while list-growth-designer handles waitlist acquisition and compliant capture. Compared with launch-registry, this skill proposes candidate stage definitions while launch-registry formalizes the canonical stage record.
How did FollowSkills review this skill?
The skill clearly limits scope, asks before saving memory, uses proposals rather than direct canonical-registry mutation, and treats imported records as untrusted. However, waitlist, tester, and analytics data may contain sensitive information, while minimization, retention, and concrete rollback procedures are not fully specified in this skill, so 8 points are deducted.
Inputs, outputs, completion criteria, and anti-fabrication rules are comparatively clear. Static review cannot reproduce the key paths, and subscriber notification, registry proposals, and platform constraints lack skill-specific tests or detailed failure feedback. The 18.0.0 skill version also conflicts with the security policy's stated supported 17.x line, so 12 points are deducted.
Trigger scenarios, inputs, outputs, exclusions, and Chinese keywords are explicit, with a keyless pasted-data path. Evidence for mainland-China reachability, platform variance, and broader non-mobile boundaries is limited, and geo-relevance is marked low, so 4 points are deducted.
The skill has strong structure: Quick Start, contract, data sources, procedure, save confirmation, handoff, references, version, and Apache-2.0 licensing. Maintenance ownership, update path, and changelog information are not clear in the skill itself, and the Writes language has slight tension with the later save-confirmation rule, so 5 points are deducted.
The expected output covers the stage ladder, graduation criteria, cohort gating, feedback loop, and referral mechanics and could directly produce a usable design document. There is no representative verified output; thresholds depend on user data and follow-on registry or operational skills. Under static calibration, 7 is the ceiling.
Measured, User-provided, and Estimated labels, official-store-source requirements, and the proposal protocol provide some auditability. The supplied tests mainly cover repository-wide architecture and audit artifacts, not this skill's key paths, and there is no third-party execution evidence, so 6 points are deducted.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →