ワンクリックでManusで任意のスキルを実行

name-the-aha

スター0

フォーク0

更新日2026年7月2日 09:44

Interrogate a product for its core value — name the observable aha moment, measure time-to-aha, or honestly conclude there is none yet. Use when starting Growth Circle work on any repo, when someone asks "how do we grow this", when GROWTH.md is missing or its Aha section is empty, or before any activation/retention/distribution work is proposed. This is the gatekeeper skill — every other growth skill depends on its output.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

zakelfassi

zakelfassi/skdd-commons

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

Name the Aha

Find the observable moment after which a user's behavior measurably changes — or conclude, honestly, that no such moment exists yet. Write the verdict to GROWTH.md; every downstream growth skill gates on it.

Gate

None — this is the circle's entry point. If the repo has no GROWTH.md, create one from the bundled template (references/GROWTH-template.md, spec v0.1) before proceeding. The template initializes every gate as closed — that default is load-bearing; downstream skills treat missing gates as closed too.

Inputs

The repo, and whatever exists of: product copy, onboarding flow, usage data, support tickets, reviews, user interviews.
If the product can be run, run it — experience the first session yourself before reading anyone's description of it.

Steps

Use the product cold. Fresh account, no shortcuts. Note the first moment you felt the thing work — and how many seconds/steps it took. If you can't reach value as a motivated evaluator, note where you stopped.
Hunt the behavior change. An aha is not a feeling; it's an event after which usage measurably changes. From any available data, look for the action that separates users who stayed from users who died. No data? Interview transcripts and reviews often name it verbatim ("once I saw X…").
Draft the statement. One sentence: user + moment + value. ("A commenter hears their first voice reply" — not "users love seamless audio collaboration.") If it can't fit one sentence, it isn't found yet.
Measure the clock. Time-to-aha from signup, measured if possible, estimated-and-tagged if not. Days is unrealistic; hours unrealistic; minutes necessary but insufficient. Set the reduction target one order of magnitude down.
Deliver the verdict. Write to GROWTH.md ## Aha (statement, evidence, time-to-aha, target) and set gate: aha = open. Every claim carries an evidence link or the tag hypothesis — an untagged assertion violates the spec.
Or refuse. If no behavior-changing moment exists, write NONE FOUND — growth work blocked, keep the gate closed, and output the shortest path to having value instead. This is a success of the method, not a failure of the session.

Conventions

The aha is the user's moment, not the team's ("first successful deploy", not "first paid conversion").
If the product's users are agents, the aha is time-to-first-successful-call and the evaluation in step 1 is done through public docs only.
Never soften the refusal into "the aha is probably X" to unlock downstream skills. A hypothesis-tagged aha is allowed; an invented one is not.

Edge Cases

Pre-launch product, zero users. Steps 1 and 3 still run; the statement ships tagged hypothesis with a named validation plan. The gate may open on a hypothesis — the tag travels with everything built on it.
Multiple candidate ahas. Pick the earliest one that predicts retention; log the runners-up in the lore ledger as untested beliefs.
The team insists the aha is obvious. Write their version down, then do step 2 anyway. Confirmed team intuition costs one query; wrong intuition unexamined costs the whole circle.

このリポジトリの他の Skills

同じリポジトリ

prove-the-value

zakelfassi/skdd-commons

Compile a product's earned, evidence-backed claims from GROWTH.md into a public VALUE.md — the proof-of-value surface that agent-mediated discovery reads — with attestation levels, expiry dates, and honest retractions. Use when creating or refreshing a VALUE.md, when marketing copy needs grounding in evidence, when preparing a product to be evaluated by assistants and their principals' agents, or when a published claim has gone stale.

2026-07-020

run-the-loop

zakelfassi/skdd-commons

Run the growth experiment cadence — propose ranked by keystone impact, pre-register before launch, evaluate by the committed rule, keep/kill without relitigating, log everything. Enforces the virality gate (get-users-to-get-users proposals are parked until activation and retention run green) and the alienation test (auto-kill anything a fully-informed user would resent). Use when the growth cadence comes due (weekly/biweekly), when someone proposes "a growth hack", or when experiment results need an honest verdict.

2026-07-020

forge-the-local-circle

zakelfassi/skdd-commons

Use SkDD to forge project-specialized adaptations of the Growth Circle skills — local skills that carry this product's keystone, event names, query paths, contexts, and cadence baked in, so future sessions (and cheaper models) run the circle without rediscovering it. Use when the generic pack has run against a project a few times and keeps re-deriving the same context, when handing growth work to scheduled or lighter-weight agents, or when a project's circle has stabilized enough to be worth freezing as skills.

2026-07-020

wind-the-clock

zakelfassi/skdd-commons

Make the growth circle self-running — schedule its recurring checks (loop cadence, keystone sunset, first-light freshness, AEO probes, trust-ledger review) using whatever scheduling primitive the current harness offers, and record every schedule in GROWTH.md so it survives harness changes. Use when the circle's gates are open but nothing recurs, when a keystone sunset or instrumentation check exists only as a date nobody watches, after run-the-loop establishes a cadence, or when growth work keeps happening "whenever someone remembers".

2026-07-020

hire-the-circle

zakelfassi/skdd-commons

Turn growth-team values into working artifacts — role scorecards, interview kits with listen-fors — and map which rings of the growth circle run on agents versus humans, with explicit approval boundaries. Use when hiring a first growth person, when staffing growth work across a human/agent team, when a growth hire is failing and nobody can say why, or when deciding what an autonomous agent may and may not do to users.

2026-07-020

reset-for-context

zakelfassi/skdd-commons

Detect when a playbook that works in one context is failing in another — market, language, platform, segment, or agent-mediated channel — and run the 99/1 reset protocol with native-informed deviations. Use when the same keystone reads very differently across segments, when entering a new market or platform, when metrics are flat somewhere the product "should" work, or when deciding how the product shows up in assistant recommendations.

2026-07-020

name	name-the-aha
description	Interrogate a product for its core value — name the observable aha moment, measure time-to-aha, or honestly conclude there is none yet. Use when starting Growth Circle work on any repo, when someone asks "how do we grow this", when GROWTH.md is missing or its Aha section is empty, or before any activation/retention/distribution work is proposed. This is the gatekeeper skill — every other growth skill depends on its output.
metadata	{"pack":"2026-07-growth-circle","forged-by":"claude-fable-5","forged-from":"session-2026-07-02-growth-circle — the Growth Circle protocol (github.com/zakelfassi/growth-circle)","forged-reason":"Most products have no core value, and most could. Growth machinery pointed at a valueless product is spam with extra steps — so the circle's first skill exists to name the value or refuse the work.","usage-count":"0"}

Name the Aha

Gate

Inputs

The repo, and whatever exists of: product copy, onboarding flow, usage data, support tickets, reviews, user interviews.
If the product can be run, run it — experience the first session yourself before reading anyone's description of it.

Steps

Use the product cold. Fresh account, no shortcuts. Note the first moment you felt the thing work — and how many seconds/steps it took. If you can't reach value as a motivated evaluator, note where you stopped.
Hunt the behavior change. An aha is not a feeling; it's an event after which usage measurably changes. From any available data, look for the action that separates users who stayed from users who died. No data? Interview transcripts and reviews often name it verbatim ("once I saw X…").
Draft the statement. One sentence: user + moment + value. ("A commenter hears their first voice reply" — not "users love seamless audio collaboration.") If it can't fit one sentence, it isn't found yet.
Measure the clock. Time-to-aha from signup, measured if possible, estimated-and-tagged if not. Days is unrealistic; hours unrealistic; minutes necessary but insufficient. Set the reduction target one order of magnitude down.
Deliver the verdict. Write to GROWTH.md ## Aha (statement, evidence, time-to-aha, target) and set gate: aha = open. Every claim carries an evidence link or the tag hypothesis — an untagged assertion violates the spec.
Or refuse. If no behavior-changing moment exists, write NONE FOUND — growth work blocked, keep the gate closed, and output the shortest path to having value instead. This is a success of the method, not a failure of the session.

Conventions

The aha is the user's moment, not the team's ("first successful deploy", not "first paid conversion").
If the product's users are agents, the aha is time-to-first-successful-call and the evaluation in step 1 is done through public docs only.
Never soften the refusal into "the aha is probably X" to unlock downstream skills. A hypothesis-tagged aha is allowed; an invented one is not.

Edge Cases

Pre-launch product, zero users. Steps 1 and 3 still run; the statement ships tagged hypothesis with a named validation plan. The gate may open on a hypothesis — the tag travels with everything built on it.
Multiple candidate ahas. Pick the earliest one that predicts retention; log the runners-up in the lore ledger as untested beliefs.
The team insists the aha is obvious. Write their version down, then do step 2 anyway. Confirmed team intuition costs one query; wrong intuition unexamined costs the whole circle.