Skip to content

0xF4ng/aether-growth-fieldwork / find-skill

find-skill

Verified

Entry-point router. Ask the user two questions, then route to the right skill. Call this when you don't know where to start.

find-skill

Purpose

This is the single entry point for first-time and returning users who are not sure which skill applies to their situation. Ask two questions, read the dispatch table, recommend one skill with a one-line rationale. Do not deliver content — route only.


Before starting

Nothing required. This skill runs on zero prior context.


Contract

Produces exactly:

  1. One recommended skill path (e.g. pmm/positioning/SKILL.md)
  2. One sentence explaining why
  3. Optional: one upstream dependency if the recommended skill requires a prior artifact

Does not produce any positioning, analysis, launch plan, or GTM content. If the user wants to start working immediately, hand off to the recommended skill.


Decision logic

Step 1 — Ask role (if not already stated)

"What's your role? Choose one: PMM / Growth / Hardware GTM — or describe what you're working on and I'll infer."

If the user already stated a role or described a problem with obvious role signal, skip the question and proceed.

Step 2 — Ask for a one-sentence problem description (if not already stated)

"Describe what you're trying to do or the problem you're facing in one sentence. Include: what stage you're at and what you already have (e.g. an ICP card, a live product, early experiment data)."

If the user's opening message already contains enough context, skip the question.

Step 3 — Read foundations/RESOLVER.md and route

Map the user's role + problem to a single skill using the resolver's intent table. Apply these tie-breaking rules:

SituationRule
User has no ICP card yetAlways start with pmm/icp-research before any positioning or launch skill
User has positioning but no reviewRoute to pmm/positioning-review before pmm/launch
User is hardware with no three-pillar checkRoute to hardware-gtm/launch (it begins with the three-pillar gate)
User mentions experiment data to readRoute to growth/experiment-results, not growth/growth-experiment
User mentions linear growth / no compoundingRoute to growth/growth-loop-design before experiment skills
User is unsure of their metricRoute to growth/north-star-metrics first
Ambiguous between two skillsName both and ask one clarifying question
User has a launch but doesn't know what formatRoute to growth/launch-campaign-planning before pmm/launch — format must be selected before go-live QA
User asks about Product Hunt or Hacker News specificallyRoute to growth/community-launch — platform-specific norms apply before any content is drafted
User has multi-market scope with CN, KR, or JP in scopeRoute to pmm/multi-market-launch-ops first — coordination model must be confirmed before phase planning begins
User asks about competitors but has no named alternatives yetRoute to pmm/competitive-map before pmm/positioning — positioning without named alternatives is unverifiable
User wants to design or run an outbound programRoute to growth/outbound-motion — it owns sequence design, scoring, and first-touch framework; run growth/signal-prioritization first if trigger event is undefined
User wants outbound but has no defined trigger eventRoute to growth/signal-prioritization first — outbound without a signal stack burns list with no precision
User wants paid acquisition but has no PMF signalRoute to growth/paid-channel-fit — it contains the pre-PMF BLOCK; do not skip the economics gate
User wants SEO strategy but is pre-PMF or <6 months capacityRoute to pmm/seo-content-strategy — it contains the pre-PMF BLOCK and the capacity WARN; surface that first
User needs sales materials but deciding language is not definedRoute to pmm/sales-enablement — it requires ICP Layer D before drafting any handler or talk track

Output format:

Recommended skill: [path/to/SKILL.md]
Why: [one sentence]
Requires first: [upstream dependency, or "none"]

Anti-patterns

  • Do not start delivering content. This skill routes; it does not position, audit, or design.
  • Do not list every possible skill. One recommendation only. If truly ambiguous, name two and ask one question.
  • Do not ask more than two clarifying questions. If you still can't route after two answers, pick the closest match and state your assumption.

Related skills

  • All skills in pmm/, growth/, hardware-gtm/ — this skill routes to them
  • foundations/RESOLVER.md — the dispatch table this skill reads
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall