0xF4ng/aether-growth-fieldwork

48 skills

• content-craft

  Writing production workflow for technical B2B and developer-community content pieces. Invoke when an author needs to produce a migration story, technical deep dive, architectural decision piece, how-to guide, or thought-leadership article from scratch. This skill selects the right story framework, produces the draft structure, and runs a pre-publish editorial checklist. It does not review completed content — use `pmm/content-review/SKILL.md` for that gate. Appropriate for any technical B2B product; no brand-specific knowledge required.

  Self-containedInstructions only2,631 words
• changelog-marketing

  Decide whether a changelog entry should stand alone or batch with others, run the quality gate, and produce a publish-ready entry with SEO title and visual recommendation.

  Self-containedInstructions only1,522 words
• cold-start-motion

  Designs the zero-to-one distribution motion: how a founder gets the first ~100 users when there is no audience, no budget, and no repeatable channel yet. Names the minimum viable audience, picks the unscalable founder-led move to do first, then runs a cheap parallel channel test to find the one channel that compounds — and defines the threshold for graduating from hustle to a scalable motion. Use at pre-traction (0–~100 users/customers), for a brand-new product or a new segment with no existing demand, or when "build it and they will come" has produced silence.

  Self-containedInstructions only3,322 words
• community-launch

  Select the right developer community platform(s) for a product launch, time the posts correctly per platform, and draft the submission with platform-specific norms applied.

  Self-containedInstructions only1,737 words
• experiment-portfolio

  Manages a portfolio of concurrent growth experiments: stage isolation rules, horizon balancing (quick/medium/long), interaction effect detection, cadence design, resource allocation, and portfolio health metrics. A single experiment tells you one thing; a portfolio managed deliberately compounds learning and prevents the most expensive growth mistakes — running experiments that contaminate each other, optimizing one stage at the expense of another, and misreading results because of simultaneous changes. Minimum viable invocation: 3+ experiments planned or active simultaneously. For a single experiment, use /growth-experiment directly.

  Self-containedInstructions only3,329 words
• experiment-results

  Closes an experiment: reads results against the original spec, renders a Win / No Signal / Loss / Confounded verdict, extracts the learning (why, not what), and specifies the next action. Required when any experiment window closes. Connects back to /growth-experiment for reformulated experiments, or forward to scaling decisions when the verdict is Win.

  Self-containedInstructions only1,866 words
• funnel-audit

  Finds the single constraint in a conversion funnel. Takes any funnel shape (AARRR, PLG onboarding, SLG pipeline, content/SEO), identifies where the most volume is being lost, classifies the bottleneck type, and outputs ranked experiment hypotheses. Use when conversion is below benchmark, when you're unsure which stage to fix, or before allocating experiment budget.

  Self-containedInstructions only3,099 words
• growth-experiment

  Designs a growth experiment: falsifiable hypothesis, specific tactic, numeric success metric, effort estimate, channel-motion match, and a distribution handoff block. Default is shippable in 7 days with readable signal in 14. Feeds directly into /experiment-results when the window closes.

  Self-containedInstructions only2,070 words
• growth-loop-design

  Diagnoses whether a product grows through funnels (linear) or loops (compounding), selects the right loop archetype, calculates the k-factor (loop coefficient), and identifies the weakest conversion step to improve. Invoke when the team is deciding which loop archetype to invest in, or when acquisition cost keeps rising despite good retention — the symptom that a funnel needs a loop on top of it. Output is a loop step map, k-factor baseline, and a single experiment targeting the weakest step.

  Self-containedInstructions only3,303 words
• launch-campaign-planning

  Select the right launch format (blitz / launch-week / full-week) and produce a structured phase plan for a discrete product or feature launch.

  Self-containedInstructions only2,065 words
• motion-community

  Designs or audits a Community-Led Growth motion for a developer-first product: diagnoses the current community stage, selects the one primary venue, designs the content loop by conversion impact, measures community health, and connects community output to product signups. Use when building a community from scratch, diagnosing a stagnant community, or deciding which community content types to prioritize for growth.

  Self-containedInstructions only2,861 words
• motion-mlg

  Coordinates a Mixed/Multi-Led Growth motion when PLG and SLG are both active in the same accounts: detects MLG territory, maps the account duality between IC champions and economic buyers, designs a "one story, two frames" content strategy, defines handoff signals, and resolves the organizational tension between product-led and sales-led teams. Use when PQL-to-close rate is below 40%, when IC usage and enterprise deal motion are creating friction, or when self-serve and enterprise motions need to compound rather than conflict.

  Self-containedInstructions only2,687 words
• motion-plg

  Designs or audits a Product-Led Growth motion: checks PLG readiness, defines the First Value Moment, designs the activation funnel, runs the onboarding audit protocol, and specifies the PLG-to-SLG handoff. Use when building PLG from scratch, diagnosing why activation or free-to-paid conversion is low, or deciding which usage signals should trigger a sales touch.

  Self-containedInstructions only2,659 words
• motion-slg

  Designs or audits a Sales-Led Growth motion for a developer-first product: checks SLG readiness, maps the full deal anatomy, runs a sales enablement content gap analysis, designs the PLG-to-SLG handoff protocol, and checks pipeline health against benchmarks. Use when deciding whether to add SLG on top of PLG, building the sales motion from scratch, or diagnosing why the sales pipeline is stalling.

  Self-containedInstructions only2,483 words
• newsletter-growth

  Designs and runs a newsletter as a compounding growth loop — not a broadcast and not SEO. Covers the subscribe→open→value→share loop, single-issue architecture (one idea, a lead that earns the open, a takeaway worth forwarding), subject/preview lines, where the subscribe and referral asks live, cadence and retention (open/reply/unsubscribe as signal), and the resource-entry → opinion content-mix sequence that builds a list then spends its attention. Use whenever someone wants to start or grow a newsletter, treat email as a growth channel, plan an issue or a launch sequence, lift open or subscribe rates, or design a newsletter subscribe/referral loop — including from a cold start with no list. Reads a VOICE-PRINT.md when present. For search as a channel use seo-content-strategy; for drafting craft use content-craft; this skill owns the newsletter as a growth system.

  Self-containedInstructions only1,844 words
• north-star-metrics

  Selects and validates the North Star Metric (NSM), builds the input metric tree beneath it, defines guardrail metrics that cannot be sacrificed, and designs the review cadence. The NSM is the single metric that most accurately captures the value the product delivers to users — not the value the business extracts from users. Prevents the most common failure mode: optimizing for revenue metrics that move up while the product quietly loses product-market fit.

  Self-containedInstructions only2,943 words
• outbound-motion

  Designs the outbound GTM motion: which signals to prioritize, how to score and sequence accounts, and what the first-touch cadence looks like. Produces a motion spec — a decision framework for the outbound program, not a campaign execution tool. Use when the team is deciding to invest in outbound, or when the current outbound is generating low-quality pipeline.

  Self-containedInstructions only1,667 words
• paid-channel-fit

  Diagnoses whether paid acquisition is the right motion at the current stage, and if so, which channels have structural fit. Produces a go/no-go decision per channel with explicit fit criteria and a test-budget recommendation. Use before committing paid budget, or when paid CAC is rising unexpectedly. NOT a campaign builder — a channel fit diagnostic.

  Self-containedInstructions only1,462 words
• retention-analysis

  Diagnoses user retention using cohort data. Classifies the retention curve shape, identifies the churn type, matches the right intervention to the right problem, and points to the next experiment. Use when retention is below benchmark, when you have a retention rate but don't know why users are leaving, or when you've just shipped a major change and want to confirm it moved the needle.

  Self-containedInstructions only2,589 words
• short-form-social

  Turns a raw idea, observation, or longer piece into platform-native short-form social posts for a technical/founder audience — LinkedIn posts, X posts, and X threads — with a hook that lands in the first line, a body shaped to the platform, and a CTA that fits the channel. Covers hook patterns, per-platform format rules, the build-in-public posture (share the scar and the number, not the announcement), and repurposing one story across surfaces. Use whenever someone wants to write a LinkedIn post or X post/thread, turn an idea or essay into social content, sharpen a weak hook, build in public, or grow founder/brand reach on social. Reads a VOICE-PRINT.md when present and routes drafts through ai-slop-audit. For long-form essays use content-craft; for the newsletter loop use newsletter-growth.

  Self-containedInstructions only1,534 words
• signal-prioritization

  Decides which intent signals, firmographic triggers, and behavioral indicators to buy, monitor, or build — and how to weight them in account scoring. Use before investing in signal data subscriptions, or when the current signal stack is generating noisy or low-quality pipeline. NOT a signal scraper — a decision framework for signal investment.

  Self-containedInstructions only1,601 words
• channel-strategy

  Designs the hardware GTM channel strategy: selects the right channel type (SI / OEM / VAR / distributor / DTC), qualifies partners, defines co-sell mechanics, and sets MDF allocation rules. Runs the three-pillar check (Pillar 3) as a gate before channel decisions. Required upstream input for hardware-gtm/launch. Run this skill whenever the go-to-market channel is undefined or when a channel is underperforming.

  Self-containedInstructions only2,155 words
• demo-strategy

  Designs and scripts hardware product demonstrations: live demos, 60-second distribution videos, and application library content. Applies the five-step demo sequence and no-narration rule. Outputs a demo script, video brief, or application library structure depending on the context. For hardware and robotics products, the demo IS the sales pitch — this skill prevents the most common demo failure modes.

  Self-containedInstructions only2,465 words
• launch

  Coordinates a hardware product launch. Mandates the three-pillar check (Product Force / Supply Chain / Channel) before any brand or marketing decisions. Two phases: pre-launch QA (certifications, yield, partner readiness) and go-live execution (channel notification, inventory, support SLA). Triggers launch-readiness-review between Phase 1 and Phase 2. For software/AI launches, use pmm/launch instead.

  Self-containedInstructions only1,576 words
• online-growth

  Bridge for hardware teams adopting digital growth methods. Translates software growth concepts (funnel, activation, PLG signals, community) into hardware-native equivalents. Non-blocking signal module — outputs carry bridge metadata and do not gate any workflow.

  Self-containedInstructions only2,121 words
• poc-pilot

  Designs and manages the hardware deal progression through three stages: DEMO → POC → PILOT → PRODUCTION CONTRACT. Defines bounded POC scope, measurable success criteria, and explicit go/no-go clauses to prevent the two most common hardware deal failures: scope creep at POC→Pilot and undefined success criteria at Pilot→Contract. Also diagnoses and intervenes on stalled pilots.

  Self-containedInstructions only2,351 words
• recurring-revenue

  Designs the recurring revenue layer for hardware companies: software license, maintenance and support, consumables, professional services, and data/insights tiers. Models LTV, defines the Year-1 bundling strategy, and builds the commoditization defense. A hardware company that sells only hardware has a lumpy, non-compounding revenue model. This skill designs the software moat.

  Self-containedInstructions only2,361 words
• safety-trust

  Converts hardware safety certifications into trust-building GTM content: safety pages, transparency reports, certification-to-content conversion, and incident communication protocols. Safety is the highest-leverage trust signal with the stakeholders who block hardware deals — procurement, legal, EHS, and insurance. This skill treats safety documentation as a growth asset, not a legal obligation.

  Self-containedInstructions only2,822 words
• ai-api-developer-gtm

  GTM playbook for AI API products targeting developers: the API-first PLG flywheel, playground and SDK design as growth levers, cookbook and tutorial strategy, Hugging Face and GitHub as primary distribution channels, and developer community mechanics for AI APIs. Use when launching an AI API, diagnosing slow API adoption, designing developer documentation, or building a developer advocacy program.

  Self-containedInstructions only2,044 words
• ai-benchmark-distribution

  Designs, publishes, and distributes AI benchmarks and evals as a growth channel. Covers what makes a benchmark worth publishing, the benchmark-to- distribution pipeline, writing rules for benchmark posts, platform-specific formats for HN and Twitter, and when NOT to publish. Use when planning a model release, comparing against alternatives, or turning internal eval results into external trust signals for a developer audience.

  Self-containedInstructions only1,937 words
• ai-output-virality

  Designs AI output sharing mechanics that turn users into a distribution channel. Covers the three types of AI virality, where to place share moments in the product, what outputs are inherently shareable, platform fit for different output types, embedding the product into shared artifacts, and how to avoid the virality-at-cost-of-trust trap. Use when designing an AI product sharing feature or diagnosing why output quality is high but organic growth is flat.

  Self-containedInstructions only2,061 words
• ai-trust-design

  Designs the trust arc for AI products: from first wow moment through production-grade reliability. Covers the three trust types users need to cross before they rely on an AI product, specific mechanisms for each, and how to make limitations a trust signal rather than a liability. Use when designing AI onboarding, diagnosing why trial-to-paid is low despite high engagement, or building transparency documentation.

  Self-containedInstructions only1,651 words
• ai-usage-pricing-growth

  Designs and optimizes usage-based pricing for AI products: how to calibrate freemium tiers, model LTV for token/credit economies, design upgrade triggers from usage signals, and avoid the traps specific to AI pricing. Use when setting up a freemium tier, diagnosing low free-to-paid conversion, modeling unit economics for an AI API, or deciding between credits, subscriptions, and pay-as-you-go.

  Self-containedInstructions only2,066 words
• ai-slop-audit

  Analyzes a draft for the patterns that make writing read as AI-generated — across structure, vocabulary, transitions, rhythm, punctuation, and closings — and returns a scored authenticity audit with a specific rewrite directive for each defect, rewriting toward the author's real voice rather than mechanically deleting patterns. Use whenever someone wants to humanize text, make writing sound less robotic or less like ChatGPT, remove AI tells, check whether a draft "sounds AI," or de-slop an AI-assisted newsletter, social, or long-form draft before publishing. Reads a VOICE-PRINT.md when present so rewrites have a target. Run this for how a draft reads; run content-review for whether it should ship. Not a generic grammar/copyedit pass and not a find-and-replace tool.

  Self-containedInstructions only1,962 words
• brand-calibration

  Scores narratives, positioning blurbs, GTM briefs, and campaign summaries across 7 brand calibration dimensions before they drive external campaigns or circulate beyond the immediate team. Invoke when any directionally relevant narrative needs a framing and calibration pass — not a relevance filter, not a line-edit, not a content quality review. Produces a scored verdict (pass / warn / fail) with flagged bullets, specific paragraph references, and downstream impact notes. Distinct from content-review (which scores publication-ready content pieces across 8 quality dimensions) and positioning-review (which gates positioning statements before Layer 3 copy is written).

  Self-containedInstructions only2,577 words
• competitive-map

  Produces a strategic competitive landscape map and per-competitor battlecard. Use before finalizing positioning, before a major launch, or when the competitive set has shifted meaningfully. Required upstream input for /sales-enablement. Not a monitoring cron — a point-in-time strategic artifact.

  Self-containedInstructions only1,481 words
• content-review

  Scores content pieces and experiment specs before publication or launch. Part A: content scoring (8 dimensions, 0.0–1.0 each). Part B: experiment spec scoring (8 dimensions). Calibrated examples anchor scores across sessions. Verdict: APPROVE / REVISE / REJECT.

  Self-containedInstructions only4,411 words
• gtm-brief

  Produces a time-bound GTM brief artifact from ICP research, competitive intelligence, product truth, and a defined time horizon. Invoke when turning research, launch context, competitive signals, or founder/PM intent into a structured, actionable plan. This is not OKR planning — it is a decision-ready brief for a named window (day / week / month). Output is a complete brief artifact with verdict on motion fit, near-term moves, open risks, and explicit decision owners. Feeds downstream into campaign execution and experiment design.

  Self-containedInstructions only3,265 words
• icp-research

  Turns raw customer research signals (interviews, support tickets, reviews, sales calls, churn notes) into a sharp ICP profile: trigger event, JTBD, deciding language, alternatives considered, and segment priority. Required upstream input for /positioning, /launch, and /growth-experiment. Use before any strategy work when "who exactly are we targeting" is genuinely unclear, or when churn patterns have shifted.

  Self-containedInstructions only3,288 words
• launch

  Coordinates a software or AI-powered product launch. Two phases: pre-launch QA (checklist against staging environment) and go-live execution (tracking, rollback, distribution). Requires FINAL positioning and an ICP card as upstream inputs. Triggers launch-readiness-review between Phase 1 and Phase 2. For hardware launches, use hardware-gtm/launch instead.

  Self-containedInstructions only2,454 words
• launch-readiness-review

  Launch gate. Runs a software or hardware checklist against the launch brief after Phase 1 QA. Blocks GO status until all applicable items pass. Verdict: GO / CONDITIONAL-GO / NO-GO.

  Self-containedInstructions only1,859 words
• multi-market-launch-ops

  Select the right coordination model (hq-led / hybrid / local-led) for each market in a multi-market launch, produce the market lane plan, and define the asset delivery schedule.

  Self-containedInstructions only1,909 words
• positioning

  Builds a complete positioning artifact: named competitive alternative, 3-5 specific unique value attributes with proof points, and a structured positioning statement. Full chain: requires ICP card upstream; outputs to positioning-review before achieving FINAL status. Use when launching a new product or market, when messaging is not converting, or when entering a new competitive context.

  Self-containedInstructions only3,969 words
• positioning-review

  Artifact gate for positioning output. Runs a binary checklist against the positioning artifact produced by /positioning. Blocks FINAL status until all items pass. Verdict: FINAL / REVISE / BLOCK.

  Self-containedInstructions only2,531 words
• pricing

  Sets price as a decision derived from value, not from cost: chooses the value metric you charge by, triangulates the price against value, cost floor, and the competitive alternative, designs the packaging/tiers, and gates the result on unit-economics sanity (LTV/CAC, CAC payback) and a buy-readiness check. Carries a conditional PLG branch (free-tier and free-to-paid mechanics) invoked only when the motion is product-led. Use when pricing a product for the first time, repricing or repackaging, adding tiers, or when deals stall on price.

  Self-containedInstructions only3,418 words
• sales-enablement

  Produces sales enablement artifacts: objection-handling framework, talk track structure, and battlecard updates for in-deal use. Use when sales reps are losing deals to objections they can't handle, when a new competitor emerges in deals, or when onboarding new reps who need structured messaging. Requires: ICP card + competitive map as upstream inputs.

  Self-containedInstructions only1,455 words
• seo-content-strategy

  Plans SEO as a GTM acquisition motion — keyword strategy, content architecture, and distribution plan grounded in ICP demand signals. Produces a content strategy that compounds over time rather than single-post tactics. Use when organic search is a viable acquisition channel for the ICP and team has capacity for sustained content. NOT a technical SEO audit.

  Self-containedInstructions only1,628 words
• voice-print

  Captures a specific writer's or founder's voice into a reusable VOICE-PRINT.md by reverse-engineering real writing samples, separating stable voice from per-channel register. Use whenever someone wants content to "sound like me," wants to define, capture, document, or hand off a writing or brand voice, is onboarding a writer or agent to a founder's voice (the taste-handoff), or is setting up a content workflow with no voice profile yet — and before drafting newsletter, social, or long-form content when no voice profile exists. Run it before ai-slop-audit and the content-creation skills, which consume its output. Not for one-off drafting or generic copy edits where no reusable voice artifact is wanted — only when the goal is to produce or reuse a voice profile.

  Self-containedInstructions only1,819 words