oneafrikan/the-grid / agent-factory/roles/growth-hacker
growth-hacker
Unverified| File | Kind | Size |
|---|---|---|
| AGENTS.md | markdown | 5.0 KB |
| IDENTITY.md | markdown | 654 B |
| MEMORY.md | markdown | 1.8 KB |
| SKILL.md | skill md | 7.2 KB |
| SOUL.md | markdown | 4.6 KB |
| USER.md | markdown | 941 B |
| role.yaml | config | 934 B |
MEMORY.md
View on GitHub<!--
MEMORY.md — Growth Hacker role memory seed (flat-file / signals model).
This file is APPENDED to _core/MEMORY_base.md at compose time.
Headings match MEMORY_base.md where they overlap so the merge reads cleanly.
Phase-1: plain markdown. A queryable DB (gbrain) replaces this later —
keep sections dumb and portable. No SQL, no structured query syntax.
A specialist experimenter records its funnel baseline and every experiment it
has run — won or lost — so it doesn't re-run dead ideas. Leave a section blank
rather than guessing — blank is honest; wrong is dangerous.
-->
# Memory (Growth Hacker seed)
## Funnel baseline
<!-- The funnel steps and their current conversion/drop-off rates — the source
of truth for picking the bottleneck and reading any lift.
Format: - <step A → step B>: <rate>% (as of YYYY-MM-DD) -->
_None yet._
## Experiments run (won / lost)
<!-- Every completed experiment, won or lost. A logged loss is a learned
constraint; an unlogged loss gets re-run.
Format: - YYYY-MM-DD <name> — hypothesis: <one line> | result: WON/LOST/INCONCLUSIVE (<lift>, <sig>) | learning: <one line> -->
_None yet._
## Active experiments
<!-- What is running right now. Read guardrails before reading the result.
Format: - **<name>** — metric: <metric> | arms: <n> | ends: YYYY-MM-DD | threshold: <lift> -->
_None yet._
## Recent decisions
<!-- Dated log of ship/kill/iterate calls and why. Append; do not overwrite.
Format: - YYYY-MM-DD: <decision> on <experiment> — <why> -->
_None yet._
## Learned preferences
<!-- Observed preferences of the operator — risk tolerance, how decisive a result
must be to ship, spend ceiling, how much to ask vs proceed. Accumulated over sessions. -->
_None yet._
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |