growth-orchestrator
Skill3 starsChanged 4 months agoMITView on GitHub
The coordinator for SocialForge — routes a social-media goal to the right skills in the right order and runs them as an end-to-end workflow. Use when the user gives a broad growth goal ("grow my account", "launch on TikTok", "go viral", "plan my month", "I have a video, do everything"), or isn't sure which skill they need. Trigger on any multi-step social-growth request. Works with any capable model.
In this repository19 other files it gives its agents.
- analytics-interpreterSkill
- audience-bullseyeSkill
- brand-voice-keeperSkill
- breakout-detectorSkill
- campaign-builderSkill
- channel-competitor-analysisSkill
- content-strategy-engineSkill
- cross-platform-adapterSkill
- engagement-boosterSkill
- hook-machineSkill
- offer-cta-architectSkill
- onboarding-brand-briefSkill
- performance-optimizerSkill
- profile-optimizerSkill
- repurpose-masterSkill
- trend-jackerSkill
- viral-script-generatorSkill
- visual-idea-generatorSkill
- youtube-title-labSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 35
Gate on quality: After hooks and scripts, apply the ship-only-4s-and-5s bar (see hook-machine).
- Distinctive: line 59
Always name the chain and the final deliverable before running it — no aimless brainstorming.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Growth Orchestrator
Individual skills are power tools; the orchestrator is the workflow that points them at a goal in sequence, passing each skill's output into the next. It turns "help me grow" into a concrete pipeline with a deliverable at the end.
First: diagnose the goal
Classify the request into one of the standard workflows, and gather the minimum inputs (niche, platform(s), current size, the asset if any). Don't over-ask — start with what's given and fill gaps as you go.
Standard workflows (skill chains)
- New account / from scratch:
onboarding-brand-brief→audience-bullseye→channel-competitor-analysis→content-strategy-engine→hook-machine→viral-script-generator - "I have one long video, do everything":
repurpose-master→hook-machine(per clip) →cross-platform-adapter→visual-idea-generator→ posting schedule - "Make this specific post go viral":
channel-competitor-analysis(of top performers in niche) →hook-machine→viral-script-generator→visual-idea-generator - Ride a trend now:
trend-jacker→hook-machine→viral-script-generator(fast lane, ship same day) - Monthly plan:
audience-bullseye→content-strategy-engine→campaign-builder→ cadence - "Why isn't this working?":
analytics-interpreter→performance-optimizer→hook-machine/content-strategy-engine(fix the weakest link) - Launch/series/challenge:
campaign-builder→content-strategy-engine→viral-script-generator→engagement-booster
Method
- Route. Pick the workflow; state the chain you'll run and the final deliverable.
- Run in sequence, pass context forward. Each skill consumes the prior output (persona → pillars → hooks → scripts). Don't restart from zero at each step.
- Gate on quality. After hooks and scripts, apply the ship-only-4s-and-5s bar (see
hook-machine). Weak link → loop that one skill, don't proceed. - Deliver + measure. End with a concrete artifact (calendar, script pack, campaign) and the metric to watch. Feed real results back into
performance-optimizernext cycle.
Output template
## Growth plan: <goal>
Workflow: <named chain>
Inputs used: <niche / platform / size / asset>
### Pipeline
Step 1 — <skill> → <output>
Step 2 — <skill> → <output> (uses step 1)
...
### Deliverable
<the final artifact>
### Metric to watch + next-cycle loop
<the one number; what to run next based on it>Rules
- Always name the chain and the final deliverable before running it — no aimless brainstorming.
- Pass context forward; never make a later skill re-derive what an earlier one already produced.
- One weak link kills the funnel. Gate after hooks/scripts and loop the weakest step rather than shipping it.
- Match ambition to inputs — a from-scratch account gets foundations first (persona, pillars), not a viral moonshot.
- Close the loop: every plan ends with a metric and what to run next cycle.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

