mirror of
https://github.com/hanzoai/skills.git
synced 2026-11-19 00:47:36 +00:00
Four MIT collections ported — growthOS, openclaw-marketing-skills, Marketing-Skills and pm-skills — as 160 skills, 12 agents and 45 commands, each naming its origin in its own frontmatter so the tree can be checked against THIRD_PARTY_NOTICES rather than trusted. Sixteen names appeared in more than one collection and none of the copies were identical; the longest wins, which lands on the more developed text where they genuinely diverge. A fifth collection is deliberately absent. awesome-growth-hacking-skills carries NO licence, which leaves its author every right by default — and it is a list of links rather than a collection of skills, so there is nothing in it to port and no permission to port it with. It is cited as a directory to read. THE CONNECTOR SKILLS ARE REWRITTEN, not ported. They arrived installing vendor SDKs, running OAuth flows of their own, and ending with long-lived credentials in JSON files under .agents/ and ~/.growthos/ at mode 600. That is a secret on a disk with no rotation path, protected from other users and not from the agent — and one auth implementation per skill. Hanzo holds these connectors in Go, per user, sealed in KMS, so `connect` is the one home for the flow and the platform skills defer to it by provider id: google_ads, meta_ads, x. It is reachable as HTTP or as MCP tools at api.hanzo.ai/v1/mcp — the same routes, typed once in Go, so a tool and a curl cannot disagree. Two had nothing real behind them and now say so. There is no search_console provider, so that skill names what does answer the same questions (google_analytics, google_bigquery) and states that the remedy is a provider in hanzoai/cloud rather than a vendor SDK here. And getxapi-connect was a wrapper around a paid reseller of X's public data with the vendor's key in an env var; it is `listen` now, on our own x connector — a skill named after a vendor makes the vendor the capability and dies with it. The skills referenced paths that only existed inside the source repo, so the shared material they read is ported to reference/ and the paths rewritten. Three skills need the growthOS APPLICATION rather than its data; per the estate's own split an application belongs in hanzoai/ads, social, email or sms as a cloud plugin, so those three say what they need instead of carrying an import that resolves to nothing. Third-party product names are out of our prose and kept in the notices, which is where the licence requires them and the only place they belong. A skill's persona names a role, not somebody else's product. Co-authored-by: Hanzo Dev <[email protected]>
3.7 KiB
3.7 KiB
source
| source |
|---|
| melgarafael/growthOS |
/grow free-content — Educational Team bridge
Subcommand that pulls raw material (videos, lessons, transcripts) from the Educational Team project (TIM) via Maestri, runs it through the content-factory skill to extract viral-worthy chunks, and pipes the result into the normal carousel pipeline.
Usage
/grow free-content # interactive: asks which source
/grow free-content "última aula sobre 3 Camadas da Maestria"
/grow free-content --source ~/educational-team/lessons/aula-05-maestria.md
Pipeline
- Maestri terminal check —
maestri listto confirmOrquestrador - Educational teamis connected - Source selection — if not passed as arg, ask user:
- "qual aula/vídeo você quer transformar em conteúdo?"
- "quer escolher um específico OU pegar o mais recente no repo educational-team?"
- Dispatch Orquestrador —
maestri ask "Orquestrador - Educational team"with compact prompt:FREE CONTENT REQUEST from . Locate {source}, transcribe if video, extract: 1) viral chunks (self-contained, 60-90s worth) 2) key frameworks mentioned (3 Camadas, 3 Pilares, 7 Passos, etc.) 3) suggested carousel topics Return path to a markdown file at reference/voice/free-content/from-educational-{timestamp}.md - Wait for Orquestrador output — monitor via
maestri checkevery 3-5 min - Process via content-factory skill — the raw output is passed through
content-factorywhich already knows how to turn educational material into AutomatikClub Free Content Hub posts - Generate carousel briefs — for each viral chunk, create a
BRIEF-free-content-{slug}.mdinreference/design-system/ - Hand off to carousel-designer — each brief enters the normal pipeline (asset auto-pick → lime-geist render → review dashboard)
- Notify user — list the briefs that were created and next steps
Folder structure
reference/voice/free-content/
├── from-educational-{timestamp}.md # raw output from Orquestrador
├── chunks/ # extracted viral chunks
│ └── chunk-{slug}.md
└── INDEX.md # tracks all free-content runs
Integration with learning loop
Every carousel generated from free-content is tagged in metadata.json with source: "free-content" so the review dashboard and PROFILE.md can track which topics came from educational material vs native ideation.
Example autonomous run
User: /grow free-content
Claude:
→ Loading Maestri terminals...
→ Orquestrador - Educational team ✓ connected
→ Which lesson/source?
User: última aula sobre as 3 camadas
Claude:
→ Dispatching Orquestrador...
→ [waiting 3 min]
→ Received: reference/voice/free-content/from-educational-20260408-163200.md
→ Extracted 4 viral chunks:
- "A maestria não é o fim" (filosófico)
- "Técnica vs Lógica vs Maestria — quanto você cobra em cada camada" (paradox)
- "O aluno que pulou direto pra Maestria sem técnica" (cautionary)
- "Exercício: onde você está no cubo 3D?" (diagnostic)
→ Creating 4 briefs in reference/design-system/
→ Dispatching carousel-designer via Maestri for each
→ 4 carousel sections added to carousels-v4.html
→ Ready for review: /grow review
Rules
- NEVER bypass the Orquestrador (it owns the educational-team repo context)
- ALWAYS cross-reference the output with GOLDEN-DOC voice
- If a chunk violates the vocabulary rules (bot/chatbot/etc), FILTER it out before handing to carousel-designer
- Free content is ALWAYS voice-tagged: every generated carousel includes
source: free-content, lesson: {id}in metadata