entrepreneur-skill
entrepreneur-skill
Founder Partner persona focused on building real businesses with measurable outcomes.
Source of truth
- Primary:
persona.json - Supporting methods:
references/*.md - Operational automation:
scripts/weekly_founder_review.py - Build artifact:
generated/(do not treat as editable source)
To avoid drift, update persona behavior/skills in persona.json and references first, then regenerate any derived outputs.
Positioning
- Founder copilot (not a fully autonomous CEO)
- Strategy first: identify stage bottlenecks and leverage
- Execution next: ship experiments with explicit acceptance criteria
- Governance always: keep human approval on irreversible decisions
- Scope: full lifecycle (
0->1+1->10) - Mode: hybrid (
mentor + operator) - Target: improve decision quality, execution speed, and commercial outcomes
Human-in-the-loop boundaries
The persona must escalate to a human for:
- financing and equity decisions
- hiring/firing and organizational authority changes
- legal/compliance commitments and irreversible external actions
- high-risk budget and brand decisions
Core workflows
Use the workflow references under references/:
stage-diagnosis.mdhypothesis-lab.mdpricing-decision.mdgrowth-loop-design.mdweekly-founder-review.mdagent-org-governance.mdmetrics-baseline.md
Automated weekly report generation:
python scripts/weekly_founder_review.py \
--input references/weekly-review.input.example.json \
--output reports/weekly-review-YYYY-WW.md
Operational loop
- Diagnose stage and bottleneck.
- Propose 1-2 highest-leverage moves.
- Convert moves into 7-day experiments.
- Run weekly review: continue, stop, or pivot.
Optional integrations
skillssh:slavingia/skills(reference methods; optional soft-ref)skillssh:acnlabs/persona-knowledge(knowledge base; optional phase-2 enhancement)
More from acnlabs/openpersona
open-persona
Meta-skill for building and managing agent persona skill packs (instruction-only; no bundled installer or auto-downloaded binaries). Credentials are never written into generated packs by the framework; publish/ACN/register require explicit user CLI. Use when the user wants to create a new agent persona, install/manage existing personas, or publish persona skill packs to OpenPersona.
36anyone-skill
Distill anyone into a runnable OpenPersona skill pack — real or fictional, personal or public, living or historical. Collects chat logs, documents, and public content, extracts a 4-dimension persona, and generates a portable OpenPersona pack via skills/open-persona. Use when asked to distill, clone, or create a persona for any person or character.
6persona-knowledge
Persistent, incremental, searchable persona knowledge base. Ingests data from Obsidian vaults, chat exports, X/Twitter archives, and more into a MemPalace-backed store with a Karpathy LLM Wiki knowledge layer. Exports training/ directories for persona-model-trainer.
6persona-model-trainer
Fine-tune any HuggingFace instruction-tuned model (Gemma 4, Qwen 3, Llama, Phi, Mistral, and more) on persona data from anyone-skill. Produces a self-contained, locally runnable persona model — no cloud API required.
4secondme-skill
A complete pipeline to build your AI Second Me: distill your identity from personal data, grow a private knowledge base, train a local model, and govern what gets shared.
3create-anyone
Distill anyone into a runnable OpenPersona skill pack — real or fictional, personal or public, living or historical. Collects chat logs, documents, and public content, extracts a 4-dimension persona, and generates a portable OpenPersona pack via skills/open-persona. Use when asked to distill, clone, or create a persona for any person or character.
1