메뉴
Initiative-level portfolio management with dependency tracking and milestone coordination
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Onboard a new client/company onto this platform's real Agentic OS: create the company record, scan its websites/repos, auto-provision specialist agents, activate its 24x7 agency runtime, and know exactly which "OS" building blocks (memory, integrations, dashboard) already exist versus which are roadmap gaps. ADAPTED FROM: a third-party giveaway skill ("agentic-os-installer" by Gennaro Santoro / Operations Heroes) that described a generic vault + Google-suite + skill-pack installer. That skill's product (Obsidian vault, Gmail/Calendar/ Drive wiring, "skill packs") does not exist in this repo and its promotional content (Skool community link) does not belong here. This is a clean-room rewrite that keeps the useful idea — "stand up a working agency OS for a client from a short checklist" — and maps every step to the real module that already implements it in this codebase, per CLAUDE.md architecture rules.
Agile sprint planning, velocity tracking, and burndown metrics for agent-managed projects
AI-assisted engineering impact analysis — productivity metrics and code quality insights
Cross-harness agent patterns — standardize agent execution across different coding assistants
Temporal context graph for agent memory — track entity relationships and state changes over time
Andrej Karpathy's coding guidelines for AI agents — concise, correct, and well-tested code
| name | agentic-portfolio |
| description | Initiative-level portfolio management with dependency tracking and milestone coordination |
Initiative-level portfolio management (agents/portfolio.py) that sits one level
above agentic-agile. Ranks initiatives (epics) with WSJF (Weighted Shortest
Job First), allocates finite team capacity, lays work onto a Now/Next/Later
roadmap, and rolls sprint delivery progress up from agentic-agile.
from agents.portfolio import PortfolioManager
from agents.agile_sprints import AgileManager
pf = PortfolioManager()
pf.add_initiative("Checkout v2", business_value=8, time_criticality=5, risk_reduction=3, job_size=4)
pf.add_initiative("Search relevance", business_value=5, time_criticality=2, risk_reduction=2, job_size=8)
ranked = pf.prioritized() # highest WSJF first
alloc = pf.allocate_capacity(capacity=8) # what fits this increment
roadmap = pf.plan_roadmap(capacity_per_horizon=8) # Now / Next / Later
# Roll delivery up from the agile sprints that implement each initiative
am = AgileManager()
sprint = am.create_sprint("Sprint 5")
pf.link_sprint(ranked[0].initiative_id, sprint.sprint_id)
progress = pf.rollup_progress(am)
WSJF = Cost of Delay / Job Size, where
Cost of Delay = business_value + time_criticality + risk_reduction.
Higher WSJF is scheduled sooner. Use a relative scale (modified Fibonacci:
1, 2, 3, 5, 8, 13, 20) for each component.
prioritized(), allocate_capacity(), plan_roadmap(), rollup_progress(), metrics()add_initiative, prioritize, allocate_capacity, roadmap, get_metrics.
python -m pytest tests/test_portfolio.py -v
agentic-agile (sprint/story level — the layer below)portfolio (Portfolio Manager)