paperclip-api
Use when managing Paperclip AI agent companies - creating tasks, managing agents, approving hires, running heartbeats, or any Paperclip control-plane…
Сводит статус итерации, оценивает прогресс milestones, фиксирует изменения приоритетов, отслеживает зависимости и выдаёт roadmap в формате Now/Next/Later с атрибуцией задержек по 5 причинам, health score и фреймворком обрезки scope при нехватке ресурсов. User-invoked only — do
$ npx -y skills add serejaris/personal-corp-os --skill pm-roadmap --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/pm-roadmapContext preview
The summary Claude sees to decide when to auto-load this skill.
Сводит статус итерации, оценивает прогресс milestones, фиксирует изменения приоритетов, отслеживает зависимости и выдаёт roadmap в формате Now/Next/Later с атрибуцией задержек по 5 причинам, health score и фреймворком обрезки scope при нехватке ресурсов. User-invoked only — do
name: pm-roadmap description: Сводит статус итерации, оценивает прогресс milestones, фиксирует изменения приоритетов, отслеживает зависимости и выдаёт roadmap в формате Now/Next/Later с атрибуцией задержек по 5 причинам, health score и фреймворком обрезки scope при нехватке ресурсов. User-invoked only — do NOT auto-trigger. Triggers on /pm-roadmap, "обнови roadmap", "статус спринта", "анализ задержек", "update roadmap", "sprint status", "milestone progress", "delay analysis".
Part of the Personal Corp framework — running a one-person business through AI agents. Aggregate current iteration status, evaluate milestone progress, track priority changes and dependencies, output a roadmap status overview and planning suggestions.
| Field | Required | Notes | |---|---|---| | Iteration status | yes | Current Sprint task list and statuses (manual or pulled from PM tool) | | Roadmap horizon | no | Quarter / half / year; default quarter | | Changes | no | Items needing priority or timeline adjustment + reason | | Dependencies | no | Cross-team / tech dependencies and current state |
If a PM tool integration is available, pull the current Sprint task list and bucket by status. Otherwise ask the user for the list in any format (table, screenshot, verbal).
| Field | Value | |---|---| | Sprint name / period | {Sprint X / date range} | | Planned tasks | {N} | | Done | {X} ({X/N%}) | | In progress | {Y} | | Not started | {Z} | | Blocked / delayed | {W} | | Estimated on-time delivery | {%} |
**Delayed-task analysis:**
| Task | Original due | New ETA | Reason | Milestone impact | |---|---|---|---|---| | {task} | {date} | {date} | {cause} | yes/no |
**Five-cause delay attribution:**
| Cause | Pattern | Improvement | |---|---|---| | **Scope change** | Mid-development requirement edits, scope creep | Strengthen requirement freeze; route changes through approval | | **Estimation gap** | Actual effort far exceeds estimate | Calibrate from history, add buffer | | **Tech risk** | Approach proves infeasible, perf wall, tech debt blocking | Pre-development tech-spike phase | | **Dependency block** | Waiting on another team / third party / approval | 2-week-ahead dependency early-warning | | **Headcount change** | PTO, attrition, redirected | 20% capacity buffer in planning |
If the same root cause appears 3+ times, escalate to a process-improvement item.
| Milestone | Target date | Key deliverable | Progress | Status | Risks | |---|---|---|---|---|---| | {M1} | {date} | {deliverable} | {X%} | On-time / at-risk / delayed | {risk} |
**Status criteria:**
| Item | Change | Old priority | New priority | Reason | Impact | |---|---|---|---|---|---| | {item} | Up / down / new / removed | {P0/P1/P2} | {P0/P1/P2} | {reason} | {scope} |
**Change-reason categories:**
| Dependency | Type | Owner / consumer | Need-by | State | Risk | |---|---|---|---|---|---| | {desc} | Tech / team / external | {who depends on whom} | {date} | Resolved / in progress / blocked | High / medium / low |
**Dependency types:**
Recommend the next 2-3 iterations.
**Now / Next / Later view:**
| Horizon | Items | Priority | Confidence | Dependencies | |---|---|---|---|---| | **Now** (current iteration) | {in-flight work} | Locked | High | {resolved} | | **Next** (1-2 iterations out) | {planned work} | Locked / TBD | Medium-high | {to follow up} | | **Later** (3+ iterations out) | {directional plans} | Directional | Low-medium | {to evaluate} |
**Capacity assessment:**
**Roadmap health score:**
| Dimension | Weight | Scoring | Score | |---|---|---|---| | On-time delivery rate | 30% | > 80% = 5, 60-80% = 3, < 60% = 1 | {X} | | Scope stability | 20% | Change < 10% = 5, 10-30% = 3, > 30% = 1 | {X} | | Dependency resolution | 20% | > 90% = 5, 70-90% = 3, < 70% = 1 | {X} | | OKR alignment | 15% | All work traces to OKR = 5 | {X} | | Team confidence | 15% | Team confident on timely delivery = 5 | {X} |
**Composite:** weighted total ≥ 4 healthy / 3-4 at-risk / < 3 needs urgent action.
**Feature-cut decision framework (when capacity is short):**
| Cut first | Reason | Condition | |---|---|---| | Nice-to-have | Doesn't affect core value | Cut directly | | Splittable feature's second half | MVP-first | Confirm MVP standalone usable | | Polish / perfectionism | Functional > perfect | No irreversible tech debt introduced | | Low-confidence requirements | Unvalidated hypotheses | Tag "deferred for validation" |
**Principle:** cut scope > delay > add people (Brooks's Law: adding people to a late project makes it later).
# Roadmap Update
**Date:** {date}
**Horizon:** {quarter / half}
**Current iteration:** {Sprint name / dates}
## 1. Current Iteration Status
Completion rate: {X%} ({done}/{total})
Blockers: {N}
## 2. Milestone Progress
| Milestone | Target | Progress | Status |
|---|---|---|---|
## 3. Priority Changes
| Item | Change | Reason |
|---|---|---|
## 4. Dependencies & Risks
- High-risk dependencies: {desPersonal Corp is a way to run a one-person company through AI agents: tasks out of your head, departments instead of one person's memory, a weekly retro instead of "I'll sort it out someday".
Use when managing Paperclip AI agent companies - creating tasks, managing agents, approving hires, running heartbeats, or any Paperclip control-plane…
Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.
Use when user asks for Claude Code usage stats, weekly analytics, project activity summary, or wants to see what projects were worked on. Triggers on…
Use when needing strategic project analysis from multiple independent expert perspectives. Triggers on business decisions, growth strategy, product direction,…
Use when creating or refactoring CLAUDE.md files - enforces best practices for size, structure, and content organization
Use when a Personal Corp operating loop needs setup, repair, a new department, or task routing: HQ files and agent rules, GitHub issue workflow, corp-* owner…