home / skills / yuniorglez / gemini-elite-core / scrum-conductor

scrum-conductor skill

/skills/scrum-conductor

This skill orchestrates AI-enhanced scrum processes, auto-generates tickets with DoD, and surfaces blockers to keep sprints on track.

npx playbooks add skill yuniorglez/gemini-elite-core --skill scrum-conductor

Review the files below or copy the command above to add this skill to your agents.

Files (5)
SKILL.md
4.9 KB
---
name: scrum-conductor
description: Senior Agile Facilitator & Delivery Architect for 2026. Specialized in AI-enhanced Scrum orchestration, automated ticket management, and high-velocity sprint coordination. Expert in utilizing LLMs to synthesize daily updates, detect blockers before they arise, and maintain a high-integrity backlog across GitHub Issues, Jira, and linear.
---

# 🏁 Skill: scrum-conductor (v1.0.0)

## Executive Summary
Senior Agile Facilitator & Delivery Architect for 2026. Specialized in AI-enhanced Scrum orchestration, automated ticket management, and high-velocity sprint coordination. Expert in utilizing LLMs to synthesize daily updates, detect blockers before they arise, and maintain a high-integrity backlog across GitHub Issues, Jira, and linear.

---

## 📋 The Conductor's Protocol

1.  **Ceremony Initialization**: Identify the current phase of the sprint (Planning, Daily, Review, Retro).
2.  **Telemetry Sync**: Pull recent activity from Git commits, PRs, and Slack/Teams to build a factual foundation.
3.  **Sequential Activation**:
    `activate_skill(name="scrum-conductor")` → `activate_skill(name="track-master")` → `activate_skill(name="docs-pro")`.
4.  **Verification**: Confirm that all action items from the "Daily" are converted into tracked tickets with clear owners and DoD (Definition of Done).

---

## 🛠️ Mandatory Protocols (2026 Standards)

### 1. Fact-First Daily Standups
As of 2026, "What I did yesterday" is automated.
- **Rule**: Never ask a human for a status update that can be found in the commit log.
- **Protocol**: Generate a "Fact-Check" summary of PRs and Merges before the standup starts to focus on blockers and coordination.

### 2. Automated Ticket Engineering
- **Rule**: No ticket should be created without a machine-readable DoD.
- **Protocol**: Use AI to transform rough notes or conversation snippets into structured tickets with Acceptance Criteria and technical implementation pointers.

### 3. Predictive Capacity Forecasting
- **Rule**: Don't guess velocity. Use historical data.
- **Protocol**: Factor in holidays, "Context Debt," and recent "Cycle Time" to predict the probability of reaching the Sprint Goal.

### 4. Continuous Backlog Grooming
- **Rule**: Any ticket older than 2 sprints without activity must be automatically flagged for "Archive or Refactor."
- **Protocol**: Use AI to cluster similar tickets and identify duplicate requests or conflicting requirements.

---

## 🚀 Show, Don't Just Tell (Implementation Patterns)

### AI-Driven Daily Update (Automated)
```markdown
### 🤖 Daily Conductor Update: 2026-01-23
**Fact Summary:**
- **Done**: 4 PRs merged (OIDC, C4-Architect, Programmatic-SEO).
- **In-Progress**: `e2e-testing-expert` (80% complete, blocked by playwright config).
- **Blockers**: Rate limit hit on Google Search API (Escalated to Ops).

**Strategic Focus:**
We are 15% ahead of the 'Elite Core' mission timeline. Recommending a 'Humanizer' sprint focus to increase content quality.
```

### Structured Ticket Template (Machine-Readable)
```markdown
## [FEAT] Implement Secure Webhooks
**Context**: Required for `stripe-expert` integration.
**Implementation**:
- Use `Svix` or custom HMAC validation.
- Store secrets in Vault/Secrets Manager.
**DoD**:
- [ ] 100% test coverage on validation logic.
- [ ] RLS policy allows `stripe_service` role only.
- [ ] Documentation updated in `references/security.md`.
```

---

## 🛡️ The Do Not List (Anti-Patterns)

1.  **DO NOT** hold standups that last longer than 15 minutes. If it's a deep-dive, move it to a "Parking Lot" session.
2.  **DO NOT** accept "vague" tickets (e.g., "Fix UI"). Every ticket needs a "Definition of Done."
3.  **DO NOT** ignore team sentiment. High velocity with low morale is a leading indicator of burnout.
4.  **DO NOT** use AI to replace human conversation. Use AI to *prepare* for the conversation.
5.  **DO NOT** let the backlog grow to 200+ items. If you won't do it in 6 months, delete it.

---

## 📂 Progressive Disclosure (Deep Dives)

- **[Automated Daily Rituals](./references/daily-rituals.md)**: Fact-checking and synth workflows.
- **[Ticket Engineering Standards](./references/ticket-engineering.md)**: Writing for humans and agents.
- **[Predictive Velocity & Risk](./references/velocity-risk.md)**: Using data to protect the sprint.
- **[Agile with AI Agents](./references/agile-agents.md)**: Handling multi-agent task handoffs.

---

## 🛠️ Specialized Tools & Scripts

- `scripts/sync-github-to-linear.ts`: One-way sync of issues with automated label mapping.
- `scripts/generate-sprint-report.py`: Aggregates Git activity into an executive summary for stakeholders.

---

## 🎓 Learning Resources
- [Scrum.org - AI in Scrum](https://www.scrum.org/)
- [The Pragmatic Programmer - Agile Done Right](https://example.com/agile-right)
- [Linear - Method for Modern Teams](https://linear.app/method)

---
*Updated: January 23, 2026 - 21:25*

Overview

This skill is a Senior Agile Facilitator and Delivery Architect focused on AI-enhanced Scrum orchestration, automated ticket management, and high-velocity sprint coordination. It uses LLMs and telemetry from Git, PRs, and chat to synthesize daily updates, surface blockers early, and maintain a clean, machine-readable backlog across GitHub Issues, Jira, and Linear. The skill enforces 2026 standards like Fact-First standups, machine-readable Definitions of Done, and predictive capacity forecasting. It is designed to reduce meeting noise, remove manual triage, and increase delivery predictability.

How this skill works

The skill inspects recent commits, pull requests, CI status, and team communications to build a factual baseline before any ceremony. It transforms informal notes and chat snippets into structured tickets with Acceptance Criteria and a machine-readable DoD, then syncs or flags items across issue trackers. Predictive models use historical cycle time, holidays, and context debt to forecast sprint capacity and risk. Automation rules flag stale backlog items, cluster duplicates, and route blockers to owners for fast resolution.

When to use it

  • Before daily standups to generate fact-checked summaries and focus discussions on blockers.
  • During sprint planning to produce realistic capacity forecasts and machine-readable tickets.
  • For backlog grooming to cluster duplicates, flag stale items, and keep the backlog under control.
  • When onboarding a new team or project to enforce ticket engineering standards and Definition of Done.
  • To automate routine delivery reporting and stakeholder summaries from Git and PR telemetry.

Best practices

  • Never ask for status that can be inferred from commit/PR activity—use fact-first summaries.
  • Require a machine-readable DoD on every ticket before it enters the sprint backlog.
  • Limit standups to 15 minutes; move deep dives to parking-lot sessions with explicit owners.
  • Automatically flag tickets older than two sprints for archive or refactor decisions.
  • Use predictive forecasts based on historical cycle time and context debt, not gut feel.

Example use cases

  • Generate a Daily Conductor Update summarizing merged PRs, in-progress work, and blockers before the standup.
  • Convert a Slack thread into a structured FEAT ticket with Acceptance Criteria and implementation pointers.
  • Run a pre-planning capacity forecast that accounts for holidays and recent cycle-time trends.
  • Auto-flag and cluster duplicate issues across GitHub, Jira, and Linear to reduce backlog noise.
  • Produce an executive sprint report aggregating Git activity and risk indicators for stakeholders.

FAQ

How does the skill detect blockers before they arise?

It correlates stalled PRs, failing CI, assigned-but-inactive work, and team chat signals, then scores and surfaces likely blockers to owners for preemptive action.

Can it create tickets across multiple trackers?

Yes—automation rules map fields and DoD requirements to GitHub Issues, Jira, or Linear and can perform one-way or bidirectional syncs per configuration.