Agent skill

critical-chain-scheduler

Critical Chain Project Management (CCPM) skill with buffer management and resource leveling

Stars 514
Forks 31

Install this agent skill to your Project

npx add-skill https://github.com/a5c-ai/babysitter/tree/main/library/specializations/domains/business/operations/skills/critical-chain-scheduler

Metadata

Additional technical details for this skill

domain
business
category
theory-of-constraints
specialization
operations

SKILL.md

Critical Chain Scheduler

Overview

The Critical Chain Scheduler skill provides comprehensive capabilities for implementing Critical Chain Project Management (CCPM). It supports critical chain identification, buffer sizing and monitoring, resource leveling, and multi-project synchronization.

Capabilities

  • Critical chain identification
  • Project buffer sizing
  • Feeding buffer calculation
  • Resource buffer placement
  • Multi-project buffer management
  • Buffer consumption tracking
  • Relay runner behavior monitoring

Used By Processes

  • TOC-004: Critical Chain Project Management
  • CAP-002: Production Scheduling Optimization

Tools and Libraries

  • Project management APIs
  • Scheduling optimization tools
  • Resource management systems
  • Buffer monitoring dashboards

Usage

yaml
skill: critical-chain-scheduler
inputs:
  project_name: "New Product Launch"
  tasks:
    - id: "T1"
      name: "Design"
      duration_50: 10  # 50% confidence estimate
      duration_90: 18  # 90% confidence estimate
      resources: ["Engineer A"]
      predecessors: []
    - id: "T2"
      name: "Prototype"
      duration_50: 5
      duration_90: 9
      resources: ["Engineer A"]
      predecessors: ["T1"]
    - id: "T3"
      name: "Testing"
      duration_50: 8
      duration_90: 14
      resources: ["Engineer B"]
      predecessors: ["T2"]
  resource_constraints:
    - name: "Engineer A"
      capacity: 1
outputs:
  - critical_chain
  - project_buffer
  - feeding_buffers
  - resource_buffers
  - project_schedule
  - buffer_status_report

CCPM vs. Traditional Project Management

Aspect Traditional CCPM
Task estimates Include safety Aggressive (50%)
Safety time Hidden in tasks Aggregated in buffers
Start rule As soon as possible As late as safely possible
Progress tracking Task completion Buffer consumption
Resource focus Utilization Flow

Buffer Types and Sizing

Project Buffer

Location: End of critical chain
Size: 50% of critical chain length
Purpose: Protect project due date

Feeding Buffer

Location: Where non-critical path joins critical chain
Size: 50% of feeding chain length
Purpose: Protect critical chain from delays

Resource Buffer

Location: Before resource-constrained critical chain tasks
Purpose: Alert resources to upcoming critical work

Buffer Management

Buffer Status % Consumed Action
Green 0-33% Plan recovery
Yellow 34-66% Implement recovery
Red 67-100% Escalate and expedite

Relay Runner Behavior

  1. Don't start early
  2. Work at full effort once started
  3. Pass work immediately when complete
  4. Focus on elapsed time, not effort

Integration Points

  • Project management systems
  • Resource management platforms
  • Portfolio management tools
  • Time tracking systems

Expand your agent's capabilities with these related and highly-rated skills.

a5c-ai/babysitter

gsd-tools

Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).

514 31
Explore
a5c-ai/babysitter

model-profile-resolution

Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role.

514 31
Explore
a5c-ai/babysitter

verification-suite

Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.

514 31
Explore
a5c-ai/babysitter

state-management

STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.

514 31
Explore
a5c-ai/babysitter

git-integration

Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.

514 31
Explore
a5c-ai/babysitter

frontmatter-parsing

YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.

514 31
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results