ucsb-nlp-chang/federatedskill/queue-capacity-planning
Claude Code and agent skill by ucsb-nlp-chang/federatedskill
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Use when simulating multi-week backlog burn-down, capacity planning with step-down staffing rules, or generating Excel queue plans with constrained text summaries. Triggered by inputs containing weekly demand, training, or audit hours alongside requirements for on-call day transitions (e.g., 6→5→4 days based on backlog and demand thresholds).
Install
npx vskill@latest install ucsb-nlp-chang/federatedskill/queue-capacity-planningSKILL.md
Queue Capacity Planning & Backlog Simulation
Workflow
- Inspect Input Data: Load the reference spreadsheet. Identify rows/columns for Week numbers, Demand/Alert Load, Training Hours, and Audit Hours. Note the initial backlog value.
- Run Simulation: Execute
scripts/queue_simulator.pywith the input path, output Excel path, and output summary path. The script implements the standard step-down logic and generates both deliverables. - Verify Outputs:
- Check Excel row count matches the week span.
- Verify headers exactly match:
Week,On-Call Days,Forecast Alert Load (Analyst Hrs),Weekly Triage Capacity (Analyst Hrs),Start-of-Week Alert Queue (Analyst Hrs),End-of-Week Alert Queue/Buffer (Analyst Hrs),Burnout Overtime Hours. - Confirm transition weeks in the summary match the Excel data.
- Validate summary constraints: exactly 3 lines, ~38 words, 3 sentences, mentions both step-down weeks.
Decision Rules & Transition Logic
- Start: 6 on-call days (168 hrs capacity, 16 hrs overtime).
- Catch-up Phase: Maintain 6 days until
End-of-Week Queue ≤ 0. - Step-Down Trigger: Once backlog is cleared, evaluate next week's demand:
- If
Demand > 112→ switch to 5 days (140 hrs capacity, 8 hrs overtime). - If
Demand ≤ 112→ switch to 4 days (112 hrs capacity, 0 hrs overtime). - Step-Up Trigger: If currently on 4 days and
Demand > 112, revert to 5 days. - Queue Tracking:
End_Queue = Start_Queue + Demand - Capacity. ClampStart-of-Weekto0for reporting after catch-up, but maintain the negative buffer internally for accurate capacity tracking.
Anti-Patterns
- Do not reset the internal queue to 0 when it goes negative. Track the negative buffer to prevent capacity miscalculations in subsequent weeks.
- Do not assume staffing only steps down once. Demand spikes can trigger temporary step-ups (4 → 5 days).
- Do not hardcode summary text without verifying word/sentence counts programmatically.
Troubleshooting
- If the script fails due to unexpected input layout, read
references/simulation_rules.mdto adjust row/column indices in the parser. - If verifier rejects the summary, check sentence boundaries and ensure both transition weeks are explicitly named.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpaper_logs/3_fed_hetero_cc/glm-5/Operational-Recovery-Planning/round_001/.snapshots/u1/queue-capacity-planning/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ucsb-nlp-chang/federatedskill/queue-capacity-planning)