agentleFS
Sign inStart free
link7373link7373/agentic-pmo/.claude/skills/plan-capacity/SKILL.md

plan-capacity

Skill1 starsChanged 3 months agoMITView on GitHub

Plan capacity and balance load across teams — compare committed/planned work against available capacity, surface over-allocation and bottlenecks, and recommend sequencing or trade-offs. Use when staffing or load changes, or ahead of a planning cycle. Dispatches the program-manager with the scrum-master.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before a planning cycle, when staffing/load changes, or when teams feel over-committed.

    line 9
  2. Distinctive:

    Run scenarios — re-sequence, defer, reallocate, reduce scope, add capacity with its lead time — and show the effect of each on the …

    line 28
  3. Very specific:

    Start from templates/capacity-plan.md.

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/plan-capacity — Match work to capacity

When to use

Before a planning cycle, when staffing/load changes, or when teams feel over-committed.

Dispatches

program-manager (lead, cross-team view; owns the sequencing decision) + resource-manager (supply data) + scrum-master (per-team velocity/availability) + portfolio-analyst (demand and collision data).

Inputs

knowledge/resources.md (people, allocations, constraints — the supply side), knowledge/cadence.md (teams, velocity history), knowledge/portfolio.md and project plans (demand), knowledge/roadmap.md, knowledge/backlog.md, knowledge/raid-log.md (dependencies), prior cycles in knowledge/capacity/.

Steps

  1. Establish available capacity after deductions — leave, support and on-call, overhead, ramp, context switching — from knowledge/resources.md. Show the deductions; nominal headcount is not capacity. Where a team is measured in velocity rather than FTE, keep that in its own units and never add the two together.
  2. Lay committed and proposed work against capacity; identify over-allocation and the bottleneck role, not just an aggregate shortfall. Portfolios rarely run out of people in general.
  3. Map cross-team dependencies and collisions that constrain sequencing (from knowledge/portfolio.md and the program view).
  4. Run scenarios — re-sequence, defer, reallocate, reduce scope, add capacity with its lead time — and show the effect of each on the constraint. Present options with consequences; the sequencing call belongs to program-manager and anything costing money to the sponsor per knowledge/governance.md.
  5. Limit system-level WIP; protect the critical path across the portfolio. Flag sustained utilization above ~85% as a risk rather than reporting it as efficiency.
  6. State data confidence — which demand estimates are measured versus guessed, and how stale the resource register is.

Methods

knowledge/methods/resource-management.md (deductions, utilization, constraints), knowledge/methods/portfolio-management.md (demand & capacity cycle, collisions, WIP), knowledge/methods/project-management.md (dependencies, critical path), knowledge/methods/agile-scrum-mechanics.md (velocity/forecasting).

Output

Start from templates/capacity-plan.md. Save to knowledge/capacity/YYYY-MM-DD-<cycle>-capacity.md; reflect accepted changes into knowledge/roadmap.md and project plans; log capacity decisions to knowledge/decision-log.md. Report by role or team — individual allocation rows stay in knowledge/resources.md. Follow standards/document-standards.md.

Created by Colin Beck<br> LinkedIn: https://www.linkedin.com/in/beckcolin/<br> GitHub: https://github.com/link7373

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free