agentleFS
janelleciprianojanellecipriano/pm-skills/skills/capacity-planning/SKILL.md

capacity-planning

Skill1 starsChanged 5 months agoMITView on GitHub

Model team capacity against committed and planned demand to spot over-allocation and forecast what can realistically be delivered. Use when the user says "capacity planning", "do we have bandwidth", "are we over-allocated", "headcount vs. demand", "can we take on X", or needs to balance workload against available people.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If over-allocated, present options: cut/defer scope, add people, extend timeline, reduce overhead.

    line 27
  2. Distinctive:

    Always state assumptions — capacity numbers are only as good as the overhead estimate behind them.

    line 39

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

Capacity Planning

Compare the work a team has signed up for against the capacity it actually has, and make over-allocation visible before it becomes slippage.

When to use

  • Deciding whether the team can absorb new work.
  • Planning a quarter/sprint allocation across people and workstreams.
  • Diagnosing chronic over-commitment.

Inputs to gather

  • People on the team and their availability (FTE %, PTO/holidays, on-call, shared allocations).
  • The time horizon (sprint, month, quarter).
  • Committed + requested work with rough sizing (see estimation-sizing).

Process

  1. Compute gross capacity = people × working days in the horizon.
  2. Subtract overhead: meetings, support/on-call, PTO, ramp-up, and a realistic productivity factor (people aren't 100% project-billable — often ~60–80%). State the factor used.
  3. That's net available capacity.
  4. Sum committed demand (sized work) and compare to net capacity → surplus or deficit.
  5. Break down by person/role to catch individual over-allocation even when the team total looks fine (a single bottleneck skill blocks everything).
  6. If over-allocated, present options: cut/defer scope, add people, extend timeline, reduce overhead. Recommend one.

Output format

## Capacity — {{team}} · {{horizon}}
| Person | Avail % | Net days | Allocated days | Over/Under |
| --- | --- | --- | --- | --- |

**Team:** net capacity {{X}} vs. demand {{Y}} → **{{surplus/deficit}} of Z days**
**Assumptions:** productivity factor {{%}}, overhead {{...}}
**Recommendation:** {{cut / add / extend}}

Always state assumptions — capacity numbers are only as good as the overhead estimate behind them.

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.