manage-resources
Skill1 starsChanged 3 months agoMITView on GitHub
Maintain the supply side of capacity — the people and roles register, allocations and utilization, vendor and contractor status, scarce-skill constraints, and forecast supply changes. Use before capacity planning, when onboarding or losing people, or when allocations stop adding up. Dispatches the resource-manager.
In this repository30 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- build-business-caseSkill
- build-roadmapSkill
- capture-feedbackSkill
- close-projectSkill
- coordinate-programSkill
- define-metricsSkill
- define-strategySkill
- design-dashboardSkill
- elicit-requirementsSkill
- groom-backlogSkill
- make-deliverableSkill
- manage-changeSkill
- plan-capacitySkill
- plan-launchSkill
- plan-portfolio-automationSkill
- plan-projectSkill
- plan-sprintSkill
- powerbiSkill
- prioritizeSkill
- review-okrsSkill
- review-portfolio-intakeSkill
- run-ceremonySkill
- run-discoverySkill
- run-gate-reviewSkill
- setup-pmoSkill
- track-financialsSkill
- track-portfolioSkill
- track-statusSkill
- write-prdSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Distinctive: line 9
Before a capacity planning cycle, when people join or leave, when a contract is approaching its end, or when someone asks "do we have the …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
/manage-resources — Who we actually have
When to use
Before a capacity planning cycle, when people join or leave, when a contract is approaching its end, or when someone asks "do we have the people for this?"
Dispatches
resource-manager (lead) + program-manager (decides any rebalancing) + financial-analyst (vendor and
contractor cost).
Inputs
knowledge/resources.md (the current register), knowledge/cadence.md (teams, calendar),
knowledge/portfolio.md and knowledge/projects/ (what people are committed to),
knowledge/financials.md (vendor spend).
Steps
- Refresh the register — people, roles and skills, teams, employment type, and available FTE. Where leave or availability data hasn't been provided, record unknown; an assumed figure propagates into a capacity conclusion that looks computed.
- Work down from nominal to real. Deduct leave, support and on-call, meetings and overhead, ramp, and context-switching — and show the deductions. A 1.0 FTE person typically delivers 0.5–0.7 FTE of project work.
- Reconcile allocations. Percentage over a window, committed separated from proposed. Anyone over 100% is a finding — someone has committed capacity that doesn't exist. Flag anyone spread across three or more projects; switching cost is eating 20%+ of their time.
- Roll up utilization by role, never by naming individuals in anything that will be seen outside this file. Treat sustained utilization above ~85% as a risk to surface, not an efficiency to report.
- Name the constraint. Which scarce role or skill actually gates the portfolio, what it gates, and the
lead time on each way of relieving it — hire, contract, train a second person, or redesign the work. Add
key-person dependencies to
knowledge/raid-log.md. - Review vendors and contractors. Contract ends are capacity cliffs: check each has a knowledge-transfer plan and a renewal decision date early enough that "we had no choice" isn't the reason for extending.
- Forecast the trajectory. Joiners with ramp, leavers with notice, leave, planned hiring. Mark unstarted hiring as low-confidence supply or show it only as a scenario — capacity plans built on hiring that hasn't started are reliably wrong.
Methods
knowledge/methods/resource-management.md (deductions, utilization, constraints, vendors, forecasting),
knowledge/methods/portfolio-management.md (how supply joins the demand cycle),
knowledge/methods/agile-scrum-mechanics.md (team velocity — a different unit, never added to FTE).
Output
Updated knowledge/resources.md (people, allocations, utilization, vendors, constraints, planned changes);
key-person dependencies in knowledge/raid-log.md; findings feed /plan-capacity, whose plans land in
knowledge/capacity/. Log resourcing decisions to knowledge/decision-log.md. Follow
standards/document-standards.md.
Privacy
This register names people. Never copy individual allocation or utilization rows into a deliverable, a dashboard, or a message to leadership — roll up to role or team. Individual utilization shown upward turns a planning tool into a performance instrument, and the data stops being honest the moment people notice.
Created by Colin Beck<br>
LinkedIn: https://www.linkedin.com/in/beckcolin/<br>
GitHub: https://github.com/link7373
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
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.

