track-portfolio
Skill1 starsChanged 3 months agoMITView on GitHub
Roll up the whole portfolio — refresh the register, gate the data, and surface themes, collisions, dependency clusters and the binding capacity constraint — then report it in two tiers, delivery detail and leadership rollup. Use for the portfolio cycle or an on-demand portfolio read. Dispatches the portfolio-analyst with delivery-monitor, then comms-lead. Supports optional tool sync.
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
- manage-resourcesSkill
- 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-statusSkill
- write-prdSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
Run scenarios on any breach — defer / re-sequence / reduce scope / add capacity — each with its effect on the constraint and its cost.
- Very specific: line 44
Start from templates/portfolio-report.md.
- Very specific: line 50
If knowledge/integrations.md configures Slack/Teams or Notion, offer to post the leadership tier there.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
/track-portfolio — How the whole portfolio is doing
When to use
The monthly portfolio cycle, ahead of a planning or investment decision, or when leadership asks "what's
actually going on across everything?". For a single project or sprint, use /track-status instead.
Dispatches
portfolio-analyst (lead) + delivery-monitor (project- and sprint-level health inputs) →
comms-lead (format the leadership tier).
Inputs
knowledge/portfolio.md, knowledge/projects/, knowledge/sprints/, knowledge/roadmap.md,
knowledge/raid-log.md, knowledge/cadence.md (teams, velocity, calendar),
knowledge/product-context.md (goals/OKRs to link investment against).
Steps
- Refresh the register — one row per project/program on the standard schema; reconcile any program row that contradicts its children rather than averaging over it.
- Gate the data first. If
/review-portfolio-intakehasn't run this cycle, run its checks now and carry the confidence levels through. Report on gaps rather than aggregating over them — say what could not be assessed and why. - Roll up health: triple constraint per item, milestone hit rate, RAG with reason and action; where a
cost/schedule baseline exists add SPI/CPI; take velocity and burndown reads from
delivery-monitor. - Analyze across: themes and recurring patterns, collisions (two or more items needing the same scarce team in the same window), dependency clusters, the binding capacity constraint by role, portfolio WIP and throughput, and concentration of risk.
- Run scenarios on any breach — defer / re-sequence / reduce scope / add capacity — each with its effect on
the constraint and its cost. Present options with consequences; hand the sequencing decision to
program-managerand the investment decision to leadership. - Have
comms-leadformat the leadership tier: exceptions and decisions needed, not an inventory.
Methods
knowledge/methods/portfolio-management.md (register, capacity cycle, collisions, KPIs, reporting tiers),
knowledge/methods/project-management.md (triple constraint, earned value, RAID, RAG),
knowledge/methods/metrics-and-experimentation.md (trends over snapshots; don't over-react to noise),
standards/communication-standards.md.
Output
Start from templates/portfolio-report.md. A two-tier portfolio report saved to
knowledge/portfolio/YYYY-MM-DD-portfolio-report.md, an updated knowledge/portfolio.md (register, capacity
summary, collisions), a capacity cycle artifact when the demand/supply run is part of this cycle, and any
portfolio-level decision logged to knowledge/decision-log.md. Follow standards/document-standards.md.
Optional sync
If knowledge/integrations.md configures Slack/Teams or Notion, offer to post the leadership tier there.
Files remain source of truth; skip silently if not configured.
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.

