review-portfolio-intake
Skill1 starsChanged 3 months agoMITView on GitHub
Quality-gate the status and capacity submissions from project and program managers — test each for completeness, currency, consistency and credibility, set a confidence level per item, and return specific asks to named owners. Run before any portfolio rollup. Dispatches the portfolio-analyst.
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
- run-ceremonySkill
- run-discoverySkill
- run-gate-reviewSkill
- setup-pmoSkill
- track-financialsSkill
- track-portfolioSkill
- track-statusSkill
- write-prdSkill
The file
Files
/review-portfolio-intake — Can this data be trusted?
When to use
At the close of a reporting cycle, before /track-portfolio. Also on demand when a portfolio number looks
wrong, when leadership questions a report, or when a manager's submissions have been drifting.
Dispatches
portfolio-analyst.
Inputs
knowledge/portfolio.md (the register and its last confidence flags), knowledge/projects/,
knowledge/sprints/, knowledge/raid-log.md, knowledge/roadmap.md, knowledge/cadence.md.
Steps
- Collect the submissions for the cycle and check each against the intake contract: complete (every required field has a value or an explicit "unknown"), current (updated inside the window — check the timestamp, not just the content), consistent (internally coherent, and coherent with the RAID log, roadmap and sprint data), credible (narrative and numbers agree).
- Flag the specific contradictions rather than general concerns — a green RAG beside a slipped milestone; a date that has moved twice while the colour held; an unchanged update on a moving project.
- Set a confidence level per register row (high / medium / low / missing) and write it to
knowledge/portfolio.md. - Build the ask list by named owner with a concrete request — the field, what's wrong, and what to supply. Never silently repair a submission; the same gap recurs next cycle if the loop doesn't close.
- Track chronic gaps. An owner missing several cycles is a portfolio risk, not an admin nuisance — escalate
to
knowledge/raid-log.mdwith an owner.
Methods
knowledge/methods/portfolio-management.md (the intake contract, confidence levels, the feedback loop),
knowledge/methods/project-management.md (RAG discipline, RAID), standards/communication-standards.md.
Output
An intake quality review saved to knowledge/portfolio/YYYY-MM-DD-intake-review.md, plus updated confidence
flags and the Data gaps table in knowledge/portfolio.md. Feedback is specific and constructive — aimed at
improving the next submission, not grading the last one. Follow standards/document-standards.md.
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.

