track-financials
Skill1 starsChanged 3 months agoMITView on GitHub
Run the financial cycle — refresh actuals against cost baselines, compute earned-value indices (CPI/EAC/VAC), forecast the remaining work, check funding envelopes, and review whether claimed benefits actually arrived. Use monthly or before a gate. Dispatches the financial-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
- review-portfolio-intakeSkill
- run-ceremonySkill
- run-discoverySkill
- run-gate-reviewSkill
- setup-pmoSkill
- track-portfolioSkill
- track-statusSkill
- write-prdSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 23
Check baseline integrity: Every approved change in knowledge/change-log.md should have re-baselined knowledge/financials.md.
- Very specific: line 52
If knowledge/integrations.md configures Slack or Notion, offer to post the exceptions summary.
≈ “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-financials — Where the money actually is
When to use
The monthly financial cycle, before a gate or steering committee, or when a project's spend stops matching its progress.
Dispatches
financial-analyst (lead) + delivery-monitor (schedule-side earned value and completion evidence).
Inputs
knowledge/financials.md (baselines, actuals, benefits register), knowledge/projects/,
knowledge/status/, knowledge/change-log.md (approved changes that moved a baseline),
knowledge/portfolio.md, knowledge/cadence.md (fiscal calendar).
Steps
- Refresh actuals. Record spend to date per project against its envelope. Where spend data hasn't been provided, the actual is unknown — not zero and not the forecast. Name the gap and its owner.
- Check baseline integrity. Every approved change in
knowledge/change-log.mdshould have re-baselinedknowledge/financials.md. Any that didn't is the first finding — without it, every variance below is measured against a target everyone has already agreed is wrong. - Compute earned value where a baseline exists. CPI = EV/AC, SPI = EV/PV, EAC = BAC/CPI, VAC = BAC−EAC. Where there is no cost baseline, write "CPI unavailable — no cost baseline" rather than deriving one. EV needs objective completion criteria; percent-complete self-reported by the team is not objective.
- Forecast the remaining work. Sunk cost is data, not an input. Use
EAC = AC + (BAC − EV)only when you can name what specifically changed about the remaining work — "we'll catch up" is not that. Give a range with its drivers. - Check the envelopes. Approved vs. committed vs. spent per funding source; flag any envelope that the current forecast breaches, and by when.
- Review benefits. For each benefit in the register whose realization window has started, compare actual against claim — including when it didn't arrive. Feed the delta back into estimating; that loop is what makes the whole exercise worth running.
- Lead with the exceptions. Projects where CPI is deteriorating, an envelope is at risk, or a benefit has silently disappeared. Everything on plan goes in a table, not in prose.
Methods
knowledge/methods/financial-management.md (forecasting discipline, EAC choice, benefits realization),
knowledge/methods/project-management.md (full EVM mechanics),
knowledge/methods/portfolio-management.md (portfolio KPIs, reporting tiers).
Output
Updated registers in knowledge/financials.md (actuals, EVM, benefits, assumptions) and a review artifact at
knowledge/financials/YYYY-MM-DD-<period>-financial-review.md; benefits reviews as
YYYY-MM-DD-<initiative>-benefits-review.md. Log any re-forecast or benefit write-off to
knowledge/decision-log.md. Follow standards/document-standards.md.
Optional sync
If knowledge/integrations.md configures Slack or Notion, offer to post the exceptions summary. Never post
project-level cost detail to a broad channel without confirming the audience. Files remain source of truth.
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.

