run-gate-review
Skill1 starsChanged 3 months agoMITView on GitHub
Run a stage-gate review — check evidence against pre-agreed entry criteria, assess delivery, financial and benefits position, and record a go / go-with-conditions / hold / kill decision with named conditions. Use at any gate defined in knowledge/governance.md. Dispatches the governance-lead.
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
- setup-pmoSkill
- track-financialsSkill
- 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 47
Start from templates/gate-review.md.
- Very specific: line 53
If knowledge/integrations.md configures Slack/Notion, offer to circulate the decision and conditions to the named owners.
≈ “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
/run-gate-review — Decide whether it proceeds
When to use
At any gate defined in knowledge/governance.md — typically before funding, before build, before launch, and
at closure. Also use when someone asks for more money or time on an initiative that has never been gated.
Dispatches
governance-lead (lead) + financial-analyst (cost and benefits position) + delivery-monitor (delivery
position) + portfolio-analyst (portfolio context and data confidence) + comms-lead (formats the pack via
/make-deliverable from templates/steerco-pack.md where the gate goes to a committee).
Inputs
knowledge/governance.md (this gate's criteria, decider, evidence required), the business case in
knowledge/financials/, the project plan, knowledge/status/, knowledge/financials.md,
knowledge/raid-log.md, knowledge/change-log.md.
Steps
- Restate the gate's one question from
knowledge/governance.md. Gates answer one question; everything else is evidence for it. If the gate has no recorded criteria or decider, fix that first — an ungated review is a status meeting. - Test each entry criterion against evidence. Record a verdict and a link per criterion. "Testing is complete" is a claim; a test report is evidence. Where evidence doesn't exist, the criterion is not met — say so and let the decider weigh it rather than softening the verdict.
- Assess the three positions — delivery (schedule and scope vs. baseline), financial (spend, forecast, CPI/SPI where a baseline exists; otherwise state that it doesn't), and benefits (are the business case's claims still credible, and what changed since approval?).
- Surface risk at this gate. Top RAID entries at the relevant level with scores; anything above the
escalation threshold in
knowledge/governance.mdis named explicitly. - Frame the decision strictly forward. Ignoring everything already spent, is the remaining cost the best use of that money? This is the counter to the sunk-cost trap that makes late gates rubber-stamps.
- Record one of four outcomes — go, go-with-conditions, hold, kill. Conditions carry an owner and a date or they are decoration. Record dissent honestly; a gate record showing unanimous agreement every time is not being used properly.
- Set the next gate and what must be true to enter it.
Methods
knowledge/methods/governance-and-change.md (gates, sunk-cost trap, decision rights, dissent),
knowledge/methods/financial-management.md (what a gate should demand of a case),
knowledge/methods/portfolio-management.md (portfolio governance and stage gates).
Output
Start from templates/gate-review.md. Save to knowledge/programs/YYYY-MM-DD-<project>-gate-<n>.md; update
the stage and RAG in knowledge/portfolio.md; log the decision and its conditions in
knowledge/decision-log.md. Where the gate went to a committee, the pack goes to knowledge/deliverables/.
Follow standards/document-standards.md.
Optional sync
If knowledge/integrations.md configures Slack/Notion, offer to circulate the decision and conditions to the
named owners. Files remain source of truth; skip 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.

