risk-register
Skill0 starsChanged yesterdayMITView on GitHub
Find what could go wrong before it does: run a premortem ("it is six months later and the project failed: why?"), rate each risk by likelihood and impact, give it an owner, a prevention plan, a warning sign and a plan B, and keep the register alive during the project. Use when someone asks what could go wrong, before committing money or a date, or when a project starts to feel fragile. Triggers: "risks", "what could go wrong", "premortem", "risk register", "plan B", "risques", "qu'est-ce qui peut mal tourner", "registre des risques", "plan de secours", "riesgos", "qué puede salir mal", "registro de riesgos".
12 other projects use a version of this.
Adopted by
Most recently taken up by
- lengrufeng2008/dsh-skill-librarytheir own version, first seen Nov 15, 2026
- grcmana/grc-ostheir own version, first seen Nov 8, 2026
- grcmana/grcskillstheir own version, first seen Nov 8, 2026
- kaandgnsh/Claude-Bluetheir own version, first seen Nov 1, 2026
- MRCalderon3D/everything-game-dev-codetheir own version, first seen Oct 13, 2026
- microsoft/hve-coretheir own version, first seen Oct 13, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- microsoft/hve-core★ 1.6ksame name
- MRCalderon3D/everything-game-dev-code★ 105same name
- zbruhnke/claude-code-starter★ 16same name
- Dokkabei97/forged-claude-code★ 2same name
- grcmana/grc-os★ 2same name
- grcmana/grcskills★ 2same name
- Vaibhavkkm/vkkm-aegis-plugin★ 2same name
- aakash-dhar/claude-skills★ 0same name
- kaandgnsh/Claude-Blue★ 0same name
- kenmulford/PMSkills★ 0same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- decision-makingSkill
- delegation-briefSkill
- meeting-toolkitSkill
- project-budgetSkill
- project-charterSkill
- project-recoverySkill
- project-scheduleSkill
- responsibility-matrixSkill
- retrospectiveSkill
- scope-changeSkill
- stakeholder-mapSkill
- status-updateSkill
- vendor-selectionSkill
- weekly-reviewSkill
- work-breakdownSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
After project-charter and before committing money or a date.
- Distinctive: line 21
Before a big step: signing a contract, starting works, launching, migrating.
- Distinctive: line 22
When the project starts to feel fragile.
“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Risk register
Teams that imagine their project has already failed find more of its real risks than teams that ask "any risks?". This skill uses that premortem, then turns the answers into a short register with owners and warning signs.
When to use
- After
project-charterand before committing money or a date. - Before a big step: signing a contract, starting works, launching, migrating.
- When the project starts to feel fragile.
Inputs
- The charter, schedule and budget if they exist.
- The people involved, ideally in the same room or the same thread.
- What went wrong in similar past projects.
Method
- Run a premortem (Klein): "Imagine it is the deadline and the project failed badly. Write down every reason why." Each person writes alone first, then the list is shared; this brings out risks people hesitate to mention.
- Group and rewrite each risk as cause, event and consequence: "Because the electrician is fully booked, the works could start late, delaying the move by a month."
- Rate likelihood and impact on a simple 1 to 3 scale, with a sentence that justifies each rating.
- Plan the response for the top risks: avoid, reduce, transfer (insurance, contract clause, guarantee) or accept with a plan B. Give each one an owner and a cost.
- Define a warning sign for each top risk: the observable fact that says it is happening (no confirmation from the supplier 10 days before the date).
- Keep it alive: review it at each milestone and in
status-update; close risks that passed, add new ones.
Output
### Risk register: <project> (reviewed <date>)
| # | Risk (cause, event, consequence) | Likelihood (1-3) | Impact (1-3) | Response | Owner | Warning sign | Plan B |
|---|---|---|---|---|---|---|---|Quality bar
- Risks are specific to this project, written as cause, event and consequence.
- Each top risk has an owner, a response, a warning sign and a plan B.
- Ratings are justified, and the register has a review date.
- Insurance, guarantees and legal obligations are checked on official sources with the date when they are part of the response.
- Written in the user's language, with the terms below.
Terminology
| English | Français | Español |
| Risk register | Registre des risques | Registro de riesgos |
| Premortem | Analyse pré-mortem | Análisis pre mortem |
| Likelihood, impact | Probabilité, impact | Probabilidad, impacto |
| Mitigation | Mesure de réduction | Medida de mitigación |
| Contingency plan, plan B | Plan de secours | Plan de contingencia |
| Warning sign | Signal d'alerte | Señal de alerta |
Sources
- Klein, G. (2007). Performing a project premortem. Harvard Business Review, 85(9), 18–19.
- International Organization for Standardization. (2018). ISO 31000:2018 Risk management: Guidelines. ISO.
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.

