raid-log
Skill1 starsChanged 5 months agoMITView on GitHub
Create and maintain a RAID log — Risks, Assumptions, Issues, and Dependencies — for a project or program. Use when the user says "RAID log", "risk register", "track our risks/assumptions/issues/dependencies", "log a new risk", or needs a structured way to track and review threats and open items.
In this repository18 other files it gives its agents.
- capacity-planningSkill
- decision-logSkill
- dependency-mappingSkill
- escalationSkill
- estimation-sizingSkill
- exec-summarySkill
- launch-readinessSkill
- okr-trackingSkill
- postmortemSkill
- prd-reviewSkill
- program-health-dashboardSkill
- project-charterSkill
- release-notesSkill
- retrospectiveSkill
- roadmap-planningSkill
- sprint-planningSkill
- stakeholder-comms-planSkill
- status-reportSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
Use templates/raid-template.md.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
RAID Log
Build and maintain a RAID log: the running record of Risks, Assumptions, Issues, and Dependencies that could affect delivery.
Definitions (keep them distinct)
- Risk — something that might happen and would have impact. Has probability + impact + mitigation.
- Assumption — something taken as true without proof; becomes a risk if wrong. Track validation.
- Issue — a risk that has materialized, or a current problem. Needs an owner and resolution.
- Dependency — something you need from (or owe to) another team/vendor, with a date.
When to use
- Standing up risk tracking for a project, or adding/updating entries during delivery.
- Prepping a risk review or steering-committee section.
Process
- Classify each item into exactly one of R / A / I / D.
- For risks: score Probability (H/M/L) and Impact (H/M/L), derive severity, and give a mitigation + owner. Note a trigger/early warning if useful.
- For assumptions: note how/when it will be validated and the impact if false.
- For issues: capture impact, owner, target resolution date, and status.
- For dependencies: capture what, direction (we need / they need), owner on both sides, and needed-by date.
- Give every entry a stable ID, an owner, a status (Open/Mitigating/Closed), and a last-updated date. Sort by severity.
Output format
Use templates/raid-template.md. When updating an existing log, preserve IDs and show what changed.
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.