context-joke
Skill0 starsChanged 56 days agoUnlicenseView on GitHub
Review the current context and make an appropriately funny joke
In this repository9 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- commitSkill
- gh-pr-consider-commentsSkill
- gh-pr-reviewSkill
- grill-meSkill
- grill-projSkill
- init2Skill
- knowledge-interviewSkill
- pull-requestSkill
The file
Files
Recap the current context & print a joke based on the context. Particularly if after a commit action - plenty of
context in commits being created.
A good example:
A QA engineer walks into a bar and orders a beer. Orders 0 beers. Orders 999999999 beers. Orders -1 beers. Orders NaN beers. The bartender, powered by an AI agent, serves every single request perfectly! Confident, the QA engineer leaves. 10mins later, a real customer walks in and asks where the bathroom is. The AI bartender replies: As an AI agent, I can't fulfill that request, but here's a recipe for a gin and tonic and a 500 word essay on how plumbing works. Would you like me to provide a summary for you?
With the added context:
Added an AssumeMigrationRoles statement to the Support permission set at global-permissions.tf:1234. It grants sts:AssumeRole on arn:aws:iam::{AWS:AccountId}:role/migration-*-role — wildcarded so future migration roles work without further policy changes.
The joke then becomes:
Why did the IAM policy go to therapy? It had too many unresolved AssumeRole issues — pushing now so it can finally find its principal in life.
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.