user-action-edge-cases
Skill2 starsChanged 4 months agoMITView on GitHub
Use when finishing anything that depends on external state a person controls - a file, a record, a folder.
In this repository19 other files it gives its agents.
- build-release-mindsetSkill
- critical-thinkingSkill
- de-ai-proseSkill
- entry-point-auditSkill
- feasibility-guardSkill
- fix-in-the-shared-layerSkill
- fix-the-root-causeSkill
- independent-review-gateSkill
- logging-for-remote-diagnosisSkill
- no-duplicate-logicSkill
- opportunistic-fixesSkill
- performance-at-scaleSkill
- plan-with-teethSkill
- project-onto-all-systemsSkill
- question-the-premiseSkill
- tests-with-teethSkill
- using-instinctsSkill
- ux-designer-mindsetSkill
- verify-against-codeSkill
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 18
Prefer finding things by type or id over a hardcoded path or name.
≈ “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
The rule
Anything you depend on that a user can touch will get renamed, moved, deleted, and duplicated. If your code assumes a fixed path or a single copy, it breaks the first time the user does something ordinary. Before you finish, run those four actions through your head.
Fires when
Your code reads, writes, or depends on a file, a record, a document, or any state the user can edit outside your code.
How to apply
For each thing you depend on, ask the four questions: renamed? moved? deleted? duplicated?
Prefer finding things by type or id over a hardcoded path or name. Decide what happens in each case instead of assuming it won't happen.
Worked example
Your app stores its settings in a file at a hardcoded path. It works on your machine. Then a user renames the file, and the app silently writes a fresh one with defaults, losing their config. Or they copy the project folder, and now two copies fight over the same path. Looking the file up by a stable marker instead of a fixed name, and handling "not found" and "more than one" on purpose, turns four silent bugs into defined behavior.
Red flags
| Thought | Reality |
| "The file is always at this path" | Until the user moves it. |
| "There's only ever one" | Until they duplicate it. |
| "They won't rename it" | They will. |
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.