user-impact
Skill2 starsChanged 4 months agoMITView on GitHub
Translate the technical discussion at hand into what a user will actually feel - use when the user asks what a change means for users, wants the UX framing of a technical decision, or needs to explain engineering work to a non-technical audience.
In this repository6 other files it gives its agents.
- add-eval-caseSkill
- defend-your-workSkill
- note-graduationSkill
- obsidian-captureSkill
- research-industry-patternsSkill
- writing-adrsSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 17
Keep the system number (p99, QPS, error rate) in parentheses only when the audience is mixed.
- Distinctive: line 18
Every felt moment names its technical cause, so the mapping survives a "why?" from either side of the room.
- Distinctive: line 24
When a change cannot be felt - a refactor, a cost saving, a risk reduction - say so plainly, and name who feels it instead: on-call, …
- Distinctive: line 29
Every technical item under discussion has either a felt moment or an invisible verdict - none skipped, none merged into a vague summary.
≈ “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
User impact
Translate the technical material already on the table - the diff, the design, the incident, the tradeoff - into what a person using the product will feel. Work only from what this conversation has established; a translation invented from a generic feature description defends nothing.
The felt moment
Render each technical fact as a felt moment: a specific person, mid-task, noticing something. "Checkout confirms in under a second instead of spinning" is a felt moment; "improved latency" is a label.
- Measure in human units: seconds waited, taps saved, retries avoided, errors seen, steps removed. Keep the system number (p99, QPS, error rate) in parentheses only when the audience is mixed.
- Every felt moment names its technical cause, so the mapping survives a "why?" from either side of the room.
- Rank the moments by how strongly they are felt, and lead with the strongest.
The invisible verdict
"Users feel nothing" is a real and valuable answer. When a change cannot be felt - a refactor, a cost saving, a risk reduction - say so plainly, and name who feels it instead: on-call, finance, future developers. Manufacturing a user benefit for invisible work is the failure this skill exists to prevent.
Done
Every technical item under discussion has either a felt moment or an invisible verdict - none skipped, none merged into a vague summary.
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.