product-question-tldr
Skill2 starsChanged 36 days agoMITView on GitHub
Answer a product question via /product-question, then boil the answer down to an ELI18 TLDR — one plain-English takeaway an 18-year-old would get instantly
In this repository75 other files it gives its agents.
- acceptance-criteriaSkill
- architect-guideSkill
- architect-reviewSkill
- audit-fixerSkill
- avo-admin-expertSkill
- backend-services-expertSkill
- bug-hunt-allSkill
- bug-hunt-fixSkill
- bug-huntSkill
- build-feature-remoteSkill
- build-featureSkill
- codeSkill
- component-testSkill
- controller-expertSkill
- create-qa-documentSkill
- debugSkill
- devops-expertSkill
- execute-qaSkill
- feature-qaSkill
- fix-bug-indexSkill
- fix-honeybadgerSkill
- fix-spec-bugsSkill
- fix-system-testSkill
- frontend-expertSkill
- frontend-reviewSkill
- full-qa-fixSkill
- full-qaSkill
- full-reviewSkill
- green-ciSkill
- group-issuesSkill
- honeybadger-auditSkill
- ideateSkill
- impact-assessmentSkill
- improveSkill
- merge-mainSkill
- model-expertSkill
- model-testSkill
- native-bug-hunt-fixSkill
- native-bug-huntSkill
- page-speedSkill
- plan-questionsSkill
- planSkill
- plan-system-testsSkill
- policy-testSkill
- prdSkill
- prd-worktreeSkill
- product-questionSkill
- qa-branchSkill
- qa-testerSkill
- refactor-sweepSkill
- resolve-honeybadgerSkill
- resolve-issueSkill
- resolve-issuesSkill
- review-acceptance-criteriaSkill
- review-fixesSkill
- review-railsSkill
- rspec-test-expertSkill
- scale-reviewSkill
- service-testSkill
- settle-pr-reviewSkill
- The first 60 shown.
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 20
One or two sentences, max: If you need a third sentence, you haven't found the point yet.
- Distinctive: line 22
Use a relatable frame when it helps: "like getting a receipt," "like a subscription that retries your card."
- Distinctive: line 23
Keep it honest: the TLDR must not oversimplify into being wrong.
- Distinctive: line 24
If the code doesn't do the thing, the TLDR says so plainly: "The app doesn't do this."
≈ “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
Product Question TLDR
Answer this product question, then give the TLDR: "${1:the user's question}"
How this works
This skill runs in two steps:
- Get the real answer. Invoke the
product-questionskill (via the Skill tool) with the same question, and follow its instructions fully: answer exclusively from the code (never docs), verify behavior end-to-end, and produce its normal short, plain-language answer. - Boil it down to an ELI18 TLDR. Take that answer and compress it into a takeaway a smart 18-year-old with zero healthcare, billing, or software background would understand on first read.
TLDR rules
- One or two sentences, max. If you need a third sentence, you haven't found the point yet.
- Everyday words only. No industry terms — no "eligibility check," "ERA," "claim adjudication," "ledger," "portal" — unless you translate them in place ("the insurance company's answer about what they'll pay").
- Use a relatable frame when it helps: "like getting a receipt," "like a subscription that retries your card."
- Keep it honest: the TLDR must not oversimplify into being wrong. If the full answer has one exception that changes the story, fold it in with a short "unless…" clause; otherwise drop edge cases entirely.
- If the code doesn't do the thing, the TLDR says so plainly: "The app doesn't do this."
Output format
**Answer:** <the full /product-question answer, unchanged>
**TLDR (ELI18):** <the one-to-two-sentence plain-English takeaway>Example
Q: "What happens when a client misses a payment?"
Answer: "Nothing automatic happens on a missed payment itself — the invoice just stays unpaid. Each night the system retries charging any unpaid invoices against the client's saved card, and if a charge fails, the biller sees it flagged on the client's ledger. Clients are not notified of failed charges."
TLDR (ELI18): "It's like a subscription that quietly retries your card every night until it goes through — the client never hears about failed charges, but the billing staff sees them flagged."
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.

