celestial-skills / requirements-interview-engineering
AGENTS.md1 starsChanged 18 days agoApache-2.0View on GitHub
Turn a vague request into a confirmed plan by asking one decision-changing question at a time with a recommended default, so nothing gets built on a guess. Generated from the Celestial engineering practice “Requirements interview”.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository182 other files it gives its agents.
- skills/accessibility-audit-engineering/AGENTS.mdAGENTS.md
- skills/angular-app-engineering/AGENTS.mdAGENTS.md
- skills/aspnet-core-api-engineering/AGENTS.mdAGENTS.md
- skills/chrome-extension-engineering/AGENTS.mdAGENTS.md
- skills/ci-cd-pipelines-engineering/AGENTS.mdAGENTS.md
- skills/code-review-engineering/AGENTS.mdAGENTS.md
- skills/compose-android-app-engineering/AGENTS.mdAGENTS.md
- skills/context-engineering-engineering/AGENTS.mdAGENTS.md
- skills/database-migrations-engineering/AGENTS.mdAGENTS.md
- skills/dbt-analytics-engineering/AGENTS.mdAGENTS.md
- skills/dependency-supply-chain-engineering/AGENTS.mdAGENTS.md
- skills/deprecation-and-removal-engineering/AGENTS.mdAGENTS.md
- skills/design-tokens-to-code-engineering/AGENTS.mdAGENTS.md
- skills/django-app-engineering/AGENTS.mdAGENTS.md
- skills/end-to-end-testing-engineering/AGENTS.mdAGENTS.md
- skills/expo-react-native-app-engineering/AGENTS.mdAGENTS.md
- skills/fastapi-service-engineering/AGENTS.mdAGENTS.md
- skills/fastify-api-engineering/AGENTS.mdAGENTS.md
- skills/feature-flags-engineering/AGENTS.mdAGENTS.md
- skills/flutter-app-engineering/AGENTS.mdAGENTS.md
- skills/framework-upgrades-engineering/AGENTS.mdAGENTS.md
- skills/git-workflow-engineering/AGENTS.mdAGENTS.md
- skills/go-http-service-engineering/AGENTS.mdAGENTS.md
- skills/graphql-api-engineering/AGENTS.mdAGENTS.md
- skills/incident-response-engineering/AGENTS.mdAGENTS.md
- skills/incremental-implementation-engineering/AGENTS.mdAGENTS.md
- skills/internationalisation-engineering/AGENTS.mdAGENTS.md
- skills/kubernetes-helm-engineering/AGENTS.mdAGENTS.md
- skills/laravel-app-engineering/AGENTS.mdAGENTS.md
- skills/launch-readiness-engineering/AGENTS.mdAGENTS.md
- skills/llm-features-and-evals-engineering/AGENTS.mdAGENTS.md
- skills/marketing-site-engineering/AGENTS.mdAGENTS.md
- skills/nestjs-service-engineering/AGENTS.mdAGENTS.md
- skills/nextjs-app-engineering/AGENTS.mdAGENTS.md
- skills/nuxt-app-engineering/AGENTS.mdAGENTS.md
- skills/observability-engineering/AGENTS.mdAGENTS.md
- skills/privacy-by-design-engineering/AGENTS.mdAGENTS.md
- skills/python-ml-service-engineering/AGENTS.mdAGENTS.md
- skills/rails-app-engineering/AGENTS.mdAGENTS.md
- skills/react-web-app-engineering/AGENTS.mdAGENTS.md
- skills/release-and-versioning-engineering/AGENTS.mdAGENTS.md
- skills/rest-api-design-engineering/AGENTS.mdAGENTS.md
- skills/rust-axum-service-engineering/AGENTS.mdAGENTS.md
- skills/rust-cli-tool-engineering/AGENTS.mdAGENTS.md
- skills/safe-refactoring-engineering/AGENTS.mdAGENTS.md
- skills/secure-code-review-engineering/AGENTS.mdAGENTS.md
- skills/source-grounded-development-engineering/AGENTS.mdAGENTS.md
- skills/spec-before-code-engineering/AGENTS.mdAGENTS.md
- skills/spec-driven-development-engineering/AGENTS.mdAGENTS.md
- skills/spring-boot-service-engineering/AGENTS.mdAGENTS.md
- skills/sveltekit-app-engineering/AGENTS.mdAGENTS.md
- skills/swiftui-ios-app-engineering/AGENTS.mdAGENTS.md
- skills/systematic-debugging-engineering/AGENTS.mdAGENTS.md
- skills/task-breakdown-engineering/AGENTS.mdAGENTS.md
- skills/tauri-desktop-app-engineering/AGENTS.mdAGENTS.md
- skills/technical-documentation-engineering/AGENTS.mdAGENTS.md
- skills/terraform-infrastructure-engineering/AGENTS.mdAGENTS.md
- skills/test-first-development-engineering/AGENTS.mdAGENTS.md
- skills/threat-modelling-engineering/AGENTS.mdAGENTS.md
- skills/typescript-library-engineering/AGENTS.mdAGENTS.md
- The first 60 shown.
The file
We split this AGENTS.md 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 23
Ask exactly one question per message and wait for the answer.
- Distinctive: line 25
Do not start building until the summary is confirmed.
- Distinctive: line 26
Ask about data ownership, retention and migrations before any UI detail.
- Distinctive: line 27
Ask who may see and change each new piece of data when the request touches permissions or personal data.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md — Requirements interview
Turn a vague request into a confirmed plan by asking one decision-changing question at a time with a recommended default, so nothing gets built on a guess.
How to do it
- List the unknowns — Read the request and write down every gap: users, inputs, outputs, scale, constraints, edge cases, deadlines. Check the code, issue history and docs first so you only ask what they cannot answer.
- Rank by impact — Order the unknowns by how much each answer would change the plan. Questions about scope, data shape and irreversible choices go first; naming and styling go last or become defaults.
- Ask one question — Ask the top question alone, in plain words, with two to four concrete options and your recommended default marked with a one-line reason. Wait for the answer before asking the next.
- Adjust the list — After each answer, drop questions it made irrelevant and re-rank the rest. New unknowns raised by the answer join the list in their impact order.
- Stop at diminishing returns — Stop asking when no remaining answer would change the approach, the scope or the estimate. Turn the rest into stated assumptions with your defaults.
- Play back the summary — Write a short summary: goal, users, in scope, out of scope, decisions with their answers, assumptions. Ask for an explicit yes or corrections before any build starts.
- Record the decisions — Save the confirmed summary where the work is tracked (issue, spec or decision log) and link it from the pull request, so later readers see what was agreed and why.
Checklist (before a pull request)
- Only questions the code and docs could not answer were asked
- Questions were asked one at a time, highest impact first
- Each question offered options and a recommended default
- Remaining unknowns are written down as assumptions
- The requester confirmed the summary before building began
- Decisions are recorded in the issue, spec or decision log
Rules
- Ask exactly one question per message and wait for the answer. (A batch of questions gets partial answers and the most important one is often skipped.)
- Attach a recommended default and its reason to every question. (It lets the requester answer with a single word and shows your reasoning.)
- Do not start building until the summary is confirmed. (Code written before agreement anchors everyone on the first guess.)
- Ask about data ownership, retention and migrations before any UI detail. (Data decisions are the most expensive to reverse.)
- Ask who may see and change each new piece of data when the request touches permissions or personal data. (Access rules left implicit end up decided by accident in code.)
Checks
| Gate | Tool | Threshold | When |
| Decisions recorded | Issue or pull request template check | Work that began as an underspecified request links a confirmed summary with decisions and assumptions | Before the first commit and on the pull request |
Generated from the Celestial engineering practice “Requirements interview”.
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.

