Loading prompt…
Turns a project idea into a complete scaffold: a summary, build steps, directory structure, the purpose of each file, commented source for every file, a setup script and a README.
Version 1 · 3 variables · 2 required
Fill in the values below — the customized prompt updates as you type. marks a required value.
What the project should do. Narrow and concrete beats broad and ambitious.
Language, runtime and any framework you want used. Say 'your choice, explain why' to leave it open.
Hard limits and things to deliberately leave out: no database, standard library only, must run offline, target version.
Fill in Project idea, Stack or language to copy the customized prompt.
PROJECT:
A command-line tool that watches a directory and mirrors changed files into an S3 bucket continuously.
SUMMARY:
A watcher process observes filesystem events under a root directory. Each create or modify event is debounced, then handed to a worker that uploads the file to S3 under a key mirroring its relative path. A small JSON state file records the last-uploaded hash per path so a restart does not re-upload unchanged files.
STEPS:
1. Install dependencies and configure AWS credentials in the environment.
2. Create a config file naming the watch root and bucket.Showing all 1 public result on version 1.
PROJECT:
A command-line tool that watches a directory and mirrors changed files into an S3 bucket continuously.
SUMMARY:
A watcher process observes filesystem events under a root directory. Each create or modify event is debounced, then handed to a worker that uploads the file to S3 under a key mirroring its relative path. A small JSON state file records the last-uploaded hash per path so a restart does not re-upload unchanged files.
STEPS:
1. Install dependencies and configure AWS credentials in the environment.
2. Create a config file naming the watch root and bucket.
3. Run the watcher; it performs one reconciling pass, then streams changes.
4. Stop with Ctrl-C; in-flight uploads finish before exit.
STRUCTURE:
```
filesync/
README.md
pyproject.toml
src/filesync/
__init__.py
cli.py
watcher.py
uploader.py
state.py
tests/
test_state.py
```
DETAILED EXPLANATION:
- `cli.py`: parses arguments, loads config, wires the watcher to the uploader.
- `watcher.py`: wraps watchdog, debounces rapid events into a single upload.
- `uploader.py`: computes the S3 key, uploads, retries with backoff.
- `state.py`: reads and atomically writes the hash-per-path JSON file.
CODE:
Contributor notes: Illustrative example — not an actual model run. Written to show the shape of a good answer so the prompt can be judged before you spend a call on it. Attribution: adapted from https://github.com/danielmiessler/fabric by danielmiessler, licensed MIT. Source file: https://github.com/danielmiessler/fabric/blob/main/data/patterns/create_coding_project/system.md
1 public result from 1 model
Reports go to moderators and are never shown publicly.
fix(auth)!: reject refresh tokens issued before a password change Refresh tokens were validated only against their signature and expiry, so a token minted before a password reset stayed usable for its full thirty-day lifetime. Anyone holding a captured token kept access after the account owner rotated their credentials, which is precisely the scenario a password reset is meant to close. The user row now carries credentials_changed_at, and verifyRefreshToken compares the token's iat claim again
Generates a Conventional Commits message from a diff or a plain description, picking the right type and scope, using imperative mood, and flagging breaking changes correctly.
**Summary** Rate limiting for the public search endpoint moves from a per-process in-memory counter to a shared Redis counter, so the limit now applies across all application instances rather than per instance. **Files Changed** - `src/middleware/rate_limit.py` — replaces the module-level `defaultdict` with a Redis-backed sliding window. - `src/config.py` — adds `REDIS_URL` and `SEARCH_RATE_LIMIT_PER_MINUTE`, both required at startup. - `tests/test_rate_limit.py` — new tests covering the wind
Turns raw git diff output into a structured PR description covering summary, files changed, significant code, reasoning, project impact, a test plan and reviewer notes.
### Overall Assessment The function's intent is immediately obvious, which is a real strength — nobody will misread what it returns. Its two weaknesses are both structural rather than cosmetic: it issues one database round trip per user, and it raises an unhandled exception the first time an id has no matching row. ### Prioritized Recommendations 1. Replace the per-id query with a single `IN` query to eliminate the N+1 pattern. 2. Decide explicitly what should happen when a user id has no row
Reviews a snippet or diff across correctness, security, performance, readability, idiom and error handling, then returns prioritized fixes with before/after code and a rationale for each.
Oldest first · one level of replies
Sign in to join the discussion. Share what you learned or made with this prompt.
No comments yet
Be the first to share how this prompt worked for you.