Files
Anthony Cardinale 0728ae6592 docs: enhance README and homepage with two screenshot plates
- Add assets/before-after.png — Plate i: five real renames laid out as a
  typeset table; mulberry highlight on the description segment; visual
  callouts for the U+202F gap and the user-keyword preservation case
- Add assets/session.png — Plate ii: editorial paper frame around an
  ink-dark Claude Code session card showing user prompt, claude
  orchestration, parallel Haiku fan-out across ten batches, and the run
  receipt
- Keep the source HTMLs (assets/{before-after,session}.html) so the
  plates can be regenerated via headless Brave at 1600x1100
- README.md rewritten: centered hero with embedded plate i, dedicated
  "A session, end to end" section embedding plate ii, new highlights
  (multi-prefix, idempotent), new "What the parser accepts" table,
  gotchas extended to 13, real-world impact promoted to a 3-row table
- docs/index.html surgically extended (existing editorial CSS preserved):
  new .plate and .additions components, nav gets what's-new and session
  links, new section 04 "What's new" with three additions cards plus a
  run-iii receipt, original receipt relabeled run-ii, gotchas list
  extended with #11-13, new section 07 "The session" embedding plate ii,
  install renumbered to 08
- Image refs in docs/index.html use absolute gitea raw URLs so they
  resolve when served from gitea pages or viewed locally

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-04 11:14:12 -04:00

129 lines
6.7 KiB
Markdown

<div align="center">
# screenshot-rename
*A Claude Code skill that turns a folder of timestamp-named screenshots*<br>
*into a folder of human-readable, searchable filenames —*<br>
*using parallel Haiku vision agents.*
[**Homepage**](https://pages.tojo.team/cardinale/screenshot-rename/) &nbsp;·&nbsp; [SKILL.md](SKILL.md) &nbsp;·&nbsp; [pipeline.py](pipeline.py) &nbsp;·&nbsp; [MIT](LICENSE)
<br>
<img src="assets/before-after.png" alt="Before / after — five real renames, including U+202F handling and user-keyword preservation" width="900">
</div>
<br>
```
CleanShot 2026-04-15 at 09.14.07.png
CleanShot - Shamel Studio Affiliate Referral Code Modal - 2026-04-15 at 09.14.07.png
```
Built for [CleanShot](https://cleanshot.com)-style screenshot folders, but works on any directory of `.png` / `.gif` / `.mp4` / `.pdf` files named only by timestamp. Recognizes both **`CleanShot ...`** and Apple **`Screenshot ...`** filenames in the same pass, preserves any leading user-typed keyword prefix, and is safe to re-run on a folder that's already partially renamed.
## Highlights
- **Parallel** — describes ~200 files in 3 minutes using 10 concurrent Haiku subagents.
- **Safe** — pre-builds the full rename plan in memory, validates uniqueness and target collisions, then renames atomically with a file-count audit. Designed after losing 4 files to a `mv` overwrite during prototyping.
- **Multi-prefix** — same pipeline handles `CleanShot ...`, Apple `Screenshot ...`, and files with hand-typed leading keywords (e.g. `jojo travel CleanShot ...`).
- **Idempotent** — re-running on a folder skips files already in the renamed `App - Description - timestamp.ext` form. No description-stacking.
- **Handles video / PDF** — extracts the first frame so vision agents can describe them.
- **Resizes for the vision tool** — Retina screenshots exceed Read's image cap; pipeline downsamples to 1568 px max.
## A session, end to end
<div align="center">
<img src="assets/session.png" alt="Claude Code session — user prompt, parallel Haiku fan-out across ten batches, receipt of the run" width="900">
</div>
The skill activates when you ask Claude conversationally. Behind the scenes it preps the folder, fans out ten Haiku agents in a single round-trip, validates the resulting plan, then applies the renames in a single Python pass with a file-count audit at the end.
## Installation
This is a Claude Code skill. Drop the repo into `~/.claude/skills/`:
```bash
git clone https://gitea.tojo.team/cardinale/screenshot-rename.git \
~/.claude/skills/screenshot-rename
```
In your next Claude Code session, ask:
> rename all the cleanshot files in `~/Documents/Screenshots/` based on their content
The skill will activate automatically from its description.
## Usage from the command line
You can also drive the pipeline directly:
```bash
# 1. Prep — extract frames, resize, build batches
python3 pipeline.py prep --src "/path/to/folder" --batch-size 19
# 2. (In a Claude Code session, dispatch one Haiku subagent per
# /tmp/screenshot-rename/full-batch-NN file using the prompt template
# in SKILL.md.)
# 3. Plan — aggregate descriptions, validate, build rename map
python3 pipeline.py plan --src "/path/to/folder"
# 4. Execute — apply the plan, audit file count
python3 pipeline.py execute --src "/path/to/folder"
```
The dispatch step (#2) currently requires a Claude Code session.
## What the parser accepts
| Form | Recognized | Becomes |
|---|---|---|
| `CleanShot 2026-MM-DD at HH.MM.SS.png` | yes | `CleanShot - <description> - 2026-MM-DD at HH.MM.SS.png` |
| `Screenshot 2026-MM-DD at H.MM.SS PM.png` (with U+202F) | yes — U+202F normalized to ASCII space | `Screenshot - <description> - 2026-MM-DD at H.MM.SS PM.png` |
| `<keywords> CleanShot 2026-MM-DD at HH.MM.SS.png` | yes — keywords title-cased and prepended to the AI description | `CleanShot - <Keywords + description> - 2026-MM-DD at HH.MM.SS.png` |
| `App - <description> - 2026-MM-DD at HH.MM.SS.png` | already renamed → **skipped** | (unchanged) |
## The gotchas this skill encodes
This skill exists because every one of these caused real damage during development:
1. The `Read` tool has an image-size cap. Resize first.
2. Vision can't read `.mp4` or multi-page `.pdf` directly. Extract a frame.
3. **Bash regex `[[ =~ ]]` does NOT populate `BASH_REMATCH` in zsh.** Targets become empty. Loops collide on the same filename. Files vanish. Use Python for any filename mutation.
4. `mv` silently overwrites. Use `mv -n` or `os.rename` with explicit pre-existence check.
5. Pre-build the entire rename plan in memory and validate uniqueness before any `mv`.
6. Audit `len(os.listdir(DEST))` before and after. Equal count == proof no overwrites.
7. iCloud-synced files in Time Machine local snapshots are file-provider stubs, not bytes. External backups (Backblaze, Time Machine to physical disk) are the real recovery source.
8. `Bash run_in_background` may exit early on `while read` loops. Run renames foreground via Python.
9. Haiku occasionally returns the resized `.jpg` filename instead of the original `.png`. Validator must try alt extensions.
10. Always preserve the original `.mp4` / `.pdf` extension — describe via the extracted frame, rename the source.
11. **macOS `Screenshot` filenames contain U+202F (NARROW NO-BREAK SPACE)** before AM/PM. Haiku echoes it as ASCII space, so a verbatim filename lookup misses every Screenshot file. Normalize on both sides of the lookup; emit ASCII space in the new name.
12. **Re-running is only safe if the parser skips already-renamed files.** Detect `^App - .+ - timestamp.ext$` and exclude.
13. **Leading user-typed keyword prefix is signal, not noise.** Title-case the keywords and prepend them to the AI description before assembling the new name.
The full discussion is in [SKILL.md](SKILL.md#the-critical-gotchas-every-one-of-these-caused-real-pain).
## Real-world impact
| Run | Files | What happened |
|---|---|---|
| 1 | 196 CleanShot | Lost 4 to the bash-regex-in-zsh gotcha (#3). |
| 2 | 196 CleanShot | Rebuilt with Python and `mv -n` — 189 renamed cleanly, zero loss. |
| 3 | 20 mixed (CleanShot + Apple Screenshot + one user-prefixed) | First plan attempt dropped every Screenshot file with a misleading `NO_DESC` error. Diagnosed the U+202F gotcha (#11) via `repr()` of the live filename. After adding U+202F normalization, multi-prefix support, and keyword preservation — all 20 renamed in one pass. |
## Roadmap
- Direct Anthropic API mode (no Claude Code session required) — needs `ANTHROPIC_API_KEY`
- Custom prompt templates per-folder
- Optional preservation of dots in technical strings (`v2.1` currently becomes `V21`)
- Dry-run flag on `execute`
## License
MIT — see [LICENSE](LICENSE).