@floh-solutions/pharos-cli 0.17.0 → 0.17.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/package.json +3 -3
  2. package/skill/SKILL.md +14 -5
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@floh-solutions/pharos-cli",
3
- "version": "0.17.0",
3
+ "version": "0.17.1",
4
4
  "description": "Azure DevOps from a headless shell, for an agent: the whole context of a task in one call, and the wiki/comment verbs Microsoft's MCP server does not ship.",
5
5
  "license": "UNLICENSED",
6
6
  "author": "FLOH Solutions",
@@ -24,8 +24,8 @@
24
24
  "node": ">=22"
25
25
  },
26
26
  "dependencies": {
27
- "@floh-solutions/ado-core": "0.8.0",
28
- "@floh-solutions/plan-to-board": "0.1.1"
27
+ "@floh-solutions/plan-to-board": "0.1.1",
28
+ "@floh-solutions/ado-core": "0.8.0"
29
29
  },
30
30
  "devDependencies": {
31
31
  "@types/node": "^22.10.2",
package/skill/SKILL.md CHANGED
@@ -257,15 +257,24 @@ nobody here set up, so read a missing command as "find your own", not as a bug.
257
257
 
258
258
  | file | how |
259
259
  |---|---|
260
- | `.pdf` | `pdftotext -layout f.pdf -` — poppler; 40 KB of text with the table layout kept |
261
- | scanned `.pdf` | `pdftoppm -png -r 150 f.pdf page` → `page-01.png`, then look at the image |
260
+ | `.pdf` | `pdftotext -layout f.pdf -` — poppler; keeps the table layout |
261
+ | scanned `.pdf` | `pdftoppm -png -r 150 f.pdf page`, then look at the PNGs it wrote |
262
262
  | `.docx` | `soffice --headless --convert-to "txt:Text (encoded):UTF8" f.docx --outdir ./out` — LibreOffice; tables come out tab-separated |
263
+ | `.xlsx` | `soffice --headless --convert-to csv f.xlsx --outdir ./out` — **first sheet only**, so check whether the workbook has more |
263
264
  | `.pptx` | `~/.claude/skills/pptx/.venv/bin/python -m markitdown deck.pptx` — slide text, and it NAMES the embedded images without extracting them |
264
265
  | images in a `.pptx` | `unzip -o -q deck.pptx 'ppt/media/*' -d ./out` → `out/ppt/media/*.png` |
265
266
 
266
- `pandoc` is **not** installed here, whatever another skill's instructions say,
267
- and `markitdown` in that venv does `.pptx` onlyit went in without the
268
- `[docx]` and `[pdf]` extras and raises `MissingDependencyException` for both.
267
+ **Do not predict what `pdftoppm` names its output.** The page number is padded
268
+ to the width of the page COUNT, so a one-page scan which is what an attachment
269
+ usually is — gives `page-1.png` while a forty-page one gives `page-01.png`. List
270
+ the directory rather than guessing the name; a guessed name that is not there
271
+ reads as "the render failed" when it worked.
272
+
273
+ `pandoc` is **not** installed here, whatever another skill's instructions say.
274
+ `markitdown` in that venv does `.pptx` and nothing else: it went in without the
275
+ `[docx]`, `[pdf]` and `[xlsx]` extras and raises `MissingDependencyException`
276
+ for all three. That is why LibreOffice, not markitdown, is the line above for
277
+ everything except a deck.
269
278
 
270
279
  ## Mentioning somebody
271
280