kyle/sift
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

skill: confirm numbers and counts from a digest with --grep; the question refusal is now only past 5000 chunks

Browse Source 
Found in the P5b prod check: "how many PIO state machines in total?" on the RP2040 datasheet
came back 4 (bm25 and hybrid); the answer, 8, is a terse bullet on p. 9 that --grep finds at once.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
kyle
2026-09-26 20:33:19 -07:00
co-authored by Claude Opus 5.5
parent bdc093ee02
commit 94da9d9127
1 changed files with 6 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skill/SKILL.md
+6 -3
View File
@@ -66,11 +66,14 @@ long one comes back as a map — an outline with page numbers, then the first pa
- `sift fetch URL --pages 41-60` for a page range, `--grep 'pattern'` for matching lines, or - `sift fetch URL --pages 41-60` for a page range, `--grep 'pattern'` for matching lines, or
`--question "…"` for a digest that cites each fact as `(p. N)`; `--question` works on long `--question "…"` for a digest that cites each fact as `(p. N)`; `--question` works on long
PDFs, and the first answer may be `bm25` (lexical) — ask again later for a sharper one. PDFs, and the first answer may be `bm25` (lexical) — ask again later for a sharper one.
- A digest reads only the ~5 passages that looked most relevant, so it can miss a fact that
sits in a terse list elsewhere (a feature summary, a spec table). **Before you rely on a
number, a count or a spec from a digest, confirm it with `--grep`** and quote that line.
- Scanned PDFs have no text layer: sift reports `no text layer (scanned PDF?)` — point it at an - Scanned PDFs have no text layer: sift reports `no text layer (scanned PDF?)` — point it at an
OCR source rather than trying to fix it here. OCR source rather than trying to fix it here.
- A range returns at most 100 pages and grep at most 100 matches. On a very long document - A range returns at most 100 pages and grep at most 100 matches. On an extremely long document
`--question` is refused with `document too long for question (N chunks); use grep or pages` — (over 5000 chunks) `--question` is refused with `document too long for question (N chunks);
do that: `--grep` for the terms, then `--pages` around the hits. use grep or pages` — do that: `--grep` for the terms, then `--pages` around the hits.
Never download a PDF and run `pdftotext` yourself; `sift` is the sanctioned extractor. Never download a PDF and run `pdftotext` yourself; `sift` is the sanctioned extractor.