@pmelab/gtd 10.11.0 → 11.0.0
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.
- package/README.md +8 -20
- package/dist/gtd.bundle.mjs +3 -45
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -287,17 +287,8 @@ noted in steps 2, 3, and 4 below.
|
|
|
287
287
|
thing should do first, then how it should be built, and hands you a file with
|
|
288
288
|
its open questions in it at either point. Answer them in your editor, in the
|
|
289
289
|
file, and start the loop again. Leave the file untouched and start the loop
|
|
290
|
-
instead to accept the plan as-is, unanswered questions and all.
|
|
291
|
-
|
|
292
|
-
- Each open question, on what-it-should-do first and how-it-should-be-built
|
|
293
|
-
second: would a wrong assumption here cost a whole rebuild, or is a
|
|
294
|
-
confident default safe to infer and tick in for you? The first floor is
|
|
295
|
-
strict (a wrong guess about what you want is expensive); the second is
|
|
296
|
-
permissive (a wrong technical call is still caught later, in review) — the
|
|
297
|
-
same judged stop, tuned differently depending on which question it's
|
|
298
|
-
answering. Confident enough on both, with a specific answer picked from the
|
|
299
|
-
question's own options, skips it entirely; any doubt still stops and hands
|
|
300
|
-
you the file.
|
|
290
|
+
instead to accept the plan as-is, unanswered questions and all. One point
|
|
291
|
+
along this phase is judged rather than always asking you outright:
|
|
301
292
|
- Before the how-it-should-be-built pass starts: does this plan actually need
|
|
302
293
|
one? A confident no skips it — and the review it would have raised — going
|
|
303
294
|
straight from your answers to a single built package, with no technical
|
|
@@ -329,15 +320,12 @@ noted in steps 2, 3, and 4 below.
|
|
|
329
320
|
other question.
|
|
330
321
|
|
|
331
322
|
4. **You review.** You get a review document listing what changed and what to
|
|
332
|
-
look at
|
|
333
|
-
|
|
334
|
-
|
|
335
|
-
|
|
336
|
-
|
|
337
|
-
|
|
338
|
-
you leave a comment, is it actionable, or just approval? Confident it's
|
|
339
|
-
approval-only skips the replan and signs off directly — the same
|
|
340
|
-
`gtd judge answer` / conservative-default shape as step 3's own judged
|
|
323
|
+
look at. Tick the boxes to approve, or write what is wrong. Approving ends
|
|
324
|
+
the process; feedback sends it back to step 2 for a fresh plan — it never
|
|
325
|
+
patches over a design you rejected. One more judged point sits on that
|
|
326
|
+
feedback path: after you leave a comment, is it actionable, or just approval?
|
|
327
|
+
Confident it's approval-only skips the replan and signs off directly — the
|
|
328
|
+
same `gtd judge answer` / conservative-default shape as step 3's own judged
|
|
341
329
|
points.
|
|
342
330
|
|
|
343
331
|
You never talk to it. Every exchange is a file in `.gtd/` that you edit in your
|