super-ux 0.62.0 → 0.64.0
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/CHANGELOG.md +27 -0
- package/package.json +1 -1
- package/templates/test-panel.md +36 -0
package/CHANGELOG.md
CHANGED
|
@@ -1,3 +1,30 @@
|
|
|
1
|
+
## 0.64.0 (2026-10-22): the test panel, and a voice checker named by its tools
|
|
2
|
+
|
|
3
|
+
- **The test panel** (`templates/test-panel.md`, `ux-foundation` → *The test panel*): ten portraits the task-pipeline design-tester walks through the scenarios before and after a build, each with its basis (evidence or hypothesis), situation, goals, features, composite scenarios by SCR- id, activation funnel, retention loop and needs. A test instrument: it decides what to test, never what to build. Its gate is task-pipeline's `design_gate.py panel`.
|
|
4
|
+
- **`copywriting`** describes the optional tone-of-voice checker by its tools instead of a private product name.
|
|
5
|
+
|
|
6
|
+
## 0.63.0 (2026-10-20): short descriptions, triggers in the body
|
|
7
|
+
|
|
8
|
+
- **Every skill description is a router of 279 to 393 characters** (was 332 to
|
|
9
|
+
948). The operator's Claude Code skill listing measured 29,995 of about
|
|
10
|
+
30,000 characters for 134 skills, and 81 skills showed no description at
|
|
11
|
+
all; a plugin skill cannot be hidden, so length is the only lever. Each
|
|
12
|
+
description is one "Use when" sentence, four to six English and Russian
|
|
13
|
+
triggers, one "Not for" boundary naming the sibling, and the refusal
|
|
14
|
+
phrase where the route has one. Total for the seven skills: 4,426 to 2,436.
|
|
15
|
+
- **Every removed trigger phrase moved verbatim into a `## Triggers` section**
|
|
16
|
+
of its SKILL.md body, so the family routing hook's words still appear in the
|
|
17
|
+
skill's own text.
|
|
18
|
+
- **`ux-flows` Improve procedure moved to `references/flow-improve.md`**, text
|
|
19
|
+
unchanged apart from link paths, so the body stays inside the house audit's
|
|
20
|
+
4,750-token working limit with the new `## Triggers` section (4,712 tokens
|
|
21
|
+
before, 4,564 after).
|
|
22
|
+
- **Commands carry one short sentence each** (60 to 89 characters, was 99 to
|
|
23
|
+
224; total 2,424 to 1,116).
|
|
24
|
+
- **`validate.py` holds the budget:** a skill description over 500 characters
|
|
25
|
+
or without a "Not for" boundary fails, a command description over 120 fails,
|
|
26
|
+
and the trigger-position check reads `Triggers:` as well as `Triggers - `.
|
|
27
|
+
|
|
1
28
|
## 0.62.0 (2026-10-19): retrieval crawlers, the audit's brief, landing promises, Copylot sweep
|
|
2
29
|
|
|
3
30
|
- **`B050` judges retrieval agents only.** The AI-search contradiction is a block
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "super-ux",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.64.0",
|
|
4
4
|
"scripts": {
|
|
5
5
|
"test": "python3 test/validate.py && python3 test/brand_lint_test.py && python3 test/display_copy_test.py && python3 test/ux_lint_test.py && python3 docs/ux/lint.py && python3 docs/brand/lint.py && node test/installer_test.js && npm run test:audit",
|
|
6
6
|
"test:audit": "for t in test/audit_regressions/*.py; do python3 \"$t\" || exit 1; done"
|
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
# Test panel: <product>
|
|
2
|
+
|
|
3
|
+
Ten portraits the design-tester walks through the scenarios before and after a build
|
|
4
|
+
(task-pipeline `references/design-review.md`). A panel is a **test instrument**: it decides
|
|
5
|
+
what to test, never what to build. Each portrait says its basis: `evidence RE-NN` when the
|
|
6
|
+
research ledger supports it, `hypothesis` when it is a reasoned guess filling coverage.
|
|
7
|
+
|
|
8
|
+
Revision: <date> · confirmed by the operator: <yes/no> · foundation: `docs/ux/foundation.md`
|
|
9
|
+
|
|
10
|
+
Every portrait keeps these eight lines, in this form, so `design_gate.py panel` can read them.
|
|
11
|
+
|
|
12
|
+
## P-01 <short name>
|
|
13
|
+
|
|
14
|
+
- **basis**: evidence RE-01, RE-04 | hypothesis
|
|
15
|
+
- **situation**: <who, where, on what, under what pressure>
|
|
16
|
+
- **goals**: <the jobs they hire the product for, in their words>
|
|
17
|
+
- **features**: <the features they actually use, by name>
|
|
18
|
+
- **scenarios**: <two to four composite chains across features, by SCR- id: SCR-03 → SCR-07>
|
|
19
|
+
- **activation**: <steps to first value, and the step they are likely to drop at>
|
|
20
|
+
- **retention**: <trigger → action → reward → what brings them back, and what makes them leave>
|
|
21
|
+
- **needs**: <device and engine, locale, text size, accessibility, connection>
|
|
22
|
+
|
|
23
|
+
## P-02 <short name>
|
|
24
|
+
|
|
25
|
+
- **basis**: …
|
|
26
|
+
- **situation**: …
|
|
27
|
+
- **goals**: …
|
|
28
|
+
- **features**: …
|
|
29
|
+
- **scenarios**: …
|
|
30
|
+
- **activation**: …
|
|
31
|
+
- **retention**: …
|
|
32
|
+
- **needs**: …
|
|
33
|
+
|
|
34
|
+
<!-- … through P-10. Spread the ten across the foundation's personas, the activation stages
|
|
35
|
+
(new, activating, active, at risk, returning), and the needs that change a screen: small
|
|
36
|
+
phone, large text, keyboard only, a second locale, a slow connection. -->
|