@oneie/claude 0.3.2 → 0.4.0
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/agents/w1-recon.md +9 -2
- package/agents/w2-decide.md +40 -9
- package/agents/w3-edit.md +34 -4
- package/agents/w4-verify.md +112 -15
- package/commands/do-autonomous.md +1 -1
- package/commands/do.md +84 -46
- package/commands/skill-create.md +4 -4
- package/commands/sync.md +7 -7
- package/hooks/scripts/stop-reflect.sh +3 -3
- package/hooks/scripts/sync-todo-docs.sh +1 -1
- package/package.json +2 -1
- package/rules/documentation.md +18 -18
- package/rules/engine.md +2 -2
- package/scripts/do-auto.sh +5 -5
- package/scripts/do-folder.sh +1 -1
- package/scripts/do-prove.sh +10 -27
- package/scripts/do-reconcile.sh +212 -19
- package/scripts/do-smoke.sh +65 -25
- package/scripts/do-survey.sh +1 -1
- package/scripts/do-tier.sh +1 -1
- package/scripts/w4-rubric.ts +1 -1
- package/skills/oneie/SKILL.md +4 -4
- package/skills/signal/SKILL.md +2 -2
- package/skills/sui/SKILL.md +1 -1
- package/templates/template-agent.md +50 -0
- package/templates/template-feature.md +27 -0
- package/templates/template-plan.md +75 -0
- package/templates/template-teach.md +59 -0
- package/templates/template-tests.md +43 -0
- package/templates/template-todo.md +781 -0
|
@@ -0,0 +1,59 @@
|
|
|
1
|
+
---
|
|
2
|
+
slug: {{slug}}
|
|
3
|
+
written: {{YYYY-MM-DD}}
|
|
4
|
+
proven: true
|
|
5
|
+
promise: text/{{slug}}.md
|
|
6
|
+
---
|
|
7
|
+
|
|
8
|
+
# {{Feature Name}}
|
|
9
|
+
|
|
10
|
+
> Written after PROVE passes. Describes behavior that exists, not behavior that is planned.
|
|
11
|
+
> The promise (`text/{{slug}}.md`) is what this doc must match.
|
|
12
|
+
|
|
13
|
+
## What it does
|
|
14
|
+
|
|
15
|
+
{{1–3 sentences. What the user/operator gets. Every claim here must be in the proven behavior.}}
|
|
16
|
+
|
|
17
|
+
## How to use it
|
|
18
|
+
|
|
19
|
+
{{The golden path. Step-by-step. Present tense. Tested commands only.}}
|
|
20
|
+
|
|
21
|
+
```bash
|
|
22
|
+
# Example — copy-pasteable, verified to work
|
|
23
|
+
```
|
|
24
|
+
|
|
25
|
+
## Reference
|
|
26
|
+
|
|
27
|
+
| Concept | Where |
|
|
28
|
+
|---------|-------|
|
|
29
|
+
| {{name}} | {{`file:line` or section link}} |
|
|
30
|
+
| Script | `.claude/scripts/{{relevant-script}}.sh` |
|
|
31
|
+
| Template | `text/template-{{template}}.md` |
|
|
32
|
+
|
|
33
|
+
---
|
|
34
|
+
|
|
35
|
+
## Runbook
|
|
36
|
+
|
|
37
|
+
### Verify it's working
|
|
38
|
+
|
|
39
|
+
```bash
|
|
40
|
+
# The proof command from the PROVE step — still valid as a health check
|
|
41
|
+
```
|
|
42
|
+
|
|
43
|
+
### Common issues
|
|
44
|
+
|
|
45
|
+
| Symptom | Cause | Fix |
|
|
46
|
+
|---------|-------|-----|
|
|
47
|
+
| {{symptom}} | {{cause}} | {{fix}} |
|
|
48
|
+
|
|
49
|
+
### Rollback
|
|
50
|
+
|
|
51
|
+
{{What to undo if this needs to be reverted. Specific commands, not vague guidance.}}
|
|
52
|
+
|
|
53
|
+
<!--
|
|
54
|
+
TEACH stop rules (from do.md):
|
|
55
|
+
- Write AFTER PROVE passes (proven: true in frontmatter marks this)
|
|
56
|
+
- Match the promise: every user-facing claim must appear in text/{{slug}}.md
|
|
57
|
+
- Doc + runbook in one file; presence check is: test -f text/{{slug}}-doc.md
|
|
58
|
+
- do-reconcile.sh dictionary on this file before committing (no dead names)
|
|
59
|
+
-->
|
|
@@ -0,0 +1,43 @@
|
|
|
1
|
+
---
|
|
2
|
+
slug: {{slug}}
|
|
3
|
+
surface: {{frontend|api|backend|substrate}}
|
|
4
|
+
cycle: {{C1}}
|
|
5
|
+
folder: {{one.ie/web|packages/sdk|channels}}
|
|
6
|
+
deliverables:
|
|
7
|
+
- {{D1 — what it asserts}}
|
|
8
|
+
---
|
|
9
|
+
|
|
10
|
+
# Tests — {{slug}} · {{cycle}}
|
|
11
|
+
|
|
12
|
+
> One `expect()` per deliverable — assert the destination, not the path.
|
|
13
|
+
> Run: `bun run verify` in `{{folder}}/`
|
|
14
|
+
> Written first (before W3 edits land), verified at W4.
|
|
15
|
+
|
|
16
|
+
## {{D1 — user-facing outcome}}
|
|
17
|
+
|
|
18
|
+
```typescript
|
|
19
|
+
import { describe, it, expect } from 'vitest'
|
|
20
|
+
// import { {{thing}} } from '{{path}}'
|
|
21
|
+
|
|
22
|
+
describe('{{slug}} · {{deliverable}}', () => {
|
|
23
|
+
it('{{outcome a user would care about}}', async () => {
|
|
24
|
+
// arrange
|
|
25
|
+
// const input = ...
|
|
26
|
+
|
|
27
|
+
// act
|
|
28
|
+
// const result = await ...
|
|
29
|
+
|
|
30
|
+
// assert
|
|
31
|
+
// expect(result).toBe(...)
|
|
32
|
+
})
|
|
33
|
+
})
|
|
34
|
+
```
|
|
35
|
+
|
|
36
|
+
<!--
|
|
37
|
+
Rules (from do.md testing policy):
|
|
38
|
+
- ≤1 test file per cycle
|
|
39
|
+
- Goal-based: assert shipped outcome, not implementation detail
|
|
40
|
+
- Vitest-first; add requires_playwright: true in todo frontmatter if browser needed
|
|
41
|
+
- N-variant split-test → winner mark(), losers warn(0.5)
|
|
42
|
+
- One import per test file (avoid cross-cycle coupling)
|
|
43
|
+
-->
|