@dzhechkov/skills-feature-adr 1.3.50 → 1.3.51
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/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@dzhechkov/skills-feature-adr",
|
|
3
|
-
"version": "1.3.
|
|
3
|
+
"version": "1.3.51",
|
|
4
4
|
"description": "Adaptive Feature Development skill pack for Claude Code — 11-step pipeline with Complexity Router (S/M/L/XL), ADR-driven architecture, 15 agentic-qe skills, multi-agent fleet QE. Supports --full-qe, --full-qe-extended, --with-learning, and --knowledge-extractor modes.",
|
|
5
5
|
"bin": {
|
|
6
6
|
"skills-feature-adr": "./bin/cli.js"
|
|
@@ -0,0 +1,75 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: configure-feature-adr
|
|
3
|
+
description: |
|
|
4
|
+
Guided, conversational setup that makes feature-adr aware of THIS product — vision, architecture map,
|
|
5
|
+
testing/verification rules, and (optionally) a review critic — WITHOUT the user knowing any manifest schema.
|
|
6
|
+
Complex inside, simple outside.
|
|
7
|
+
|
|
8
|
+
TRIGGERS: "настрой feature-adr под мой продукт", "помоги настроить feature-adr", "configure feature-adr
|
|
9
|
+
for my product", "какие документы нужны для feature-adr и куда их добавить", "onboard feature-adr".
|
|
10
|
+
|
|
11
|
+
Uses the deterministic engine `dz feature-adr-setup` (plan → scaffold-from-spec, propose-confirm,
|
|
12
|
+
augment-never-clobber). Reuses `dz architecture` (map) and `dz mr-rakes --gen-critic` (auto critic).
|
|
13
|
+
allowed-tools: Bash, Read, Write, Edit, AskUserQuestion
|
|
14
|
+
---
|
|
15
|
+
|
|
16
|
+
# Configure feature-adr for this product
|
|
17
|
+
|
|
18
|
+
Turn a generic feature-adr into a **project-aware** one by scaffolding four committed files under
|
|
19
|
+
`architecture/` and wiring `project-skills.json` — through a short conversation, not a schema lesson.
|
|
20
|
+
|
|
21
|
+
**Golden rule:** you NEVER hand-write manifest JSON in front of the user, and you NEVER overwrite an existing
|
|
22
|
+
file. The engine scaffolds; you interview only for what can't be auto-derived.
|
|
23
|
+
|
|
24
|
+
## Protocol
|
|
25
|
+
|
|
26
|
+
### 1. Read the current state (never writes)
|
|
27
|
+
```bash
|
|
28
|
+
dz feature-adr-setup --plan --json
|
|
29
|
+
```
|
|
30
|
+
Report in plain language: which of `vision.md` / `subsystems.manifest.json` / `testing.md` /
|
|
31
|
+
`project-skills.json` already exist, how many workspace packages were discovered (a map can be
|
|
32
|
+
auto-scaffolded), and whether a review corpus exists (a critic can be auto-generated). Tell the user exactly
|
|
33
|
+
which documents are still missing — this is the "which docs, and where?" answer.
|
|
34
|
+
|
|
35
|
+
### 2. Auto-derive what you can (confirm, don't dictate)
|
|
36
|
+
- **Map:** take the discovered packages and propose a starter subsystem grouping (foundation / arsenal / your
|
|
37
|
+
app subsystems). Show it; ask the user to rename/split to their real subsystems. (Their product, their call.)
|
|
38
|
+
- **Critic (optional):** if a review corpus exists, offer to run `dz mr-rakes --gen-critic
|
|
39
|
+
architecture/project-critic/SKILL.md --apply` to generate the critic role from their recurring rakes.
|
|
40
|
+
|
|
41
|
+
### 3. Short interview — only the un-derivable
|
|
42
|
+
Ask, ONE topic at a time (this is the whole point of the skill — keep it to a handful of questions):
|
|
43
|
+
- **Product vision** — what the product IS (one paragraph), where it's going, and 1-3 things it consciously
|
|
44
|
+
does NOT do. Seed your draft from the repo README's "why/what" section, then confirm.
|
|
45
|
+
- **Testing / verification** — the commands that prove "done" here (e.g. `pnpm test -- --run`), what "done"
|
|
46
|
+
means in this project, and any required gates (coverage, lint, typecheck). This becomes the `testing` role.
|
|
47
|
+
- **Optional roles** — ask briefly whether they have a code implementation bar (`impl-bar`) or brand/UI rules
|
|
48
|
+
(`brand`) to point at; skip if not.
|
|
49
|
+
|
|
50
|
+
### 4. Fill the SPEC and scaffold (propose-confirm)
|
|
51
|
+
Write the collected answers to a spec file, then preview:
|
|
52
|
+
```bash
|
|
53
|
+
# spec shape: { vision:{core,direction?,boundaries?[],principles?[]}, testing:{commands?[],doneDefinition?,gates?[]},
|
|
54
|
+
# subsystems:[…], roles:{critic?:"auto"|path, brand?:path, "impl-bar"?:path}, extra?:[…] }
|
|
55
|
+
dz feature-adr-setup --from-spec /tmp/feature-adr-spec.json # preview: create / augment / unchanged per file
|
|
56
|
+
```
|
|
57
|
+
Show the preview. An **existing file is `unchanged` (never clobbered)**; a structured file is **augmented**
|
|
58
|
+
(existing content kept, new added). On the user's explicit "yes":
|
|
59
|
+
```bash
|
|
60
|
+
dz feature-adr-setup --from-spec /tmp/feature-adr-spec.json --apply
|
|
61
|
+
```
|
|
62
|
+
|
|
63
|
+
### 5. Verify + hand off
|
|
64
|
+
```bash
|
|
65
|
+
dz project-skills # confirm the roles resolve (product-vision, testing, critic, …)
|
|
66
|
+
dz architecture --revise # confirm no drift
|
|
67
|
+
```
|
|
68
|
+
Tell the user: from now on every `/feature-adr` in this repo folds their vision into design + QE, their
|
|
69
|
+
testing rules into Step 8, and their critic into review — automatically. Re-run this skill any time the
|
|
70
|
+
product grows; it only augments (new packages, fresh rakes), never overwrites.
|
|
71
|
+
|
|
72
|
+
## Notes
|
|
73
|
+
- **Re-run = update.** The same flow, idempotent: step 1 surfaces only what's new.
|
|
74
|
+
- **Nothing is written without the user's confirmation**, and no hand-edited file is ever overwritten.
|
|
75
|
+
- If `dz` is not set up, install it first (`npm i -g @dzhechkov/harness-cli`); the engine needs `dz` ≥ 0.3.116.
|