phx-brainstorm
/phx-brainstorm
Rozważa funkcje Elixir i Phoenix przed planowaniem, zestawiając podejścia i wymagania do uzgodnienia.
- Autor
- oliver-kriska ↗
- Repozytorium
- claude-elixir-phoenix ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 22.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 3
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 22.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Rozważa funkcje Elixir i Phoenix przed planowaniem, zestawiając podejścia i wymagania do uzgodnienia.
Oryginalny opis (EN)
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
Jak działa
- Usage
- Workflow
- Phase 1: Adaptive Interview
- Phase 2: Decision Point
- Phase 3: Research (Diverge → Evaluate → Converge)
- Iron Laws
- Integration
- References
Podgląd SKILL.md
---
name: phx-brainstorm
description: Brainstorm Elixir/Phoenix features — explore ideas, compare approaches,
gather requirements. Use when vague idea, not sure how to approach, or want to discuss
before plan.
---
# Brainstorm — Adaptive Requirements Gathering
Interactive interview → research → synthesis loop. Produces structured
`interview.md` that `/skill:phx-plan` detects and consumes (skipping clarification).
## Usage
```text
/skill:phx-brainstorm Add some kind of notification system
/skill:phx-brainstorm Improve authentication security
/skill:phx-brainstorm # starts with open question
```
## Workflow
```
/skill:phx-brainstorm {topic}
|
v
[INTERVIEW] ←──────────────────┐
| |
v (sufficient OR user exit) |
[DECISION POINT] |
├─ Research ──→ [RESEARCH] ─┘
├─ Continue interview ──────┘
├─ Make a plan ──→ STOP (suggest /skill:phx-plan {slug})
├─ Store & exit ──→ STOP (artifacts saved)
└─ Discuss ──→ freeform ──→ [DECISION POINT]
```
## Phase 1: Adaptive Interview
Create `.claude/plans/{slug}/` directory. Start asking ONE question at a time.
### Coverage Dimensions
Track coverage across 6 dimensions (0=uncovered, 1=partial, 2=sufficient).
**Ask Scope early** — for "optimize X" topics, ask about boundaries (upstream
OK? Local-only? CI vs dev?) before research, not during.
| Dim | Target | Sufficient signal |
|-----|--------|-------------------|
| What | Specific behavior/features | Concrete verbs, not "some kind of" |
| Why | Problem solved, user need | Clear benefit stated |
| Scope | In/out boundaries | Explicit exclusions stated |
| Where | Modules, contexts, pages | File paths or context names mentioned |
| How | Approach, constraints | At least one concrete constraint |
| Edge | Error states, scale, auth | 2+ edge cases identified |
Interview is "sufficient" when total score >= 8 out of 12.
### Context-Aware Questioning
**Before each question**, run a brief codebase scan on topics the user mentioned:
1. User mentions a topic (e.g., "notifications") → run Grep/Glob for related patterns
2. Use scan results to ground your next question in what actually exists
3. Unknown/niche topic → suggest research pause before continuing
### Signal Detection
- **Vague answer** ("maybe", "not sure") → probe deeper on same dimension
- **Niche topic** mentioned → "This involves {X}. Want me to research it first?"
- **Detailed answer** covering 3+ dimensions → mark all covered, advance
- **No new coverage** for 2 consecutive questions → suggest moving to Decision Point
## Phase 2: Decision Point
Write interview.md first, then use AskUserQuestion — every option below
relies on the saved file. Move past this point only on a formal choice.
1. Write current state to `.claude/plans/{slug}/interview.md`
2. Show coverage summary: "Coverage: What 2/2 | Why 2/2 | Scope 1/2 | ..."
3. Use AskUserQuestion with EXACTLY these options (4 max — the tool's
hard limit; the auto-added "Other" covers freeform discussion):
- **Research** — search codebase + internet for approaches (2 agents)
- **Continue interview** — ask more questions
- **Make a plan** — I'll suggest: `/skill:phx-plan .claude/plans/{slug}/interview.md`
- **Store & exit** — save everything, come back later
4. Wait for user response. Do NOT proceed without explicit choice
**AskUserQuestion discipline**: decisions only, never narration or
rhetorical check-ins. Every option states concrete impact (what happens,
what it costs) so the user can pick without follow-up questions.
## Phase 3: Research (Diverge → Evaluate → Converge)
**First cycle: MAX 2 agents** — keep it fast (~2-3 min). Spawn in ONE
Tool Use block with `run_in_background: true`:
- `phoenix-patterns-analyst`: "How does this codebase handle {topics}?"
Write to `.claude/plans/{slug}/research/codebase-scan.md`
- `web-researcher`: "Elixir/Phoenix approaches to {topics}"
Return 500-word summary
**Do NOT spawn additional specialist agents** in the first cycle.
If user wants deeper investigation, they pick "More research" at the
next Decision Point — then spawn focused agents for specific questions.
**Evaluate** — for each approach found:
- Thesis: why it works for THIS codebase
- Antithesis: why it might NOT work (scale, complexity, pattern conflicts)
**Converge** — present 2-3 approaches with honest trade-offs.
Do NOT recommend one. Return to Decision Point (AskUserQuestion).
See `references/research-integration.md` for details.
## Iron Laws
1. **NEVER auto-transition** to `/skill:phx-plan` — always present as option, let user choose
2. **ONE question at a time** — never dump a question list
3. **Always write artifacts** — `interview.md` is the contract with `/skill:phx-plan`
4. **Scan codebase between questions** — every question must be context-aware
5. **AskUserQuestion at EVERY decision point** — never flow past without formal choice.
This is the most critical law. After interview, after research, after discuss — ALWAYS
present options via AskUserQuestion. Never let conversation skip the checkpoint
6. **STOP after presenting options** — do not proceed without user input
7. **MAX 2 agents in first research cycle** — deeper dives are subsequent cycles.
User picks "More research" to go deeper, not the skill
## Integration
```
/skill:phx-brainstorm ──→ interview.md ──→ /skill:phx-plan (skips clarification)
──→ /skill:phx-plan --existing (deepens)
──→ stored for later session
```
Position: optional upstream of `/skill:phx-plan` in workflow cycle.
## References
- `references/interview-techniques.md` — coverage scoring,
question templates, scan patterns, signal detection, interview.md format
- `references/research-integration.md` — diverge-evaluate-converge,
agent spawn templates, approach presentation format
Pliki w paczce (3)
- SKILL.md 6 KB
- references/interview-techniques.md 9 KB
- references/research-integration.md 7 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · oliver-kriska/claude-elixir-phoenix | 100 | MIT |
| oliver-kriska/claude-elixir-phoenix | 100 | MIT |
| oliver-kriska/claude-elixir-phoenix | 100 | MIT |
| oliver-kriska/claude-elixir-phoenix | 100 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki a0960d02598a (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100brainstorm
Prowadzi burzę mózgów nad funkcjami Elixir/Phoenix: bada pomysły, porównuje podejścia i zbiera wymagania, gdy idea jest mglista i trzeba ją omówić przed planem. - 100phx-full
Prowadzi pełny cykl pracy nad funkcją Elixir i Phoenix z bramkami kontrolnymi, od pomysłu po gotowy kod. - 100elixir-expert
Wspiera pracę z Elixirem, Phoenix, OTP i systemami współbieżnymi. - 100gendiff
Używa API gendiff z elixirstream.dev do pokazania zmian między wersjami generatorów Elixir i Phoenix (phx.new, phx.gen.auth, Nerves, Scenic, Surface, Credo), by aktualizować na podstawie rzeczywistych diffów. - 100brainstorm
Bada wymagania i podejścia w rozmowie, zanim zacznie się planowanie wdrożenia, gdy użytkownik chce omówić pomysł. - 95sentry-elixir-sdk
Konfiguruje Sentry w aplikacjach Elixir, Phoenix i Plug: błędy, tracing, logi i zadania cykliczne.