Dmitry DementievandClaude Opus 4.8
6f9de57b0c
- Зачем:
- гравитация скилла тянула к «выдать артефакт»; управляющие документы
раздувались деталями реализации (диагностировано на живом тесте — ADR
с инлайном SQL).
- Что:
- gate/stop: «готово» = общее понимание + рекомендованное направление,
записанное минимально-достаточно, а не «артефакт произведён»; определение
в одном месте (stop_condition), gate на него ссылается.
- core_rules: минимально-достаточный артефакт + барьер высоты (без инлайна
исполняемых артефактов) + single source of truth; приоритет над
конвенциями репозитория.
- шаг 2: артефакт(ы) выбираются ПОСЛЕ понимания, набором по жанрам.
- adr.md/spec.md: Lifetime test → Scope test (ADR↔spec по охвату, не сроку);
detailed plan — transient и вне scope скилла.
- description + README: формулировки-цели ведут пониманием, не артефактом.
- Проверка:
- grep: старый framing (lifetime/transient) убран; cross-ref Scope test
сходится; определение «готово» не дублируется; витрина не artifact-first.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
67 lines
1.9 KiB
Markdown
67 lines
1.9 KiB
Markdown
# Solution Design / Spec
|
|
|
|
Use for engineering, architecture, DevOps, integration, migration, or any
|
|
non-product feature work where a direction has been chosen but not yet built.
|
|
|
|
Use the minimum-sufficient version: the smallest form that fully preserves the
|
|
understanding, and no smaller. Drop sections that add nothing for this particular
|
|
problem — an empty section is noise.
|
|
|
|
## Template
|
|
|
|
```markdown
|
|
# Title
|
|
|
|
## Problem
|
|
|
|
## Context
|
|
|
|
## Goals
|
|
|
|
## Non-goals
|
|
|
|
## Current state
|
|
|
|
## Options considered
|
|
|
|
## Recommended approach
|
|
|
|
## Rationale
|
|
|
|
## Decisions and rejected alternatives
|
|
|
|
## Risks and mitigations
|
|
|
|
## Validation
|
|
|
|
## Documentation impact
|
|
|
|
## Open questions
|
|
```
|
|
|
|
## Notes on key sections
|
|
|
|
**Options considered vs Decisions.** Keep these two sections doing different jobs
|
|
so the rejected options aren't written twice. *Options considered* is the
|
|
landscape *before* the choice — the candidates and their trade-offs as they
|
|
stood. *Decisions and rejected alternatives* is the outcome *after* the choice —
|
|
what was picked and why each alternative was rejected. Frame in the first, judge
|
|
in the second.
|
|
|
|
**Decisions and rejected alternatives** is the highest-value section. Capture:
|
|
|
|
- accepted decisions and the reason behind each
|
|
- rejected alternatives and *why* they were rejected
|
|
- subtle constraints and important defaults
|
|
- sequencing decisions
|
|
- assumptions future agents must not silently re-derive
|
|
|
|
Do not turn this section into an ADR dump. Keep decisions that are local to this
|
|
work here; promote a decision to its own ADR (`artifacts/adr.md`) only when it is
|
|
durable, surprising, the result of a real trade-off, and matters beyond the scope
|
|
of this work — cross-cutting, relevant to readers elsewhere (see the scope test
|
|
in `artifacts/adr.md`).
|
|
|
|
**Validation** describes how we will know the implementation is correct — tests,
|
|
checks, acceptance criteria. It belongs here, not in `CONTEXT.md`.
|