specify
Use to turn a raw feature idea into a reviewed spec.md — a lightweight Socratic interview front (capture the idea, deep-dive the problem) merged with a full product spec (context, goals, user stories, acceptance criteria, NFRs, KPIs). Triggers on "specify {slug}", "spec for {slug}", "write the spec", "capture this idea", "draft requirements for {slug}", "/sdd:specify {slug}", "напиши специфікацію {slug}", "опиши вимоги", "зафіксуй ідею". Opens by setting the interview-depth dial (easy/medium/hard), drafts from templates/spec.md, validates each acceptance criterion Socratically, runs a clean-context critic, then writes docs/features/{slug}/spec.md. The ideation analyses (competitive research, strategic approaches, multi-perspective review, devil's-advocate) run as named subagents gated by the depth dial — easy skips them, hard runs the full suite.
genkovich · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add genkovich/sdd --skill specify技能说明
name: specify model: inherit effort: high agents: [critic, researcher, strategist, analyst, devils-advocate] description: > Use to turn a raw feature idea into a reviewed spec.md — a lightweight Socratic interview front (capture the idea, deep-dive the problem) merged with a full product spec (context, goals, user stories, acceptance criteria, NFRs, KPIs). Triggers on "specify {slug}", "spec for {slug}", "write the spec", "capture this idea", "draft requirements for {slug}", "/sdd:specify {slug}", "напиши специфікацію {slug}", "опиши вимоги", "зафіксуй ідею". Opens by setting the interview-depth dial (easy/medium/hard), drafts from templates/spec.md, validates each acceptance criterion Socratically, runs a clean-context critic, then writes docs/features/{slug}/spec.md. The ideation analyses (competitive research, strategic approaches, multi-perspective review, devil's-advocate) run as named subagents gated by the depth dial — easy skips them, hard runs the full suite.
Skill: specify
Turns a one-line idea into a reviewed spec.md: a lightweight interview captures and stress-tests the idea, then the skill drafts a product spec (context → goals → user stories → acceptance criteria → NFRs → KPIs), validates it Socratically, and runs a clean-context critic before writing. Less typing, more reviewing. This file is the spine; detail lives in references/.
The Socratic machine, the critic, and the size matrix are shared — this skill keeps only its deltas:
→ ../_shared/socratic-loop.md · ../_shared/critic.md · ../_shared/size-matrix.md · ../_shared/ask-style.md
Depth governs question volume + autonomy (and which ideation analyses run) → ../_shared/interview-depth.md.
Document prose follows the project's artifact_language setting — section headings, frontmatter and machine tokens stay English → ../_shared/artifact-language.md.
Owner
PM + Tech Lead (co-authors). PM drives goals / non-goals / KPIs; Tech Lead drives context patterns and the acceptance-criteria coverage.
Inputs
<slug>— kebab-case feature slug.- (Optional)
CONTEXT.md— the two-level glossary: read both repo-root (project-wide) anddocs/features/<slug>/CONTEXT.md(feature-scoped); per-feature wins on conflict →../glossary/SKILL.md. If present, its roles/terms are canonical and override anything that contradicts them. docs/features/<slug>/.size— depth hint (MVP vs Full per the size matrix). Read if present; established here if absent (step 1 classifies + writes it), so downstream stages never silently default to M.classify-sizere-classifies when scope changes.- (Optional) prior notes / a reference module / a ticket the user already has.
Protocol
- Ensure the settings file (first thing, after this skill's own gate). If
.claude/sdd.local.mdis absent, create it now from the canonical template — documented defaults + the self-documenting body — and patch.gitignore; if it exists, read it and never overwrite. The one procedure lives in../_shared/settings-file.md. Creating is unconditional; changing values is only ever offered byconfig. Say one line: «.claude/sdd.local.mdcreated with documented defaults —/sdd:configto tune it». Then read context + set the interview depth. If aCONTEXT.mdexists (read both repo-root anddocs/features/<slug>/— per-feature wins on conflict), load its## Glossaryas session state (canonical roles + terms). If.sizeexists, read it to size the spec's depth; if it's absent, establish it now — run theclassify-sizeprotocol inline (the canon:../classify-size/SKILL.md+ the mapping in../_shared/size-matrix.md); the four signals fold into one bundledAskUserQuestionhere (ateasydepth, take the matrix default and record it in the assumptions ledger), and writedocs/features/<slug>/.size+.route(the route defaults from the size — XS/S→quick, M→standard, L/XL→full— and is confirmed in the same bundled question, per the Routes table in../_shared/size-matrix.md) — so every later stage reads a real size instead of silently defaulting to M (the gap that otherwise surfaces only atplan-tests).classify-sizestays the utility to re-classify when scope changes. Ifdocs/architecture-map.mdexists (fromsurvey), read it so the spec is architecture-aware — it informs §1 Context, §2 Constraints, and §3 Non-goals (what the existing system already does / can't do). Absent → suggest runningsurveyfirst, but proceed (the spec is product-level and can be captured without it). Do not leak the map's tech into §5 AC — AC stay business-observable; the map shapes constraints, not acceptance criteria. Then set the interview depth (the opening question): readinterview_depthfrom the settings file ensured in the first sentence of this step (else default medium), and — unless a--depth=easy|medium|hardarg was passed (which skips the question) — ask ONE depth-selectionAskUserQuestionphrased per../_shared/ask-style.md, with the saved/medium value as the «(Recommended)» first option, overridable per run. The chosen level governs the step-2 deep-dive volume, the step-3 ideation suite, and the step-7 Socratic volume →../_shared/interview-depth.md. (Completeness — §5's 5-type AC floor — is unaffected by depth.) - Capture the idea (interview front). One
AskUserQuestionfor the raw idea in 1–3 sentences (persist verbatim as the baseline). Then a Socratic deep-dive across problem clarity / success criteria / constraints / strat