メニュー
Generate an implementation plan for a speckit feature. Explicit invocation only — never load from context or topic. Use only when the user types the exact command "speckit-plan".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | speckit-plan |
| description | Generate an implementation plan for a speckit feature. Explicit invocation only — never load from context or topic. Use only when the user types the exact command "speckit-plan". |
| disable-model-invocation | true |
Generates implementation plan artifacts from an existing spec: research.md, data-model.md, quickstart.md.
Run: .specify/scripts/bash/setup-plan.sh --json from repo root. Parse JSON for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH.
FEATURE_SPEC (spec.md) and .specify/memory/constitution.mdIMPL_PLAN template (already copied)design.md: If FEATURE_DIR/design.md exists, read it — it is the source of truth for all HTML/CSS/design content. spec.md is source of truth for functional requirements.
## Layout matrix (flex / grid) (mandatory for layout-heavy blocks; Figma-derived flex-direction / gap per breakpoint), Design Token Mapping, Breakpoints + Per-Breakpoint CSS Overrides, Dynamic Content Elements, Interactive States, Visual Acceptance Checklistblock-collection-and-party skill to find similar blocks and reference implementations — existing patterns often resolve unknowns faster than reasoning from scratchdocs-search skill for platform-specific unknowns (loading phases, auto-blocking, indexing, etc.)research.mdNEEDS CLARIFICATION must be resolved before Phase 1Prerequisites: research.md complete
Reference the building-blocks skill for EDS decoration patterns, three-phase loading conventions (eager/lazy/delayed), and CSS best practices when producing these artifacts:
data-model.md — refine the content model from spec.md into detailed authored content examples with block table structure, rows, columns, metadata, and block options (variants)quickstart.md — integration scenarios, test scenarios
@media (width >= Npx) with standard breakpointsPrerequisites: data-model.md complete (content model is stable)
Generate draft HTML test content based on data-model.md. Follow the content-driven-development skill, Phase 1.3 for the full process, content creation options, and HTML structure guidance.
Output: branch, IMPL_PLAN path, generated artifacts (research.md, data-model.md, quickstart.md, draft test content path), and readiness for next phase: /speckit-tasks (when plan is complete).
design.md is source of truth for HTML/CSS — quickstart.md and plan.md must not override itManual asset processing skill for Figma layers. Accepts layer URLs and writes deterministic files to drafts/media using curl+sips, with optional get_screenshot fallback.
Phase 3 of athenai-implement pipeline — execute tasks from plan.md and produce working block code. Includes lint-aware CSS generation and mandatory design compliance check when design.md exists.
Phase 0 of athenai-implement pipeline — conditionally produce design.md from Figma. Includes decision logic, extraction-only rules, manual asset handoff, and Phase 1 context pre-loading optimization.
End-to-end implementation pipeline — design, plan, tasks, implement, test cases, test content. Demo mode: skips unit tests and research deep-dives. Records phase wall times via `.specify/scripts/phase-timer.py` (per-phase start/end, subagent logs + merge when parallel). Explicit invocation only — never load from context or topic. Optional flags: --no-parallel (run all phases sequentially in main agent, no subagents), --no-test-cases (skip Phase 4 test case generation).
Phase 1-2 of athenai-implement pipeline — produce plan.md with authored HTML structure, parsing logic, and tasks section. Includes draft test content generation with mandatory edge case coverage.
Phase 4 of athenai-implement pipeline — generate testcases.csv from spec.md. Includes guard for --no-test-cases flag and coverage requirements for user journeys, acceptance criteria, and edge cases.