بنقرة واحدة
spec-decomposition
Analyze specifications and decompose into independent changes.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Analyze specifications and decompose into independent changes.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Orchestrates SDD project initialization — version detection, environment verification, scaffolding, and git setup.
Manage project settings in sdd/sdd-settings.yaml including component settings that drive scaffolding.
Single gateway for all core↔tech-pack interactions. Reads manifests, resolves paths, loads skills/agents, routes commands.
Manage tasks and plans using the .tasks/ directory.
Standards for authoring SDD plugin agents — frontmatter, self-containment, skill references, and no-user-interaction rules.
Standards for authoring SDD plugin commands — frontmatter, user interaction, skill/agent invocation, CLI integration, and output formatting.
| name | spec-decomposition |
| description | Analyze specifications and decompose into independent changes. |
| user-invocable | false |
Analyze a specification document to identify natural change boundaries and return a structured decomposition result. This is a pure analysis skill that takes input and returns output without user interaction.
Schema: schemas/input.schema.json
Accepts decomposition mode, spec content, and mode-specific parameters for outline, section, or hierarchical decomposition.
Schema: schemas/output.schema.json
Returns mode-specific results: outline sections, or hierarchical epic/feature groupings with dependency graph.
For detailed guidance, read these on-demand:
Modes: outline (extract headers), section (analyze one section), hierarchical (epics + features), default (full analysis)
Algorithm phases: Structure Extraction -> Boundary Detection -> Dependency Detection -> Independence Scoring -> Refinement
Complexity levels: SMALL (<= 3 ACs), MEDIUM (4-8 ACs), LARGE (> 8 ACs), EPIC (> 10 ACs + 3+ components)
Independence score: 0.0-1.0 scale; >= 0.5 is standalone, < 0.3 should be merged