菜单
Convert approved SDD specs into technical plans, design artifacts, contracts, quickstart validation, and traceable task lists.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when locating, summarizing, auditing, or debugging Codex session rollout JSONL logs by CODEX_THREAD_ID, cwd, query, issue key, project path, child or inherited-history symptoms, malformed or huge log symptoms, permission concerns, or "what happened in this Codex thread" questions.
Use when auditing agent skills or plugins for safety, coverage, duplicated logic, token/context cost, prompt-contract risk, validation readiness, marketplace visibility, dependencies, network behavior, or install/update risk. For structural split/merge/move/delete/router decisions across skills or plugins, use capability-portfolio-architect instead.
Use when auditing agent skill/plugin portfolio architecture for cross-plugin capability overlap, weak routing, duplicated or missing skills, split/merge/delete/move decisions, shared capability extraction, reference/script extraction, or plugin boundary redesign. For safety, coverage, or validation review of a single artifact without boundary changes, use capability-auditor instead.
Use when performing broad external-first discovery, vetting, scoring, distillation, or synthesis of agent skills or plugin packs from the public web, GitHub/public repositories, OpenClaw/ClawHub, marketplaces, research sources, community implementations, user references, or local skills. Use for well-vetted capability synthesis, cross-skill comparison, plugin-pack synthesis, global capability acquisition, skill strengthening, and adoption/rejection changelogs.
Route and orchestrate agent skill and plugin lifecycle work. Use when work involves agent skills, plugins, marketplace packages, capability acquisition, synthesis, creation, installation, packaging, audit, or context-density optimization.
Use when creating, updating, validating, optionally installing/cache-refreshing, or handing off marketplace-backed agent plugins. Use for plugin manifests, local marketplace entries, plugin-pack synthesis, triggerable skill bundles, install visibility gates, and Codex app deeplinks.
| name | sdd-plan-tasks |
| description | Convert approved SDD specs into technical plans, design artifacts, contracts, quickstart validation, and traceable task lists. |
Use after a spec is drafted/approved and the next step is design, planning, tasking, or implementation prep.
Load only needed artifacts: spec/requirements, constitution/steering/project context, architecture docs, brownfield code patterns, prior research/contracts/quickstart.
basic, standard, strict, or regulatedPreserve Spec Kit layout when present: plan.md, research.md, data-model.md, contracts/, quickstart.md. Preserve Kiro design.md. Use diagrams only for real boundaries.
Avoid tasks like "implement feature" or "update tests" without path, expected behavior, and validation command.
research.md or equivalent.PowerShell: use $env:PLUGIN_ROOT for $PLUGIN_ROOT command paths.
python3 "$PLUGIN_ROOT/scripts/sdd_traceability_check.py" <repo> --json
Resolve FAIL before implementation or record why proceeding is acceptable. Do not proceed if core artifacts are missing. For strict/regulated, create or identify evidence.md, validation.md, proof.md, or equivalent before tasks can be completed. LLM self-review/model confidence is not verification.
Design satisfies the spec; every buildable requirement has tasks or deferral; tasks have dependency order, parallel boundaries, verification; traceability/evidence are audit-ready.