菜单
Use GitHub Spec Kit projects and commands, including constitution, specify, clarify, plan, tasks, analyze, implement, extensions, and presets.
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-spec-kit |
| description | Use GitHub Spec Kit projects and commands, including constitution, specify, clarify, plan, tasks, analyze, implement, extensions, and presets. |
Use for GitHub Spec Kit, Specify CLI, /speckit.*, $speckit-*, .specify/, extensions, presets, or Spec Kit command behavior.
Project workspace is source of truth. Upstream https://github.com/github/spec-kit and any user-provided Spec Kit reference checkout are references unless the user asks to edit Spec Kit itself.
PowerShell: use $env:PLUGIN_ROOT for $PLUGIN_ROOT command paths.
python3 "$PLUGIN_ROOT/scripts/sdd_surface_audit.py" <repo> --json
git status --short
Check .specify/, .specify/feature.json, .specify/memory/constitution.md, specs/*/{spec.md,plan.md,tasks.md}, and .specify/extensions.yml. State any init/install/upgrade/fetch before running it.
Follow project command files when present; otherwise use this layout:
.specify/memory/constitution.mdspecs/<feature>/spec.md plus specs/<feature>/checklists/requirements.md[NEEDS CLARIFICATION]plan.md, research.md, data-model.md, contracts/, quickstart.md, risk/evidence profiletasks.md with dependency order, requirement links, paths, verification, expected evidenceFor .specify/extensions.yml: read relevant before_*/after_*; skip disabled hooks; do not evaluate non-empty conditions yourself. Mandatory hooks surface EXECUTE_COMMAND: <command> and wait when supported. Optional hooks are reported unless requested.
spec.md: no implementation leakage unless template allows; sources/assumptions/ambiguity/review gaps visible for high-impact requirements.plan.md: decisions, rationale, alternatives, constitution gate, risk/evidence profile, traceability strategy.tasks.md: IDs, story labels when applicable, paths, dependencies, independent validation.evidence.md, validation.md, proof.md, or equivalent in quickstart.md/tasks.md.python3 "$PLUGIN_ROOT/scripts/sdd_traceability_check.py" <repo> --json before implementation and before claiming done.Return active feature directory, changed Spec Kit artifacts, unresolved risks, validation commands/outcomes, evidence updates, and next phase.