一键导入
sdd
Route Spec-Driven Development work across lightweight, Spec Kit, Kiro-style, OpenSpec-style, brownfield, bugfix, planning, implementation, and audit lanes.
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。
菜单
Route Spec-Driven Development work across lightweight, Spec Kit, Kiro-style, OpenSpec-style, brownfield, bugfix, planning, implementation, and audit lanes.
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 |
| description | Route Spec-Driven Development work across lightweight, Spec Kit, Kiro-style, OpenSpec-style, brownfield, bugfix, planning, implementation, and audit lanes. |
Use first for Spec-Driven Development, Spec Kit, specs, requirements, design docs, task breakdown, Kiro-style work, implementation from a spec, or ambiguous planning-to-code work.
Pick the smallest lane that preserves intent, traceability, and proof. Tiny work stays light; ambiguous, risky, cross-boundary, orchestration, or LLM-heavy work cannot jump straight to code.
PowerShell: use $env:PLUGIN_ROOT for $PLUGIN_ROOT command paths.
Preflight when a repo path exists:
python3 "$PLUGIN_ROOT/scripts/sdd_surface_audit.py" <repo> --json
Before major edits state: LANE, EVIDENCE_PROFILE, source-of-truth paths, assumptions/open questions, next gate, and proof.
basic: local low-risk change; one focused proof.standard: normal feature/bugfix; requirements/tasks plus reproducible check or smoke path.strict: cross-module, contract/user-visible, inferred brownfield, LLM-generated, or orchestrated work; require traceability and evidence ledgers.regulated: safety, compliance, financial, privacy, security, credentials, migrations, or high-impact data; require stronger proof, formal/model evidence when feasible, or explicit risk acceptance.tiny-direct: local, low-risk, clear. Use 3-line mini-spec: intent, non-goal, proof. Never use for ambiguous/cross-boundary/security/privacy work.spec-kit: .specify/, GitHub Spec Kit, specify, /speckit.*, $speckit-*, or constitution -> specify -> plan -> tasks -> analyze -> implement.kiro-lite: .kiro/specs/ or requirements.md + design.md + tasks.md.brownfield-gap: desired behavior depends on existing code; mark inferred behavior [TO VERIFY].bugfix-spec: meaningful regression risk; capture current/expected/unchanged behavior, root-cause hypothesis, regression proof.change-proposal: cross-repo, API-breaking, migration-heavy, security/privacy-sensitive, or deployed behavior contract change; use OpenSpec-style current/proposed sections when present.orchestrated-implementation: many independent tasks with explicit boundaries, dependencies, per-unit proof; profile must be strict or regulated.sdd-spec-kit: Spec Kit setup/lifecycle.sdd-specify: requirements/spec writing.sdd-plan-tasks: design, planning, contracts, quickstart, tasks.sdd-implement: task execution.sdd-audit: traceability/completion review.## SDD Route
- LANE: <lane>
- EVIDENCE_PROFILE: basic | standard | strict | regulated
- SOURCE_OF_TRUTH: <paths>
- ARTIFACTS: <paths>
- BLOCKERS: <none or concrete blockers>
- NEXT: <focused skill/workflow step>
- PROOF: <validator or expected verification>