菜单
Execute SDD task lists safely, update task status, handle spec drift, and verify completion with fresh evidence before claiming done.
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-implement |
| description | Execute SDD task lists safely, update task status, handle spec drift, and verify completion with fresh evidence before claiming done. |
Use when tasks are ready and the user wants implementation, execution, continuation, or completion from SDD artifacts.
PowerShell: use $env:PLUGIN_ROOT for $PLUGIN_ROOT command paths.
python3 "$PLUGIN_ROOT/scripts/sdd_surface_audit.py" <repo> --json
python3 "$PLUGIN_ROOT/scripts/sdd_traceability_check.py" <repo> --json
git status --short
Read active tasks, design/plan, spec/requirements, quickstart, evidence ledger if present, and relevant code. If core artifacts are missing, route to sdd-plan-tasks or sdd-specify. Preserve unrelated user changes.
strict/regulated, keep requirement/task IDs in notes, evidence, or commits.Use the most relevant proof available: tests, build/typecheck, relevant lint, runtime/UI smoke, bug reproduction command, or labeled manual verification (reproducible by another human, scoped to the claim) when automation is unavailable.
Evidence must match the claim. Lint does not prove behavior; a unit test does not prove runtime boot; a checklist does not prove integration.
For strict/regulated, maintain evidence.md, validation.md, proof.md, or equivalent with command/manual path, current-run marker, outcome, covered IDs, and gaps/deferrals. If deterministic proof is unavailable for high-risk behavior, record risk acceptance instead of claiming full proof.
When implementation contradicts artifacts: pause, identify artifact and code evidence, update intended artifact or implementation, then re-run relevant check.
PASS or findings are disclosed.