- name
SKILL.md
技能文件保留在发布者的仓库中。
在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add levnikolaevich/claude-code-skills --skill ln-23-system-design-proposal-builder -a cursor -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add levnikolaevich/claude-code-skills --skill ln-23-system-design-proposal-builder -a claude-code -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add levnikolaevich/claude-code-skills --skill ln-23-system-design-proposal-builder -a codex -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add levnikolaevich/claude-code-skills --skill ln-23-system-design-proposal-builder -a grok -y在 Grok Bot 聊天中发送复制的消息。Bot 会从 GitHub 获取这个 SKILL.md,并添加到你所有 Bot 共享的技能中。
Install this skill: https://github.com/levnikolaevich/claude-code-skills/tree/HEAD/plugins/architecture-suite/skills/ln-23-system-design-proposal-builder来自发布者
Goal: Create a proportionate, evidence-backed target system design that turns requirements into explicit boundaries, contracts, data flow, failure behavior, operations, and tradeoffs. Change only the approved design document; do not implement, audit, or approve the delivery.
Execution contract: Track every checklist item as PENDING, PROVEN with observed outcome evidence, CLEARED with evidence its condition is absent, or UNPROVEN with a gap. Reading, delegation, tool failure, zero exit status, and self-reported success are not proof. Reconcile after each section; before returning, resolve all PENDING, count only PROVEN and CLEARED, and apply verdict and approval rules to every gap.
Preserve intent, scope, mode, and existing authorization. Complete authorized work before required external approval; ask only consequential unresolved choices. If nobody can answer, report the exact question and apply the skill's gap verdict without waiting or guessing. Cite any blocking instruction and unresolved boundary; never invent approval gates. Scale depth to material risk; preserve mandatory checks, dependencies, and safety order while choosing verification methods.
Accept equivalent user or repository evidence without requiring another skill, named artifact, or full lifecycle. Preserve source requirement and decision IDs. Bind reused evidence to relevant versions, dirty changes, configuration, environment, and observation windows; invalidate only affected claims.
Choose the primary workflow by outcome and explicit selection. Consume neighboring contracts and valid evidence without duplicating ownership or restarting audits. Split distinct deliverables by scope, not mandatory skill invocation. Broad independent assessments use audit workflows; focused domain reviews remain read-only.
On continuation, reconcile task, authorization, state, and gaps. Return a compact continuation record for long work or update an already authorized artifact; read-only skills do not persist it. Distinguish artifact readiness, verified behavior, and external-action authority.
Trace applicable requirements to their authoritative owner, planned or implemented change, acceptance evidence and status in the existing artifact or response; no new registry is required. Explicit constraints remain binding until an authorized deviation; risk determines priority, not permission to ignore them.
Investigate the causal flow beyond initially named files. Within implementation authority, include structural repair needed for the outcome; minimize total complexity and risk, not changed lines. This does not authorize unrelated cleanup or mutation during review.
Before retrieval, define the evidence question; read selectively without skipping applicable instructions. Use tools for mechanical processing; summarize bounded results, errors, coverage, and source paths, keeping full output outside context.
Before technical decisions, establish applicability and actual versions; verify version-dependent assumptions against official documentation or specifications. Search and read primary pages for current external recommendations; snippets are not evidence. Version-matched bundled documentation or valid prior evidence suffices. Record decision, version, source, and limitations. Mark unavailable evidence UNVERIFIED; block only essential dependent work. Prefer native mechanisms, justify added tools or abstractions with evidence, and reuse the existing rule owner.
Use patterns as candidate solutions, not goals. Introduce infrastructure only when a requirement, failure mode, ownership boundary, or measured horizon pays for its lifecycle cost.
This workflow owns structural alternatives and target system boundaries. Technical foundation work applies accepted decisions; it must not silently redesign the architecture. Link existing technical contracts instead of copying their checklists into the design.
docs/architecture/target-design.md.BLOCKED when a required business boundary or safety constraint cannot be responsibly assumed.Compare credible alternatives, including the simplest feasible option, against requirements, estimates, failure behavior, complexity, cost, migration, and future triggers. If constraints permit only one, explain why instead of inventing alternatives.
Trace the design without each disputed mechanism, including indirect consumers: identify required behavior or justified risk coverage lost versus upkeep removed. Propose removal when only upkeep disappears; present any loss of a required guarantee as a separate decision under the accepted-decision rule.
State selected and rejected options with consequences, sensitivity points, and assumptions that would reopen the decision.
Identify significant decisions that deserve their own compact decision records without requiring another workflow.
Define architecture acceptance evidence appropriate to each material driver: contract checks, load/failure experiments, security validation, recovery proof, or observability signals. Specify prerequisites and pass criteria; do not execute them during design.
Outline current-to-target implications and compatibility needs without expanding into a full implementation plan.
Link each accepted layer, API-ownership, state and trust-boundary constraint to a feasible verification mechanism; distinguish an executable architecture check from runtime acceptance.
READY only when the design is decision-complete enough for implementation planning; use INCOMPLETE for material but solvable gaps; use BLOCKED when required intent, evidence, authority, or destination is unavailable.Report in the user's language, in this order; label all five fields and state each fact once. Use controlled plain language: one fact per sentence, usually under 20 words, active voice, and one term per concept, with no synonyms for verdicts, IDs, or states. Small results may use one line per field; omit empty tables and do not copy linked artifacts:
Checklist: X/Y complete; Incomplete: None or each UNPROVEN item's reason, outcome impact, and exact next action; residual risks and required decisions.Skill-specific evidence: Artifact path; requirements, estimates, boundaries, contracts, HLD/critical LLD, selected decisions, alternatives, evidence, and reopen triggers. Summarize validation/transition needs, compatibility, rollout, rollback, observability, and only unresolved choices that affect implementation planning. When the design has more than a few components and the host renders Markdown diagrams, add one Mermaid boundary diagram; keep the text complete without it.
Designs target system boundaries, contracts and tradeoffs from requirements; does not plan tasks or implement.
---name: ln-23-system-design-proposal-builderdescription: Designs target system boundaries, contracts and tradeoffs from requirements; does not plan tasks or implement.---# plugins/architecture-suite/skills/ln-23-system-design-proposal-builder/SKILL.md常见问题
从发布者处下载 plugins/architecture-suite/skills/ln-23-system-design-proposal-builder/SKILL.md,或复制路径后打开仓库。PlugMCP 只收录该技能,不托管文件。
发布者将它存放在 https://github.com/levnikolaevich/claude-code-skills。
Claude、Cursor、Codex 和 Grok Build 可以读取你从发布者仓库添加的 SKILL.md。在聊天中发送技能的 GitHub 文件夹链接,Grok Bot 就会安装它。