一键导入
cost-discipline
FinOps discipline — cost allocation, budgets, commitment analysis, unit economics. Cloud-agnostic; vendor tooling from memory-long §stack.
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
FinOps discipline — cost allocation, budgets, commitment analysis, unit economics. Cloud-agnostic; vendor tooling from memory-long §stack.
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
Context engineering — memory navigation, textual graph traversal, progressive disclosure, recovery. Load when assembling context for a task or when lost.
Implementation-side security discipline — headers, dependencies, secrets, authz. Load for hardening work (sec-ops domain).
Commit conventions, branching, anchors in messages, and the git safety rules. Load for any git operation beyond status/diff.
Anti-generic-AI design discipline — bans, tells, and the slop test. Load for ANY new UI surface or visual redesign. Inspired by Impeccable (Apache 2.0).
Motion & animation discipline — purpose, performance, reduced-motion. Load when work involves animation, transitions or scroll effects.
Microcopy discipline — buttons, errors, empty/loading/success states, alt text. Voice and tone come from the project's memory, not from this skill.
| name | cost-discipline |
| description | FinOps discipline — cost allocation, budgets, commitment analysis, unit economics. Cloud-agnostic; vendor tooling from memory-long §stack. |
Cloud-agnostic (AWS/Azure/GCP mechanisms come from memory-long §stack). The fin-ops role's deep-dive: analyze broadly, edit narrowly, recommend with numbers.
Visibility (allocation works, costs attributable) → Optimization (rightsizing, commitments, waste removal) → Governance (budgets enforce, policies prevent). Don't optimize what you can't yet see — allocation first.
memory-long §conventions). Untagged = unattributable = invisible spend.Per environment AND per service · thresholds at 50/80/100% forecast · alerts route to owners (from tags), not a graveyard channel · budget actions (auto-stop non-prod, block scale-up) only in non-production without human gate.
Analyze before buying: coverage % and utilization % of existing commitments first · commit to the stable baseline, never the peak · start with shortest terms until usage history justifies longer · re-evaluate quarterly.
current cost → proposed change → estimated delta → risk. A rightsizing suggestion without numbers is an opinion. Reliability trade-offs (HA/DR reductions) always surface explicitly and go to architect.
Orphaned volumes/IPs/snapshots · oversized defaults never revisited · non-prod running 24/7 (schedule it) · storage on hot tiers with cold access patterns · anomaly detection on, with owner-routed alerts.