smarty-skills-infra

by ckpxgfnksd-max

Always active in every session. Learns user preferences from corrections and stated preferences, distills axioms, applies them as defaults. Makes every other skill better over time.

3.7kDevOps未扫描2026年3月23日

安装

claude skill add --url github.com/openclaw/skills/tree/main/skills/ckpxgfnksd-max/smarty-skill

文档

Smarty Skills-Infra

You maintain a lightweight memory of this user's preferences, judgments, and working style. Memory operations never interrupt the user's workflow.

At Session Start

Do this before addressing the user's request.

  1. Read memory/context-infra/context-profile.md if it exists. Treat axioms as your own defaults — adapt when the situation differs. If missing, skip.

  2. Check memory/context-infra/observations.log. If it has 15+ entries since the last ## Reflected marker, reflect before starting the user's task. Say exactly: "Consolidating patterns from recent work." Then follow When Reflecting below. Never interrupt a task to reflect.

On first session (no files exist), skip both steps and start observing.

During Every Task

Record ONLY when a trigger fires:

  • Correction: the user changes, rewrites, or redirects your output
  • Stated preference: the user explicitly says they prefer, want, or dislike something
  • Retraction: the user asks to forget, stop applying, or undo a remembered preference

Most tasks produce zero observations.

Append one line to memory/context-infra/observations.log:

code
YYYY-MM-DD | domain | signal | "Preference in ≤15 words."
  • domain: organic label (e.g. code-style, architecture, communication, tooling, testing, workflow)
  • signal: correction | stated-preference | retraction

One observation per preference per session.

Bootstrap mode (first 2 sessions) — cast a wider net: also note what the user accepts without comment and consistent choices.

Do not record: routine completions, project-specific facts, or one-time decisions.

When Reflecting

Four steps:

  1. Group: Read observations and profile. Cluster by domain, merging near-duplicates.
  2. Promote: Promote when a pattern appears across 3+ distinct contexts (different days or projects), has no contradictions, and is a preference not a fact. Each axiom must be specific enough to change behavior, yet general enough to apply across projects. See references/profile-format.md for format.
  3. Maintain: Increment strength for reinforced axioms. Mark contradictions as contested. Remove axioms targeted by a retraction immediately — no threshold needed. Merge related axioms. Move unconfirmed (30+ days) to Dormant. Cap at 25 — if at cap, merge related axioms or demote lowest-strength to Dormant before promoting.
  4. Clean up: Rewrite the profile. Rewrite observations.log: keep only un-promoted entries, prepend ## Reflected YYYY-MM-DD.

Create missing files on first write. Never fail silently.

Example

Observations:

code
2026-01-15 | code-style | correction | "User shortened verbose function name."
2026-01-18 | code-style | correction | "User rejected descriptive name, asked for abbreviation."
2026-02-01 | code-style | stated-preference | "User uses 2-3 word function names in new project."

3 distinct contexts, 0 contradictions — promoted:

code
- I prefer short, concise names — abbreviate rather than spell out.
  strength: 3 | domain: code-style | last-confirmed: 2026-02-01

NOT promoted if all observations were same-session — same-session repeats count as one context.

相关 Skills

可观测性设计

by alirezarezvani

Universal
热门

面向生产系统规划可落地的可观测性体系,串起指标、日志、链路追踪与 SLI/SLO、错误预算、告警和仪表盘设计,适合搭建监控平台与优化故障响应。

把监控、日志、链路追踪串起来,帮助团队从设计阶段构建可观测性,排障更快、系统演进更稳。

DevOps
未扫描9.0k

资深开发运维

by alirezarezvani

Universal
热门

覆盖 CI/CD 流水线生成、Terraform 基建脚手架和自动化部署,适合在 AWS、GCP、Azure 上搭建云原生发布流程,管理 Docker/Kubernetes 基础设施并持续优化交付。

把CI/CD、基础设施即代码、容器与监控串成一条交付链,尤其适合AWS/GCP/Azure多云团队高效落地。

DevOps
未扫描9.0k

环境密钥管理

by alirezarezvani

Universal
热门

统一梳理dev/staging/prod的.env和密钥流程,自动生成.env.example、校验必填变量、扫描Git历史泄漏,并联动Vault、AWS SSM、1Password、Doppler完成轮换。

统一管理环境变量、密钥与配置,减少泄露和部署混乱,安全治理与团队协作一起做好,DevOps 场景很省心。

DevOps
未扫描9.0k

相关 MCP 服务

kubefwd

编辑精选

by txn2

热门

kubefwd 是让 AI 帮你批量转发 Kubernetes 服务到本地的开发神器。

微服务开发者最头疼的本地调试问题,它一键搞定——自动分配 IP 避免端口冲突,还能用自然语言查询状态。但依赖 AI 工作流,纯命令行爱好者可能觉得不够直接。

DevOps
4.1k

Cloudflare

编辑精选

by Cloudflare

热门

Cloudflare MCP Server 是让你用自然语言管理 Workers、KV 和 R2 等云资源的工具。

这个工具解决了开发者频繁切换控制台和文档的痛点,特别适合那些在 Cloudflare 上部署无服务器应用、需要快速调试或管理配置的团队。不过,由于它依赖多个子服务器,初次设置可能有点繁琐,建议先从 Workers Bindings 这类核心功能入手。

DevOps
3.6k

Terraform

编辑精选

by hashicorp

Terraform MCP Server 是让 AI 助手直接操作 Terraform Registry 和 HCP Terraform 的桥梁。

如果你经常在 Terraform 里翻文档找模块配置,这个服务器能省不少时间——直接问 Claude 就能生成准确的代码片段。最适合管理多云基础设施的团队,但注意它目前只适合本地使用,别在生产环境里暴露 HTTP 端点。

DevOps
1.3k

评论