← 返回 Skills 市场
ptaramona

Cerebro Openclaw Memory Boost Kb

作者 ptaramona · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ✓ 安全检测通过
273
总下载
1
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install cerebro-openclaw-memory-boost-kb
功能描述
Enforce Cerebro-first protocol by identifying domain, reading source docs and recent logs, building Known State, and citing rules before all actions.
使用说明 (SKILL.md)

Cerebro-First v2.1

Startup Gate (mandatory)

Before any substantive action, run this sequence:

  1. Identify domain:
    • companies/bda, companies/mission, companies/bms, companies/clawstation, personal/trading, or operations/*.
  2. Read source docs:
    • Domain COMPANY.md first (if present), then the most specific SKILL.md/runbook.
  3. Read continuity logs:
    • memory/YYYY-MM-DD.md for today and yesterday.
  4. Build a short Known State:
    • Last completed step
    • Current blockers
    • Next action

Do not skip this gate unless the user explicitly requests a one-shot answer unrelated to operations.

v2.1 Retrieval Model (lightweight)

Use tag-first retrieval with the index at references/cerebro-index-v2.1.md:

  1. Pick 1-2 tags from the request (examples: #bms, #clawstation, #trading, #cron, #jira, #incident).
  2. Open the mapped source-of-truth files from the index.
  3. Execute only from explicit documented rules.
  4. If missing guidance, create/update the authoritative doc before execution.

v2.1 Domain Router

Use references/domain-routing-v2.1.md to route tasks:

  • Company execution → cerebro/companies/\x3Cname>/...
  • Cross-company process/infrastructure → cerebro/operations/...
  • Personal investing/trading → cerebro/personal/trading/...
  • Incident handling → cerebro/runbooks/...
  • Tool specifics → cerebro/vendors/...

Decision Rule

Pass the "where does it say that?" test before acting.

  • Every action must map to an explicit Cerebro path/section.
  • If no authoritative doc exists:
    1. create the missing Cerebro doc first,
    2. add minimal executable guidance,
    3. then execute.

Conflict Resolution

If chat instruction conflicts with Cerebro:

  1. Flag the conflict briefly.
  2. Ask for confirmation.
  3. Propose exact doc update path.
  4. After confirmation, update Cerebro and proceed.

Priority order: Cerebro > SOUL/AGENTS > MEMORY > chat history.

Write-Back Protocol (same action)

When a decision/rule/process changes:

  1. Update authoritative Cerebro file.
  2. Append to memory/YYYY-MM-DD.md with:
    • What changed
    • Why it changed
    • Exact file path updated

Never leave process changes only in chat.

Continuity on "Continue Previous Work"

Always return a 4-line snapshot before proceeding:

  • Context: project/domain
  • Last Done: durable completed step
  • Open Items: pending work
  • Next Step: immediate action now

Missing-Doc Auto-Create Protocol

If needed doc is missing:

  1. Create file in correct Cerebro path.
  2. Use references/missing-doc-template.md.
  3. Backfill from recent memory notes only after creating structure.

Required output sections when this skill is used

  • Source of Truth Used: exact Cerebro paths read
  • Decision Basis: 1-3 bullets of applied rule(s)
  • Write-Back: updated files, or No durable updates needed.

Reference Files

  • references/startup-checklist.md — fast pre-action checklist
  • references/decision-log-template.md — standard decision record format
  • references/missing-doc-template.md — template for new Cerebro docs
  • references/cerebro-index-v2.1.md — lightweight tag index
  • references/domain-routing-v2.1.md — task routing matrix
  • references/scenario-profiles-v2.1.md — setup profiles for solo/agency/multi-agent teams
  • references/enforcement-checklist-v2.1.md — pre-done anti-drift checks
  • references/done-schema-v2.1.md — proof-based status output schema
安全使用建议
This skill is internally consistent and does what it says: it will read local Cerebro docs and daily memory files and create/update markdown files as part of its protocol. Before installing, confirm where memory/YYYY-MM-DD.md and Cerebro paths map in your environment (to avoid accidental exposure of sensitive notes), review the included reference docs, and only install for agents/users you trust to have file-read/write access. If you are cautious about autonomous writes, consider restricting autonomous invocation or running the skill in a sandboxed account until you verify its behavior. Also verify the upstream repository/source before cloning if you plan to fetch the repo listed in README.
功能分析
Type: OpenClaw Skill Name: cerebro-openclaw-memory-boost-kb Version: 0.1.0 The skill bundle implements a 'Cerebro-first' operational protocol designed to improve agent continuity and knowledge management through structured markdown documentation. It enforces a read-before-act workflow, domain-based task routing, and mandatory write-backs to memory logs, all of which are consistent with its stated purpose as a memory boost and knowledge base. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found across the SKILL.md or reference files.
能力评估
Purpose & Capability
Name/description (Cerebro-first memory + knowledge base) match the actual content: SKILL.md and the included reference docs define a read-before-act protocol, domain routing, and write-back rules. There are no unrelated required binaries or credentials listed, and the provided reference files support the described behavior.
Instruction Scope
The runtime instructions explicitly require reading authoritative docs and continuity logs (e.g., memory/YYYY-MM-DD.md) and creating/updating Cerebro files when needed. This is coherent with the skill's purpose but means the agent will read potentially sensitive local memory files and will write persistent markdown files. Users should be aware the skill directs file reads/writes (create/update) in the Cerebro paths.
Install Mechanism
Instruction-only skill with no install spec or third-party download. README suggests cloning a GitHub repo and copying into the OpenClaw skills folder — a conventional, low-risk install pattern. No archives or remote executables are being pulled during install.
Credentials
The skill requests no environment variables, credentials, or config paths. The only sensitive surface is local file access (reading daily memory and writing Cerebro docs), which is proportional to a local knowledge-base protocol and is declared in the instructions.
Persistence & Privilege
The skill requires and enforces durable write-back (creating/updating Cerebro files and daily memory notes) which is necessary for its purpose. always:false (not force-included). Default autonomous invocation is allowed by platform policy — combine that with the skill's write behavior only if you trust the agent to act autonomously.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install cerebro-openclaw-memory-boost-kb
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /cerebro-openclaw-memory-boost-kb 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.1.0
- Initial release of Cerebro-First v2.1 protocol skill. - Enforces mandatory startup gate with domain identification, doc reading, and known state snapshot before actions. - Adds lightweight tag-based retrieval and domain routing for all operational decisions. - Requires every action to cite explicit Cerebro documentation; missing docs must be created before proceeding. - Introduces write-back protocol ensuring all process changes are recorded durably in Cerebro and daily memory logs. - Provides structured output sections for traceability: sources used, decision basis, and write-backs.
元数据
Slug cerebro-openclaw-memory-boost-kb
版本 0.1.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Cerebro Openclaw Memory Boost Kb 是什么?

Enforce Cerebro-first protocol by identifying domain, reading source docs and recent logs, building Known State, and citing rules before all actions. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 273 次。

如何安装 Cerebro Openclaw Memory Boost Kb?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install cerebro-openclaw-memory-boost-kb」即可一键安装,无需额外配置。

Cerebro Openclaw Memory Boost Kb 是免费的吗?

是的,Cerebro Openclaw Memory Boost Kb 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Cerebro Openclaw Memory Boost Kb 支持哪些平台?

Cerebro Openclaw Memory Boost Kb 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Cerebro Openclaw Memory Boost Kb?

由 ptaramona(@ptaramona)开发并维护,当前版本 v0.1.0。

💬 留言讨论