← 返回 Skills 市场
zurbrick

Cognition

作者 Don Zurbrick · GitHub ↗ · v2.0.1 · MIT-0
cross-platform ✓ 安全检测通过
363
总下载
2
收藏
2
当前安装
3
版本数
在 OpenClaw 中安装
/install cognition
功能描述
Practical memory architecture for OpenClaw agents. Helps agents remember commitments, retrieve context, prevent repeat mistakes, compile reusable procedures,...
使用说明 (SKILL.md)

Cognition

Cognition gives an OpenClaw agent a practical memory architecture: raw logs, durable knowledge, commitments, and reusable procedures.

Use it to make memory operational, not decorative.

Start Here

Install the scaffolding:

bash {baseDir}/scripts/install.sh

Then adopt it in 3 tiers.

Tier 1 — Core

Adopt this first. It is the smallest useful subset.

Core behavior

  1. Log important work to memory/YYYY-MM-DD.md
  2. Keep durable facts in MEMORY.md and deeper detail in memory/bank/*.md
  3. Track commitments in memory/FUTURE_INTENTS.md
  4. Add the protocol blocks from {baseDir}/references/protocols.md to your AGENTS.md

What Core gives you

  • recent-session continuity
  • a compact durable memory index
  • fewer dropped promises
  • a default place to put important facts instead of hoping the model remembers

Tier 2 — Recommended

Adopt this once Core is part of normal use.

Add these pieces

  • nightly staged consolidation via {baseDir}/references/consolidation-prompt.md
  • reusable procedures in memory/procedures/
  • procedure registry in memory/procedures/index.yaml
  • importance tagging from {baseDir}/references/protocols.md

Safety model

  • consolidation stages proposals before durable mutation
  • daily logs stay append-only
  • uncertain items stay tagged [NEEDS_REVIEW]
  • new procedures start as draft
  • promote procedures cautiously: draftreviewedtrusted

Tier 3 — Advanced

Only adopt this if Core and Recommended are already working.

Optional overlays

  • memory/bank/cross-references.md for linked retrieval
  • memory/KNOWLEDGE_MAP.md for coarse confidence tracking
  • memory/meta/gap_tracker.json for repeated retrieval misses
  • memory/meta/retrieval_log.json for retrieval analytics
  • weekly reflection via {baseDir}/references/weekly-reflection-prompt.md
  • hybrid retrieval tuning via {baseDir}/references/config.md

Advanced is for sharper retrieval and maintenance, not for replacing the Core system.

Core File Map

Always-on files

  • memory/YYYY-MM-DD.md — daily session log
  • MEMORY.md — durable fact index
  • memory/bank/*.md — deeper topic files
  • memory/FUTURE_INTENTS.md — commitments and deferred actions

Recommended files

  • memory/consolidation/YYYY-MM-DD-staged.md — staged memory proposals
  • memory/procedures/index.yaml — procedure registry
  • memory/procedures/*.md — reusable procedures

Advanced files

  • memory/KNOWLEDGE_MAP.md
  • memory/bank/cross-references.md
  • memory/meta/gap_tracker.json
  • memory/meta/retrieval_log.json
  • memory/summaries/YYYY-WNN.md

Reference Map

Read only what you need:

  • {baseDir}/references/protocols.md — protocol blocks to copy into AGENTS.md
  • {baseDir}/references/consolidation-prompt.md — nightly staged consolidation
  • {baseDir}/references/weekly-reflection-prompt.md — weekly reflection without direct mutation
  • {baseDir}/references/architecture.md — core systems, overlays, retrieval tiers, safety notes, file structure
  • {baseDir}/references/config.md — advanced hybrid retrieval tuning
  • {baseDir}/references/cognitive-science.md — theory appendix

Guardrails

  • Prefer staged proposals over silent durable-memory edits
  • Keep raw logs append-only
  • Keep MEMORY.md compact; move detail into memory/bank/
  • Treat procedure promotion as earned, not automatic
  • If retrieval fails, log the gap instead of inventing certainty
安全使用建议
This skill looks coherent for local memory management: it creates a workspace structure, provides consolidation/weekly prompts, and keeps changes staged before mutating durable files. Before installing: 1) Inspect templates (especially FUTURE_INTENTS.md) to confirm you accept any automated 'execute when triggered' semantics. 2) Run scripts/install.sh with an explicit workspace path (not the default) if you want control over where files are created. 3) If you enable nightly/weekly jobs, ensure the scheduled jobs run under an account with only the permissions you intend. 4) Restrict agent tool permissions (read/write/execute) if you do not want the agent to automatically act on FUTURE_INTENTS or perform file mutations without human review. 5) Back up any existing memory files you care about before installing. Overall the skill is internally consistent and does not request secrets or fetch remote code, but be cautious about enabling autonomous execution of intents and scheduled consolidation workflows.
功能分析
Type: OpenClaw Skill Name: cognition Version: 2.0.1 The 'cognition' skill provides a comprehensive and safety-conscious memory architecture for OpenClaw agents, focusing on session logging, durable knowledge storage, and procedural memory. The skill uses a local shell script (scripts/install.sh) to establish a directory structure and copy templates, with no evidence of network activity, data exfiltration, or unauthorized file access. The instructions for the agent (SKILL.md and various reference prompts) emphasize a 'staged' approach to memory updates, explicitly instructing the agent not to mutate core files like SOUL.md or AGENTS.md directly, which serves as a safeguard against accidental or malicious self-modification.
能力评估
Purpose & Capability
Name/description (memory architecture) matches the manifest: SKILL.md, reference docs, templates, and an install.sh that scaffolds local memory files. No unrelated credentials, binaries, or network endpoints are required.
Instruction Scope
Runtime instructions focus on creating and managing local memory files, staged consolidation, and weekly reports. They require the agent to read/write workspace files (explicitly required by the prompts). One item to watch: the FUTURE_INTENTS template language (‘Execute when triggered’, ‘Scanned every session start + every heartbeat’) implies the agent may act on intents — review how your agent runtime treats 'intents' to avoid unintended automated actions.
Install Mechanism
There is no remote install spec; the included scripts/install.sh is a local scaffold that copies templates into a workspace (default ~/.openclaw/workspace). The script is non-destructive (skips existing files) and contains no downloads or execution of remote code, but it will create files and directories under the chosen workspace path.
Credentials
The skill requests no environment variables, credentials, or config paths. Prompts mention using a 'recommended model' and read/write tools but do not demand secrets or external tokens — proportional to a local memory management skill.
Persistence & Privilege
always:false (no forced permanent inclusion). The skill's workflows expect scheduled jobs (cron) and agent tool access for read/write. Combined with the FUTURE_INTENTS template, this can enable automated behavior if the agent runtime is allowed to autonomously execute actions — consider limiting autonomous execution or reviewing intent-trigger rules.
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 cognition
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /cognition 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
v2.0.1
Tightened the runtime entrypoint, added a focused architecture reference, removed runtime clutter, and clarified the Core / Recommended / Advanced adoption path.
v2.0.0
v2.0.0: Council-reviewed rewrite. Critical: consolidation safety (staged diffs, provenance, append-only). 7→4 core systems, 3-tier adoption, neuroscience reframed, coarse confidence bands, procedure maturity states, degraded-mode docs, path fixes.
v1.0.0
Initial release: 7 biologically-inspired memory systems for OpenClaw agents. Nightly consolidation, metamemory, procedural memory, prospective memory, spreading activation, gap detection, weekly deep reflection.
元数据
Slug cognition
版本 2.0.1
许可证 MIT-0
累计安装 2
当前安装数 2
历史版本数 3
常见问题

Cognition 是什么?

Practical memory architecture for OpenClaw agents. Helps agents remember commitments, retrieve context, prevent repeat mistakes, compile reusable procedures,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 363 次。

如何安装 Cognition?

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

Cognition 是免费的吗?

是的,Cognition 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Cognition 支持哪些平台?

Cognition 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 Cognition?

由 Don Zurbrick(@zurbrick)开发并维护,当前版本 v2.0.1。

💬 留言讨论