BF brain-system
人脑系统是一套面向 AI Agent / 智能助手的类人脑认知操作系统，用来把一个只会即时问答的 Agent，升级成更擅长长期协作、连续执行、记忆整理、任务复盘和自我维护的工作伙伴。它不是宣称 AI 拥有意识，而是把人脑中的注意力调度、工作记忆、长期记忆、执行控制、反馈学习、睡眠巩固、神经通路和抑制机制，转化成一套可执行的 Agent 工作流。系统会把目标、事实、用户偏好、历史经验、工具、技能、风险、假设、证据和下一步行动组织成可激活的认知网络；面对任务时先识别意图和优先级，激活最相关的信息，抑制噪声和重复失败路径，再通过最小验证、工具证据、状态记录、错误反馈和复盘更新自己的判断。它包含长期记忆卫生、任务队列管理、状态仪表盘、上下文检查点、周期性自维护、睡眠式整理、快速神经通路、稳健排障、执行控制、反思复盘、经验沉淀、风险边界和自我优化等模块。适合用于长期项目跟进、复杂任务拆解、多轮排障、知识库沉淀、偏好学习、上下文压缩、Agent 自维护、工作流稳定化、从错误中学习，以及让智能助手形成更一致、更可复用的做事风格。典型触发语包括“给自己装一个人脑系统”“增强人脑系统”“像人脑一样思考/学习/记忆”“长期记忆”“自我优化”“复盘”“注意力管理”“执行控制”“任务队列”“睡眠整理”“减少遗忘”“沉淀经验”等。
As a process F 42/100 · Will not run — References files that are not bundled: scripts/hot_reload_start.sh, scripts/hot_reload_stop.sh
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Dangerous commands
cmd-cron-mentionscripts/brain_fullness.py:28Mentions editing / listing crontab (string literal in code, not executed)cron=subprocess.run(['bash','-lc','crontab -l 2>/dev/null | grep -q OPENCLAW_BRAIN_SYSTEM'], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL).returncode==0
code literal
Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 10312 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/hot_reload_start.sh - warning
missing-refreference to a missing file: scripts/hot_reload_stop.sh
Process rating: all ten parameters 42/100
- 0Tools and files. 2 referenced file(s) missing: scripts/hot_reload_start.sh, scripts/hot_reload_stop.sh
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 40Execution cost. Instruction body is 10312 tokens: crowds the task out of the window
- 85Steps. 399 steps, 2 vague phrases
- 100Failures and branches. 20 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 50 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -31 of 12 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 561: enough signal without eating the budget
- +4Structure: 52 headings
- +3Step-by-step instructions: 399 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.