SKILLEMALL.ai
GitHub ↗ RU Sign in

BF 金字塔记忆架构

通用 AI Agent 记忆架构 Skill。采用"金字塔"分层结构:顶层(AGENTS.md)只放铁律级行为规则,中层(MEMORY.md/SOUL.md/HEARTBEAT.md)放业务规则和人格配置,底层(SKILL.md/TOOLS.md)放技术实现细节。适用于所有新建子 Agent 工作区初始化。触发场景:创建新 Agent、初始化工作区、记忆架构设计、规则录入引导、md 文件冗余检查、触发机制职责划分、任务归属标记检查、cron锚点格式检查、cron复杂度分级。

ClawHub Agent Skills author: popo67ll v3.6.0 MIT-0 2 files body ≈ 3 423 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

As a process F 28/100 · Will not run — References files that are not bundled: scripts/*.js, templates/AGENTS.md, templates/MEMORY.md

ReferenceAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
81/100
safety, quality, tests
Safety 60%
100
Quality 40%
53
Run on models
none yet
Process rating
F
28/100
Will not run
References files that are not bundled: scripts/*.js, templates/AGENTS.md, templates/MEMORY.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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 · 0

✓ No critical or high findings

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: scripts/*.js
  • warning missing-ref reference to a missing file: templates/AGENTS.md
  • warning missing-ref reference to a missing file: templates/MEMORY.md
  • warning missing-ref reference to a missing file: templates/SOUL.md
  • warning missing-ref reference to a missing file: templates/IDENTITY.md
  • warning missing-ref reference to a missing file: templates/USER.md
  • warning missing-ref reference to a missing file: templates/TOOLS.md
  • warning missing-ref reference to a missing file: templates/HEARTBEAT.md

Process rating: all ten parameters 28/100

Will not run. References files that are not bundled: scripts/*.js, templates/AGENTS.md, templates/MEMORY.md
  • 0Tools and files. 8 referenced file(s) missing: scripts/*.js, templates/AGENTS.md, templates/MEMORY.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 3 mutating operations with no state check
  • 40Consistency. Frontmatter name (金字塔记忆架构) differs from the folder (pyramid-memory-architecture)
  • 100Steps. 82 steps
  • 100Execution cost. Instruction body is 3423 tokens

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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -225 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 239: enough signal without eating the budget
  • +4Structure: 26 headings
  • +3Step-by-step instructions: 82 items
  • +4Has examples (14 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.

External checks

ClawHub: suspicious
The skill is a coherent memory-architecture guide, but it includes broad workspace scanning, file rewriting/deletion guidance, cron setup, and GitHub push steps with inconsistent confirmation boundaries.
LLM: suspicious (medium) · VirusTotal: · 6 Aug 2026