AF one-step-evolution
Use when you need to stand up or standardize a fresh OpenClaw setup as the Fire Dragon Fruit Architecture: one strong main, one isolated rescue, layered file memory, project truth docs, heartbeat, isolated cron, official Feishu integration, Ollama memory embeddings, and a durable long-running operating model. Search intents include OpenClaw architecture, OpenClaw memory, OpenClaw heartbeat, OpenClaw cron, OpenClaw Feishu, OpenClaw Ollama, OpenClaw rescue, Fire Dragon Fruit Architecture, 火龙果架构, 持续进化, 分层记忆, 调度任务, 长期记忆, 自动调度, 飞书机器人, 个人经营系统, 主脑架构, and personal operating system.
As a process F 64/100 · Will not run — References files that are not bundled: assets/templates/workspace/skills/
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- 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
-
medium Broad scope
meta-agent-memory-dumpassets/templates/rescue/MEMORY.mdAgent memory / workspace files bundled with the skill (7) — likely a workspace dump with personal data or tokensassets/templates/rescue/MEMORY.md, assets/templates/rescue/SOUL.md, assets/templates/workspace/HEARTBEAT.md, assets/templates/workspace/IDENTITY.md, assets/templates/workspace/MEMORY.md
Files scanned: 23. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: assets/templates/workspace/skills/
Process rating: all ten parameters 64/100
- 0Tools and files. 1 referenced file(s) missing: assets/templates/workspace/skills/
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 9 mutating operations with no state check
- 85Steps. 131 steps, 1 vague phrases
- 100Result and completion. Output format and completion criterion are stated
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 10 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2910 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 580: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 131 items
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.