AF memo-bridge
This skill should be used when the user wants to export, import, backup, migrate, or transfer AI memory/context between different AI tools. It handles memory extraction from tools like CodeBuddy, OpenClaw, Hermes Agent, Claude Code, and Cursor, and can import into any of these tools plus ChatGPT, Doubao (豆包), and Kimi. Trigger phrases include "记忆迁移", "导出记忆", "备份记忆", "memory migration", "memory export", "transfer context", "switch AI tool", "换工具", "迁移到", as well as any mention of moving preferences, context, or history between AI assistants.
As a process F 51/100 · Will not run — References files that are not bundled: references/adapter-guide.md, references/format-spec.md
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 · 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
missing-refreference to a missing file: references/adapter-guide.md - warning
missing-refreference to a missing file: references/format-spec.md
Process rating: all ten parameters 51/100
- 0Tools and files. 2 referenced file(s) missing: references/adapter-guide.md, references/format-spec.md
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 19 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1738 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
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
- -216 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 546: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 19 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.