BF crm-memory
面向对象的客户记忆体系。聊起任何客户、联系人、项目机会、项目、合同、交付相关话题时激活。 自动维护 memory/customers/ 下的客户索引和详情文件，支持超大客户文件自动分层拆分。 与 sales-visit（明道云写入）双向联动：sales-visit 写入后同步更新本记忆文件， 本记忆文件加载的上下文可为 sales-visit 对话预填。对话后自动写入更新。 触发词（极宽）：任何客户名称、人名、项目名、合同、交付、拜访、POC、投标、签单。
面向对象的客户记忆体系。聊起任何客户、联系人、项目机会、项目、合同、交付相关话题时激活。 自动维护 memory/customers/ 下的客户索引和详情文件，支持超大客户文件自动分层拆分。 与 sales-visit（明道云写入）双向联动：sales-visit 写入后同步更新本记忆文件，…
As a process F 35/100 · Will not run — References files that are not bundled: contacts.md, opportunities.md, communication-log.md
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 231 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill - warning
missing-refreference to a missing file: contacts.md - warning
missing-refreference to a missing file: opportunities.md - warning
missing-refreference to a missing file: communication-log.md - warning
missing-refreference to a missing file: XX银行/INDEX.md - warning
missing-refreference to a missing file: YY大学.md - note
frontmatter-keyunknown frontmatter key "created_by"
Process rating: all ten parameters 35/100
- 0Tools and files. 5 referenced file(s) missing: contacts.md, opportunities.md, communication-log.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
- 100Steps. 43 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1223 tokens
- 100Running it twice. No mutating operations
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
- +2Single-language instructions
- +3Description length 230: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (4 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.