BF relay-knowledge-cli
Use relay-knowledge local CLI for repository CodeSpec/Knowledge map governance and GraphRAG: initialize, validate, route, and update codespec/codespec-map.yaml and knowledge/knowledge-map.yaml; read snapshot-bound repo business/software/view/context models for specs and coding; run durable update/status/impact loops after commits. Use for 目录化知识管理, 知识地图初始化, 业务术语与技术映射, git commit知识库增量更新, 用户代码查询kind/查询类型, 图关系, 调用关系, 导入依赖, SDK/API, definitions, references, usage, impact. Prefer graph CLI before grep/rg unless unavailable, unindexable, inexpressible, or raw regex is required. Do not use for MCP/ACP setup or protocol access.
As a process F 53/100 · Will not run — References files that are not bundled: assets/linux-x86_64/relay-knowledge, assets/windows-x86_64/relay-knowledge.exe
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6457 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: assets/linux-x86_64/relay-knowledge - warning
missing-refreference to a missing file: assets/windows-x86_64/relay-knowledge.exe
Process rating: all ten parameters 53/100
- 0Tools and files. 2 referenced file(s) missing: assets/linux-x86_64/relay-knowledge, assets/windows-x86_64/relay-knowledge.exe
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 6457 tokens
- 100Steps. 23 steps
- 100Failures and branches. 7 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
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (7 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 626: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (23 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.