BF harness-skill-generator
引导用户从 0 构建一个基于 Harness 工程的 Skill。适用于具有一定复杂度的任务场景(多阶段、多分支、需要质检、需要状态持久化)。不适用于简单的单步任务或纯 prompt 优化。触发词:'创建 Skill'、'新建 Skill'、'做一个 Skill'、'构建 Skill'、'skill generator'、'harness skill'。
引导用户从 0 构建一个基于 Harness 工程的 Skill。适用于具有一定复杂度的任务场景(多阶段、多分支、需要质检、需要状态持久化)。不适用于简单的单步任务或纯 prompt 优化。触发词:'创建 Skill'、'新建 Skill'、'做一个 Skill'、'构建 Skill'、'skill…
As a process F 35/100 · Will not run — References files that are not bundled: 按需
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: 按需
Process rating: all ten parameters 35/100
- 0Tools and files. 1 referenced file(s) missing: 按需
- 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. 90 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2366 tokens
- 100Running it twice. No mutating operations
- low 12 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
- +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
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 178: enough signal without eating the budget
- +4Structure: 41 headings
- +3Step-by-step instructions: 90 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.