BF math-screenshot-to-giscus
把数学教材截图或文本(中文,含公式)转成 giscus/GitHub Discussion 可渲染的版本。截图用 vision_analyze 逐字确认符号; 文本输入一般直接转格式(不做分析),输出 GitHub MathJax 兼容 Markdown。
把数学教材截图或文本(中文,含公式)转成 giscus/GitHub Discussion 可渲染的版本。截图用 visionanalyze 逐字确认符号; 文本输入一般直接转格式(不做分析),输出 GitHub MathJax 兼容 Markdown。
As a process F 37/100 · Will not run — References files that are not bundled: scripts/verify-giscus-md.py, scripts/_test_trap7.py, references/giscus-rendering-verification.md
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: 2. 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: scripts/verify-giscus-md.py - warning
missing-refreference to a missing file: scripts/_test_trap7.py - warning
missing-refreference to a missing file: references/giscus-rendering-verification.md - warning
missing-refreference to a missing file: templates/mathjax-test-page.html - warning
missing-refreference to a missing file: references/github-markdown-api-quick-test.md
Process rating: all ten parameters 37/100
- 0Tools and files. 5 referenced file(s) missing: scripts/verify-giscus-md.py, scripts/_test_trap7.py, references/giscus-rendering-verification.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
- 20When it triggers. No condition that starts the skill
- 100Steps. 38 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2669 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low The response is described with custom markup (6 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -221 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 128: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.