AB study-notes
Generate polished HTML study notes AND full homework solutions for academic subjects, especially STEM (physics, math, chemistry, engineering, CS). Trigger on requests to create study notes, learning notes, a study guide, lecture notes, or self-study reference — e.g. "make me notes on X", "help me learn X", "summarize X for an exam". Also trigger when the user uploads a PDF textbook or course material and asks for review notes, 学习笔记, or 复习笔记. Also trigger when the user gives homework or exercise problems (作业题 / 习题) and wants either study notes for the chapter those problems test (re-learning the chapter through its exercises) or full step-by-step solutions as a standalone HTML page, with each problem and its figure shown (simple figures as inline SVG, complex or photo figures embedded from the original) and each solution collapsed. Output is one standalone HTML file with KaTeX math, color-coded sections, collapsible derivations and solutions, callouts, worked examples, and practice problems.
Generate polished HTML study notes AND full homework solutions for academic subjects, especially STEM (physics, math, chemistry, engineering, CS).
As a process B 67/100 · Nearly there — weak spots: result and completion, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7957 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7957 tokens
- 100Steps. 74 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (12 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1005: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -33 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Structure: 29 headings
- +3Step-by-step instructions: 74 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.