AC karpathy-principles
编程原则技能，源于 Andrej Karpathy 的 LLM 编程四大通病与核心原则。 Use when: (1) writing or reviewing code, (2) user asks to build/create/refactor a feature, (3) code is becoming over-engineered, (4) unsure about what to implement and should ask first, (5) any non-trivial coding task. Not for: one-liner fixes, obvious typos. This skill keeps coding precise, minimal, and goal-driven.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 52/100
- 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
- 40Consistency. Frontmatter name (karpathy-principles) differs from the folder (precise-coding-principles)
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 15 steps
- 100Execution cost. Instruction body is 269 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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 363: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 15 items
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.