AD Engineering Discipline
Production-grade AI coding discipline. Prevents the top 4 AI coding sins: acting without thinking, over-engineering, collateral damage, and vague execution. Triggers: 'engineering discipline', '过度工程', '反合理化', '三层一致性检查', 'AI coding rules', 'Karpathy 四规则', '写代码前先想', '手术刀修复'. Use when starting any coding task, before large refactors, or when catching yourself rationalizing shortcuts. Based on Karpathy's 4 rules + battle-tested additions (3-layer consistency checks, anti-rationalization, verification loops, surgical diffs). Works with Claude Code, Cursor, Copilot, OpenClaw, and any AI coding assistant. Triggers: 'engineering checklist'、'coding discipline'、'production quality'、'AI coding guardrails'、'开发纪律'。
As a process D 44/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 44/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (Engineering Discipline) differs from the folder (engineering-discipline)
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 32 steps
- 100Execution cost. Instruction body is 1242 tokens
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
- -214 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 711: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.