AD token-optimizer
AI Agent 项目的 Token 消耗审计与系统性优化。提供四层诊断框架、六步优化 SOP、 自动化审计脚本。适用于任何使用 Rules + Memory + Knowledge + Skills 架构的 AI Agent 项目（如 CodeBuddy、Cursor、Windsurf 等）。 This skill should be used when users mention token optimization, context size reduction, prompt cost control, or AI agent operational efficiency. Triggers: token优化, token节约, token审计, 省token, 上下文膨胀, context太大, 对话成本, rules瘦身, memory清理, 知识库精简, 降低开销, token consumption, optimize tokens, reduce context, context optimization, prompt cost.
As a process D 49/100 · 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: 5. 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 49/100
- 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
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (token-optimizer) differs from the folder (token-use-optimizer)
- 100Tools and files. No external tools needed
- 100Steps. 4 steps
- 100Execution cost. Instruction body is 644 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 482: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 4 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.