AB token-saver
Five-phase token audit & optimization framework for OpenClaw: Discover → Prioritize (3D matrix) → Optimize (9 category techniques) → Validate → Monitor. Universal; adapt via appendix. Trigger: "省点 token", "token 优化", "token saver", "token audit", "检查 token 消耗" Version history: v1.0 (2026-05-03) — 初始框架, 6 categories v1.5 (2026-05-04) — +G Provider Caching, +H Behavioral Discipline v2.0 (2026-05-12) — +I Context Engineering v2.1 (2026-05-14) — +J Intelligent Model Routing (OpenSquilla) + Quick Start guide, +Category Decision Tree + Monitor phase checkpoints
As a process B 67/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, consistency
The same skill appears in 1 more place: ClawHub
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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6902 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 67/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (token-saver) differs from the folder (tsaver)
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 6902 tokens
- 100Tools and files. No external tools needed
- 100Steps. 67 steps
- 100Failures and branches. 7 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
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)
- -215 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 605: enough signal without eating the budget
- +4Structure: 49 headings
- +3Step-by-step instructions: 67 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.