AC proxy-token-optimizer
Optimize LLM token usage and API costs for the openclaw-manager proxy platform. Provides model-tier routing (route simple prompts to glm-4.7-flashx instead of glm-4.7), heartbeat cost reduction (force heartbeat calls to use the cheapest model with optimized intervals), context lazy loading (generate optimized AGENTS.md that loads only necessary context files per prompt complexity), and platform-level usage analytics (query real usage_records from PostgreSQL to generate reports and quota-matching advice). Use this skill whenever the user mentions token optimization, reducing API costs, model routing, heartbeat optimization, context loading strategy, usage reports, quota analysis, or anything related to saving money on LLM API calls in the openclaw-manager project. Also trigger when the user asks about which model to use for different task types, or wants to analyze per-instance token consumption patterns.
As a process C 61/100 · 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: 9. 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 61/100
- 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
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 11 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1591 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
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)
- +3Description length 917: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 14 headings
- +3Step-by-step instructions: 11 items
- +4Has examples (7 code blocks)
- +3All 6 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.