AA ai-usage-audit
Monthly AI usage retrospective and insights — pulls your recent conversation history, analyzes usage patterns across multiple dimensions, and generates a polished HTML report with an actionable improvement checklist. Trigger when the user says "AI usage audit", "usage review", "review my chats", "monthly retrospective", "analyze my conversations", "how have I been using AI", "月度回顾", "使用审计", "AI 使用回顾". Also trigger when the user wants to understand their AI usage efficiency, discover inefficiency patterns, or optimize human-AI collaboration. Even casual phrases like "what have I been doing lately" (referring to AI conversations) or "let's do a retro" should trigger this skill. Note: this skill requires an AI product with memory or chat history features (e.g. Claude Pro with memory).
As a process A 80/100 · Runs to the end — weak spots: progress reporting
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
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 4, column 14: description: Monthly AI usage retrospective and insights — pulls your recent co… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 80/100
- 0Progress reporting. Says nothing while it works
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 7 branches
- 85Steps. 70 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2945 tokens
- 100Running it twice. No mutating operations
- low 12 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)
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +3Description length 792: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 70 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.