AC usage-insights
Analyze how you use Claude Code - sessions, skills, tools, models, rhythm, automation, long-running sessions - and produce a minimal HTML report with insights and concrete recommendations that opens in the browser. Use when you say "analyze how I use Claude Code", "usage insights", "audit my sessions and skills", "which skills do I never use", or /usage-insights.
The skill parses Claude Code session logs and generates an HTML report with usage graphs: which skills collect dust, when you work, which models you favor. Promises concrete recommendations—what tools to drop, what to add.
Four files and a script totaling 2100 tokens. Inspection found one medium-level finding, but its nature isn't detailed in the description. Scores are solid: quality 93, safety 99. Process score 55 suggests the logic works, not perfectly. The report opens in a browser—convenient. Wide platform support: Claude, Cursor, Copilot, and seven others. Caveat: recommendations depend on log completeness; sparse logs mean a thin report. Install if you genuinely want to see which hundred skills are gathering dust on your shelf.
Analyze how you use Claude Code - sessions, skills, tools, models, rhythm, automation, long-running sessions - and produce a minimal HTML report with insights…
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 · 1
✓ No critical or high findings
Medium and low: 1
✓ Guard found no suspicious behaviour. 1 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 4. 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 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 30 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2100 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 365: enough signal without eating the budget
- +4Structure: 3 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.