AC troubleshoot
Investigate unexpected chat agent behavior by analyzing direct debug logs in JSONL files. Use when users ask why something happened, why a request was slow, why tools or subagents were used or skipped, or why instructions/skills/agents did not load.
A skill for parsing JSONL logs of agent behavior. Promises to show why a request was slow, which tools ran, why skills failed to load. One file, no syntax errors. Safety and quality scores at 100 and 87—checks passed without critical findings. Process score of 63 suggests the analysis logic works but leaves room. In practice: loads on all platforms from Claude to DeepSeek, reads logs and reconstructs what happened. The catch is that process score hints the skill doesn't always catch the right level of detail.
Worth installing. It solves a specific problem—debugging agent failures through logs—and has no errors. If you need to understand what broke in your request chain, this is a working tool.
Investigate unexpected chat agent behavior by analyzing direct debug logs in JSONL files.
As a process C 63/100 · Has gaps — weak spots: 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 · 0
✓ No critical or high findings
Files scanned: 1. 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 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4644 tokens
- 85Steps. 86 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (19 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 249: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 86 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.