Install any skill in seconds. Free to start, no credit card required.
Get Started Free →capability to parse Simplicité logs from a raw `.txt` file, filter fields to reduce noise, and output the result as structured JSON.
.claude/skills/optimize-simplicite-logs/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | — | — |
| case-04 | ✗→✓ | ▲ Improved | — | — |
| case-08 | ✗→✓ | ▲ Improved | — | — |
| case-10 | ✗→✓ | ▲ Improved | — | — |
| case-03 | ✗→✓ | ▲ Improved | — | — |
This skill provides the capability to parse Simplicité logs from a raw .txt file, filter fields to reduce noise, and output the result as structured JSON. This is critical for optimizing AI context size (saving ~56% of tokens) and providing structured, predictable data for troubleshooting.
Use this skill when you need to:
.txt format.timestamp, level, body) from verbose multi-line log output.IMPORTANT: Instead of directly reading a raw .txt log file provided by the user using file read tools, you must use one of the log converter scripts (PowerShell or Python) to parse the file into a JSON format first, optionally extracting only the fields needed.
/scripts/SimpliciteLog2Json.ps1) or the Python script (/scripts/simplicite-log2json.py).Reduces the tokens consumed by large Simplicité logs by extracting only relevant log fields (e.g. body, timestamp, level) and discarding non-relevant structural log data (like app, endpoint, contextPath).
Properly captures stack traces and multiline errors inside the body field of the JSON structure, which a simple text search might miss.
If no output path is provided for the JSON file (e.g. omitting --output or -Output), the parsed JSON will be printed directly to stdout, allowing you to pipe the output to other tools.
After processing, the tool prints a summary to stderr (or console):
Processed: 123 entries, Skipped: 2 entriesConvert a log file to JSON, keeping only the most important fields:
shpython /absolute/path/to/skills/optimize-simplicite-logs/scripts/simplicite-log2json.py <input.txt> --include timestamp,level,body --output <output.json>
powershell/python /absolute/path/to/skills/optimize-simplicite-logs/scripts/SimpliciteLog2Json.ps1 -InputPath "<input.txt>" -Output "<output.json>" -Include "body,timestamp,level"
After generating the <output.json>, you can safely read the resulting file to perform your analysis.
.txt log files from Simplicité using standard text reading tools. Always convert them to JSON using the available scripts.--include (Python) or -Include (PowerShell) to restrict fields to what is absolutely necessary to diagnose the issue (usually timestamp,level,body).timestamp, app, level, endpoint, contextPath, event, user, class, function, rowId, body.sh# 1. Run the script to generate a minified JSON output in the current directory python /absolute/path/to/skills/optimize-simplicite-logs/scripts/simplicite-log2json.py logs.txt --include timestamp,level,body --output logs_minified.json # 2. Then read logs_minified.json to understand the context.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 20 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +64 percentage points is the difference between those two pass rates over the 20 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.