Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From mcp-stata
Tail, read, or search Stata log files from previous commands or background tasks. Tails last 50 lines by default or shows search matches with 2-line context. Invoke with log path, task_id, or query.
npx claudepluginhub tmonk/mcp-stata --plugin mcp-stataHow this skill is triggered — by the user, by Claude, or both
Slash command
/mcp-stata:stata-logThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Parse the argument:
Guides log analysis with grep filters, bash pipelines, iterative refinement, and utility scripts to debug errors, incidents, and patterns efficiently.
Searches and analyzes logifai-captured development logs in NDJSON format using Read, Grep, Glob, Bash. Debugs errors, runtime issues, reviews activity via keywords, timestamps, stack traces, logifai:// URIs.
Analyzes JSONL and other log files using rg and jq: structured extraction, cross-log correlation, timeline reconstruction, pattern search.
Share bugs, ideas, or general feedback.
Parse the argument:
If a search term is provided, call:
stata_read_log(path=<first_token>, query=<second_token>, before=2, after=2, regex=False)
Display matching lines with context.
If no search term, call:
stata_read_log(path=<first_token>, tail_lines=50)
Display the last 50 lines of the log.
If the argument looks like a task_id (not a file path), call:
stata_read_log(task_id=<argument>, tail_lines=50)
If no argument is provided, tell the user to supply a log file path or task_id. These are returned by stata_run in the log_path field of the JSON response.
If the log is large and truncated, note the offset for reading more (the response includes the current byte offset).