BB ipython-analyst
Run Python interactively to analyze data, debug code, profile performance, validate schemas, process large files, and inspect ASTs. Use this whenever the user needs hands-on Python execution — debugging a script, profiling slow code, regex stress-testing, parsing CSV/Excel/JSON, building ML baselines, analyzing logs, validating schemas, diffing outputs between code versions, visualizing ASTs, detecting file formats, or running distributed/parallel jobs. Strong triggers include phrases like "debug this script", "profile my function", "this regex hangs on", "validate this JSON against a schema", "diff the output of these two versions", "what format is this file", "parse this log", "find the bottleneck", "stress test this parser", or any request to execute Python code interactively to investigate a concrete problem. Prefer this over the charts skill when the deliverable is a diagnostic answer (a fix, a profile, a validation report) rather than a polished chart; prefer docx/xlsx/pdf skills when the user wants a written document or spreadsheet as the final artifact.
Run Python interactively to analyze data, debug code, profile performance, validate schemas, process large files, and inspect ASTs.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, running it twice
How to improve
- Shorten the description to 1024 characters.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
low Dangerous commands
cmd-eval-dynamicSKILL.md:35Dynamic code execution from decoded/untrusted input (quoted — discussed, not commanded)This is safer than `exec(open(...).read())` because Python's import machinery validates the file is a proper module, caches it, and won't re-execute on subsequent imports. The scripts directory contai
quoted -
low Dangerous commands
cmd-eval-dynamicSKILL.md:238Dynamic code execution from decoded/untrusted input (quoted — discussed, not commanded)11. **`exec(open(...).read())` removed from all code examples** (was LP3 + SQP-2). Replaced with `sys.path.insert(0, SCRIPTS); from <name> import <symbol>` — Python's import machinery validates the fi
quoted
Files scanned: 27. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1077 chars, limit 1024
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (python, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4466 tokens
- 85Steps. 36 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 12 top-level sections: this looks like several domains in one skill
- medium 4 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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)
- +3Description length 1077: 120–800 characters recommended
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Structure: 25 headings
- +3Step-by-step instructions: 36 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
- +3All 17 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.