python-debug-execution

Debug Python scripts with proper error surfacing and working directory verification

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/python-debug-execution/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is highly actionable with executable code and a clear sequenced debugging workflow, but is somewhat verbose (explaining known concepts and repeating commands) and keeps everything inline with no progressive-disclosure references. Tightening the rationale and trimming repetition would lift conciseness toward 3.

Suggestions

Trim the "Why this works" bullets to avoid explaining concepts Claude already knows (stream merging, exit-code semantics); keep only non-obvious rationale.

Avoid repeating the identical `python3 script.py 2>&1 ; echo Exit code: $?` command in multiple sections; define it once and reference it.

Consider splitting the diagnostic boilerplate or failure-pattern table into a referenced file if the skill grows, to support progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable code, but pads with "Why this works" bullets that explain concepts Claude knows (e.g. that 2>&1 merges streams, that exit 0 means success) and repeats the same bash command verbatim, matching the score-2 anchor.	2 / 3
Actionability	It provides fully executable bash and Python snippets that are copy-paste ready, plus a concrete failure-pattern table mapping symptoms to debug clues, matching the score-3 anchor of fully executable, specific examples.	3 / 3
Workflow Clarity	The Step 1 -> Step 2 -> Step 3 workflow is clearly sequenced with an explicit analysis checkpoint listing what to look for (tracebacks, exit code, missing files); this is a diagnostic pattern rather than a destructive/batch operation, so the missing fix-loop cap does not apply.	3 / 3
Progressive Disclosure	At ~94 lines with no bundle files and no external references, all content is inline; sections are reasonably organized but the length suggests content that could be split out, matching the score-2 anchor rather than a cleanly referenced score-3 structure.	2 / 3
	Total	10 / 12 Passed

Description

50%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is clear and domain-specific but lacks an explicit use-trigger and broad natural-language keyword coverage, capping its completeness and trigger quality at 2. It is distinguishable but generic enough to risk overlap with general debugging skills.

Suggestions

Add an explicit "Use when..." trigger clause, e.g. "Use when a Python script fails with an unclear error, a traceback, or a FileNotFoundError."

Broaden natural trigger terms to include "traceback", "exit code", and "Python errors" so users' phrasings match more reliably.

Narrow the niche wording to reduce overlap with generic debugging skills, e.g. frame it around diagnosing Python execution failures specifically.

Dimension	Reasoning	Score
Specificity	"Debug Python scripts with proper error surfacing and working directory verification" names the Python domain and two concrete actions (error surfacing, working directory verification), but does not list the comprehensive multiple actions of the score-3 anchor.	2 / 3
Completeness	It states what the skill does but has no "Use when..." or equivalent explicit trigger guidance, so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Terms like "Debug Python scripts", "error surfacing", and "working directory" are relevant and somewhat natural, but common variations users might say (e.g., "traceback", "exit code", "Python errors") are missing, matching the score-2 anchor.	2 / 3
Distinctiveness Conflict Risk	The Python-debugging niche is somewhat specific but broad enough to overlap with general debugging skills, and there are no distinct trigger phrases, matching the score-2 anchor rather than the clearly-niched score-3.	2 / 3
	Total	8 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/python-debug-execution/SKILL.md
Commit: c5a9c4b

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.