fallback-python-execution

Reliable Python execution workflow when execute_code_sandbox or shell_agent fail

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

72%

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

The content is actionable and well-organized with concrete executable examples and a clear step sequence, but it carries some redundant explanation and an implicit rather than inline error-recovery loop. No bundle files exist, which is appropriate for this simple skill.

Suggestions

Fold error recovery into the main flow as an explicit 'if run_shell reports an error, fix the script and re-run' checkpoint to strengthen the feedback loop.

Trim the 'Why This Works' section and drop the standalone Excel example since it duplicates the step-by-step pattern already shown, reducing token cost.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete examples, but the 'Why This Works' section and the redundant Excel example (which repeats the write+execute pattern already shown in the steps) add explanation Claude does not need, fitting the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	Provides fully concrete, copy-paste-ready guidance with explicit tool invocations (write_file with path/content) and runnable commands ("python /path/to/script.py"), plus a complete working Excel example, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	Steps 1-3 are clearly sequenced and include a verify step, but the main flow lacks an explicit fix-and-retry feedback loop (error recovery is only implicit via the separate troubleshooting table), fitting the 'steps listed but checkpoints implicit' anchor.	2 / 3
Progressive Disclosure	Single self-contained SKILL.md with no bundle files and well-organized sections (When to Use, Core Technique, Step-by-Step, Example, Tips, Troubleshooting); for a simple single-purpose skill with no need for external references, this clear sectioning earns a 3.	3 / 3
	Total	10 / 12 Passed

Description

75%

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 clearly states a niche fallback purpose with an explicit when-trigger, but leans on internal tool jargon for its triggers and lacks a list of concrete capabilities. It is third person and free of fluff.

Suggestions

Add concrete actions to the description (e.g. 'write Python scripts to files and run them to create spreadsheets, documents, and data files') to lift specificity.

Pair the tool-jargon triggers with natural user phrasing like 'run Python code' or 'execute Python scripts' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("Python execution workflow") but does not enumerate concrete actions (e.g. write scripts, execute files, generate spreadsheets); it describes the technique class rather than listing specific capabilities, matching the 'names domain and some actions, not comprehensive' anchor.	2 / 3
Completeness	Explicitly answers both what ("Python execution workflow") and when ("when execute_code_sandbox or shell_agent fail") with an explicit trigger clause, matching the 'clearly answers both what AND when with explicit triggers' anchor and avoiding the missing-Use-when cap.	3 / 3
Trigger Term Quality	Includes the relevant natural term "Python execution" alongside tool-specific jargon ("execute_code_sandbox", "shell_agent") that users would not naturally say; relevant keywords are present but common variations like 'run Python' or 'Python script' are missing, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The trigger is tied to the distinct niche of specific tool failures ("execute_code_sandbox or shell_agent fail"), making it unlikely to fire for unrelated Python skills and matching the 'clear niche with distinct triggers; unlikely to conflict' anchor.	3 / 3
	Total	10 / 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/fallback-python-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.