verified-script-execution

Fallback workflow for reliable file creation and verification when automated code execution fails

Quality

68%

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/verified-script-execution/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

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

The content is highly actionable with executable commands and a clear verified workflow, and it is well-structured for a single-file skill. Its main weakness is conciseness, as it explains shell basics Claude already knows and could be tightened without losing clarity.

Suggestions

Cut explanations of basics Claude already knows (e.g. the prose around `pwd`/`ls` and the rationale for `chmod +x`) and let the commands speak for themselves.

Condense or move the full "Complete Example" block to a reference file, keeping only the minimal heredoc pattern inline in SKILL.md.

Tighten the "Efficiency Tips" and "Common Pitfalls" lists to the few highest-value items to reduce token weight.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but it over-explains basics Claude already knows (e.g. "Always confirm your current location before creating any files" justifying `pwd`, and heredoc/`chmod` mechanics), landing in the mostly-efficient-but-could-be-tightened band.	3 / 5
Actionability	It provides fully executable, copy-paste-ready bash commands and a complete worked example covering the common cases (heredoc creation, chmod, run, verify), matching the fully-executable anchor.	5 / 5
Workflow Clarity	A clear four-step sequence with an explicit verification step (Step 4) and a full worked example; validation checkpoints are present, though the verify step is somewhat advisory rather than a hard fail-fast gate, placing it just below the 5 anchor.	4 / 5
Progressive Disclosure	The skill is a single self-contained SKILL.md with no bundle files and well-organized section headers; structure is good with no nested references, but at ~150 lines some of the complete-example and tips content could be trimmed, so it sits at 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Description

62%Weight 40%Scale 1-5

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 conveys a clear purpose and an explicit activation condition, but its trigger vocabulary is narrow and its action list is only minimally specified. It is distinct enough to avoid most conflicts yet not as comprehensive as top-tier examples.

Suggestions

Add natural trigger phrases users would actually say, e.g. "Use when code execution fails, the sandbox errors out, or shell commands repeatedly error without producing files."

List more concrete actions to lift specificity, e.g. "create files via heredoc, make them executable, run them, and verify outputs".

Optionally name the failing tools explicitly (execute_code_sandbox, shell_agent) in the description so the trigger is unmistakable.

Dimension	Reasoning	Score
Specificity	"reliable file creation and verification" names the domain and two concrete actions (create, verify) but offers no broader coverage, matching the anchor for 1-2 concrete actions.	3 / 5
Completeness	It states a clear "what" (fallback workflow for file creation/verification) and an explicit "when" (when automated code execution fails); the "when" is present and concrete but could be more specific, fitting the 4 anchor.	4 / 5
Trigger Term Quality	"when automated code execution fails" provides one relevant trigger phrase but lacks common natural variations a user would actually say (e.g. "sandbox error", "code failed to run"), so keyword coverage is partial.	3 / 5
Distinctiveness Conflict Risk	Tying the skill to automated-execution-tool failure gives it a mostly distinct niche with only minor overlap risk against general file-handling skills, matching the 4 anchor rather than 3 or 5.	4 / 5
	Total	14 / 20 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/verified-script-execution/SKILL.md
Commit: 3827781

Reviewed: 5 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.