shell-agent-file-workflow

Delegate file generation to shell_agent when direct tools fail, with systematic file location and retrieval

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/shell-agent-file-workflow/SKILL.md

Quality

Content

57%

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

The content is well-organized with executable locate/copy commands and a clear three-step sequence, but the core delegation step is a non-executable placeholder and the workflow lacks an explicit in-flow validation checkpoint. The lowest dimensions are actionability and workflow_clarity.

Suggestions

Replace the placeholder `shell_agent(task="...")` with the actual tool invocation syntax (or clearly state it is illustrative) and provide one fully concrete worked example without `[file type]`-style substitutions.

Add an explicit validation checkpoint after file location (e.g., verify the file opens/is non-empty before copying) rather than leaving verification only in Tips.

Trim the redundant worked examples or the 'The agent will:' bullets to remove content that restates the workflow steps.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and well-sectioned, but the two worked examples largely restate the three steps already shown and the 'The agent will: ...' bullets over-explain shell_agent's internal behavior, so it could be tightened.	2 / 3
Actionability	Concrete, executable commands are given for locating and copying files (`find ... -type f`, `cp ... ./`, `-mmin -10`), but the central delegation step uses placeholder `shell_agent(task=...)` syntax with template substitutions like `[file type]`, which is not copy-paste executable.	2 / 3
Workflow Clarity	The delegate -> locate -> copy sequence is clearly ordered, but this autonomous-generation workflow has no inline validation checkpoint; verification is relegated to Tips/Troubleshooting, and the rubric caps such batch/fragile workflows at 2 without explicit in-flow validation.	2 / 3
Progressive Disclosure	This is a self-contained single-purpose skill with no external bundle files and no references; its clean sectioning (When to Use, Workflow Steps, Example, Tips, Troubleshooting) meets the simple-skill carve-out for a top score.	3 / 3
	Total	9 / 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 conveys the skill's purpose and a trigger condition, but it stays generic, uses procedural rather than natural trigger terms, and lacks an explicit 'Use when...' clause. It sits solidly at the midpoint across all dimensions.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers users would say (e.g., file creation tools failing, needing an agent to generate complex files).

Replace procedural phrasing with natural user-facing keywords (e.g., 'generate PowerPoint', 'create PDF report', 'recover generated files').

List concrete actions to lift specificity (e.g., 'Generate PPTX, DOCX, and PDF files; locate and copy output to the working directory').

Dimension	Reasoning	Score
Specificity	It names a domain and several actions ("Delegate file generation to shell_agent", "file location and retrieval") but describes them at a high level rather than listing multiple distinct concrete actions, so it stops short of the comprehensive-action anchor.	2 / 3
Completeness	It states what the skill does and gives a conditional trigger ("when direct tools fail"), but lacks an explicit 'Use when...' clause; per the guidelines, a missing explicit trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like "file generation", "direct tools fail", and "file location" are relevant but procedural/technical rather than the natural phrasing a user would say, and common variations are missing.	2 / 3
Distinctiveness Conflict Risk	The combination of shell_agent delegation plus file retrieval is a recognizable niche, but "file generation" is broad and could overlap with other document- or file-creation skills.	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/shell-agent-file-workflow/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.