CtrlK
BlogDocsLog inGet started
Tessl Logo

shell-agent-file-workflow

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

55

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

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

Quality

Content

60%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 skill body is well-structured with executable commands and concrete examples for a self-contained workflow. Its main weakness is the missing validation/verification checkpoint in the workflow and some redundancy across the example sections.

Suggestions

Insert an explicit validation step between locating and copying the file, e.g. 'Verify the file is non-empty and openable before copying' with a concrete check command.

Consolidate the PowerPoint and PDF examples into a single parameterized example to remove redundancy and save tokens.

Replace the [file type] / [specific content] placeholders in Step 1 with a concrete shell_agent call, keeping the generic form only as a secondary note.

DimensionReasoningScore

Conciseness

The body is reasonably lean and avoids explaining what PDFs or libraries are, but the three full worked examples (PowerPoint/PDF) largely restate the same three steps and could be trimmed, and the 'When to Use' bullets overlap with the intro sentence.

3 / 5

Actionability

Provides concrete, copy-pasteable commands (shell_agent invocation, find with -name/-mmin, cp) and specific examples for pptx/pdf; the only gap is that shell_agent's task argument uses placeholders like [file type] rather than a fully specified call in the main step.

4 / 5

Workflow Clarity

The three-step sequence (delegate, locate, copy) is clear and the troubleshooting table adds recovery hints, but there is no validation checkpoint verifying the generated file is correct before copying, and the cap for batch/destructive-adjacent operations without explicit validation applies.

3 / 5

Progressive Disclosure

Content is well-organized into clear sections (When to Use, Workflow Steps, Example, Tips, Troubleshooting) with no nested references and no bundle files to navigate; it is a self-contained single-file skill with appropriate structure, just slightly above the midpoint rather than exemplary.

4 / 5

Total

14

/

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 clearly conveys a niche fallback workflow (delegate to shell_agent, locate and retrieve generated files) and states a trigger condition. It is solid but could add natural trigger synonyms and explicit 'Use when...' phrasing to reach the top anchor.

Suggestions

Add an explicit 'Use when...' clause with concrete natural triggers, e.g. 'Use when create_file or document tools fail, or when generating complex files like .pptx, .docx, or .pdf.'

Include natural user phrases and file extensions (e.g. 'PowerPoint', 'PDF report', '.pptx', '.docx') so the description matches what users actually say.

Tighten the what/when split: lead with the capability, then a comma-separated trigger list, mirroring the rubric's good examples.

DimensionReasoningScore

Specificity

Names the concrete action 'Delegate file generation to shell_agent' and the supporting actions 'file location and retrieval', plus the trigger 'when direct tools fail'; coverage is good but the exact mechanism (write code, execute, retry) lives in the body rather than the description.

4 / 5

Completeness

It answers 'what' (delegate to shell_agent with location/retrieval) and 'when' (when direct tools fail), but the 'when' clause is a single condition without the fuller trigger guidance the good examples model with an explicit 'Use when...' listing.

4 / 5

Trigger Term Quality

Contains relevant terms like 'file generation', 'direct tools fail', and 'retrieval', but lacks the natural phrases and synonyms a user would say (e.g. 'create a file', 'generate document', file extensions like .pptx/.pdf) that the body examples actually cover.

3 / 5

Distinctiveness Conflict Risk

The 'shell_agent' fallback niche is fairly distinct from ordinary file skills, though the broad phrase 'file generation' could overlap with dedicated format-specific skills like pptx/pdf creators.

4 / 5

Total

15

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.