document-gen-fallback

Fallback workflow for multi-format document generation when shell_agent encounters errors

Quality

60%

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/document-gen-fallback/SKILL.md

Quality

Content

57%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 body is actionable and well-structured with concrete pandoc commands, but verification is shallow for a batch operation and the file is monolithic with redundant example sections.

Suggestions

Add a real validation checkpoint that confirms each output is a valid file (e.g. 'file output.pdf | grep PDF' or pandoc round-trip), not just 'ls -lh', to lift workflow clarity above the batch cap.

Remove the 'Complete Example' section or fold it into the step-by-step workflow to eliminate redundancy and improve token efficiency.

Move 'Common pandoc Commands' and 'Troubleshooting' into a separate references file linked from the body to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but the 'Complete Example' re-states the step-by-step workflow and 'Common pandoc Commands' overlaps the conversion steps, adding padding that could be trimmed.	3 / 5
Actionability	Provides concrete, copy-paste-ready pandoc and write_file commands covering docx/pdf/html, with only minor gaps (the source content block uses placeholders).	4 / 5
Workflow Clarity	Steps are clearly sequenced, but this batch multi-format operation only verifies outputs with 'ls -lh' (existence, not validity); per the batch-operation rule, missing real validation caps this at 3.	3 / 5
Progressive Disclosure	Well-sectioned single file, but no bundle files exist and reference-like material (Common pandoc Commands, Troubleshooting) is inlined rather than split into one-level-deep references.	3 / 5
	Total	13 / 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 cleanly states both purpose and trigger, but leans on internal jargon ('shell_agent') that users would not naturally invoke, and lists no concrete formats or actions.

Suggestions

Replace internal jargon with user-facing trigger language, e.g. 'Use when document generation fails or errors are unclear across .docx, .pdf, and .html formats'.

List the concrete formats and actions to lift specificity, e.g. 'Generate .docx, .pdf, and .html from Markdown via pandoc as a fallback workflow'.

Dimension	Reasoning	Score
Specificity	Names the domain ('multi-format document generation') and one concrete action ('Fallback workflow'), but does not enumerate the specific formats or actions, so coverage is not comprehensive.	3 / 5
Completeness	Explicitly states both what ('Fallback workflow for multi-format document generation') and when ('when shell_agent encounters errors'); the trigger is present but could be more specific to user-facing situations.	4 / 5
Trigger Term Quality	'document generation' is a natural keyword, but 'shell_agent encounters errors' is internal jargon a user would not naturally say, and common synonyms/format extensions are missing.	3 / 5
Distinctiveness Conflict Risk	The fallback-when-shell_agent-errors framing carves a fairly distinct niche with only minor overlap risk against a general document-generation skill.	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/document-gen-fallback/SKILL.md
Commit: 3827781

Reviewed: 25 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.