document-gen-fallback

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

Quality

61%

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

72%

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

The body is highly actionable with concrete pandoc commands and a clean section structure, but it loses conciseness to a duplicated worked example and its verification step is too weak for a batch/multi-format workflow, leaving conciseness and workflow_clarity at 2.

Suggestions

Remove the standalone 'Complete Example' (or compress it to a one-line reference) since it restates the Step 1-3 workflow verbatim, reducing token redundancy.

Strengthen Step 3 verification beyond 'ls -lh' — e.g. check pandoc's exit code and file type ('pandoc ... && file output.pdf') and add an explicit 'if conversion fails, see Troubleshooting and retry' feedback loop.

Trim the 'Common pandoc Commands' section to only the variants not already shown in the step-by-step workflow to avoid repeating the basic conversions.

Dimension	Reasoning	Score
Conciseness	The body is concrete and avoids explaining concepts Claude already knows, but the 'Complete Example' duplicates the Step 1-3 workflow with only a filename change and 'Common pandoc Commands' repeats conversions already shown, so it is 'mostly efficient but could be tightened' rather than fully lean.	2 / 3
Actionability	It provides specific, copy-paste-ready pandoc commands (e.g. 'pandoc /tmp/document_source.md -o output.docx') plus concrete write_file/run_shell invocations and a troubleshooting table, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	Steps are clearly sequenced (Step 1-3) and include a verification step, but the 'ls -lh' check is a weak checkpoint that does not confirm conversion validity or exit status, and there is no validate->fix->retry loop for this batch/multi-format operation, capping it at 2 per the rubric's batch-operation note.	2 / 3
Progressive Disclosure	This single-purpose skill is one file with no external references and is well-organized into clearly headed sections (When to Use, Core Technique, Step-by-Step, Troubleshooting, When to Return); per the simple-skills note, well-organized single-file content with no need for external references scores 3.	3 / 3
	Total	10 / 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 states a domain and a triggering condition but is generic: it names no concrete actions and relies on an internal error state ('shell_agent encounters errors') rather than natural user-facing triggers, capping most dimensions at 2.

Suggestions

Add concrete actions to the description, e.g. 'Convert Markdown sources to .docx/.pdf/.html with pandoc, then verify outputs' to lift specificity toward 3.

Replace or supplement 'when shell_agent encounters errors' with user-natural triggers such as 'Use when generating documents in multiple formats (.docx, .pdf, .html) or when document conversion fails.'

Include an explicit 'Use when...' clause with common format keywords so completeness and trigger-term quality reach the 3-anchor.

Dimension	Reasoning	Score
Specificity	The phrase 'multi-format document generation' names the domain and 'Fallback workflow' names the nature, but no concrete actions (create, convert, verify) are listed, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multiple-action list of a 3.	2 / 3
Completeness	It states both what ('Fallback workflow for multi-format document generation') and a when ('when shell_agent encounters errors'), but the trigger is a narrow internal system state rather than user-facing 'Use when...' guidance, so it does not clearly meet the explicit-user-trigger bar of a 3.	2 / 3
Trigger Term Quality	'document generation' and 'multi-format' are relevant keywords, but 'shell_agent encounters errors' is internal jargon a user would not naturally say, and common format variations (.docx, .pdf, .html) shown in the body are absent here, so it stops at 'some relevant keywords but missing common variations.'	2 / 3
Distinctiveness Conflict Risk	The fallback/error trigger carves a somewhat distinct niche, yet the broad 'document generation' domain could overlap with general document-generation skills, fitting 'somewhat specific but could still overlap' rather than a clearly non-conflicting 3.	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/document-gen-fallback/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.