document-gen-resilient

Multi-path document generation with tool checks, Unicode handling, and Python fallbacks

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/document-gen-fallback-enhanced-enhanced-96865f/SKILL.md

Quality

Content

77%

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 a clear, validated multi-step workflow, but it is verbose due to substantial duplication across the example, command reference, and troubleshooting sections, and it does not use progressive disclosure to offload reusable detail.

Suggestions

Remove duplication: delete or trim the 'Complete Example' and 'Common pandoc Commands' sections since the step-by-step workflow and troubleshooting already cover the same commands.

Move the reusable sanitization script into scripts/sanitize_for_pdf.sh and the Unicode replacement table into a references/ file, referencing them from SKILL.md to improve progressive disclosure.

Consolidate the 'Decision Matrix' and the Step 0 'Decision Tree' into a single decision section to reduce repeated guidance.

Dimension	Reasoning	Score
Conciseness	The body is actionable and avoids explaining elementary concepts, but it is heavily redundant: the 'Complete Example', 'Common pandoc Commands', and 'Troubleshooting' sections restate the same pandoc commands and fallbacks already given in the step-by-step workflow.	2 / 3
Actionability	Commands and code are fully executable and copy-paste ready — pandoc invocations, the fpdf2/reportlab Python snippets, and the bash sanitization script all run as written.	3 / 3
Workflow Clarity	Steps 0–4 are clearly sequenced with explicit validation (tool-availability checks in Step 0, output verification in Step 4) and feedback loops (primary method then ordered fallbacks on failure).	3 / 3
Progressive Disclosure	Sections are well organized, but there are no bundle files (references/scripts/assets absent) and reusable material — the sanitization script and Unicode replacement table — is inlined when it could live in separate reference files.	2 / 3
	Total	10 / 12 Passed

Description

60%

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 is specific and third-person but lacks an explicit 'Use when...' trigger clause and leans on technical jargon over natural user keywords. It is competent but not maximally discoverable or distinct.

Suggestions

Add an explicit trigger clause, e.g. 'Use when document generation fails, when producing .docx/.pdf/.html output, or when PDF conversion hits LaTeX/Unicode errors.'

Replace jargon ('multi-path', 'Python fallbacks') with natural user terms like 'generate PDF/docx/HTML documents' and 'convert Markdown to multiple formats'.

Sharpen distinctiveness by naming the failure scenario, e.g. 'Use when shell_agent document generation returns errors or PDF encoding fails.'

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete capabilities ('tool checks, Unicode handling, and Python fallbacks') rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It states what the skill does but includes no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	'document generation' is a phrase a user might say, but the rest ('multi-path', 'tool checks', 'Unicode handling', 'Python fallbacks') is technical jargon and common natural terms like PDF, docx, html, or convert are missing.	2 / 3
Distinctiveness Conflict Risk	The resilient multi-format fallback niche is somewhat specific, but without explicit triggers it could still overlap with other document-generation skills.	2 / 3
	Total	9 / 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-enhanced-enhanced-96865f/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.