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%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 content is highly actionable with a clear, well-validated workflow and feedback loops, but it is a monolithic, redundant file that repeats the same commands and fallback advice across multiple sections and does not split reference material into bundle files.

Suggestions

Remove the redundant Complete Example and Common pandoc Commands sections, which restate Step 3's commands and fallbacks verbatim.

Move the sanitize_for_pdf.sh script and the Troubleshooting catalog into references/ (e.g. references/sanitize.sh, references/troubleshooting.md) and link to them from the body to improve progressive disclosure.

Consolidate the Step 0 decision tree and the Decision Matrix into a single decision reference to eliminate duplicated guidance.

Dimension	Reasoning	Score
Conciseness	The body is operationally dense and avoids explaining concepts Claude already knows, but the same conversion commands and fallback advice are restated across Step 3, the Complete Example, Common pandoc Commands, and Troubleshooting, so it could be tightened considerably; not a 2 because the padding is structural redundancy rather than concept fluff.	3 / 5
Actionability	Commands and scripts throughout are copy-paste ready and executable (which-pandoc checks, pandoc conversion invocations, grep Unicode detection, fpdf2/reportlab Python snippets, a full sanitize_for_pdf.sh script), covering the common DOCX/PDF/HTML cases concretely.	5 / 5
Workflow Clarity	Steps 0-4 are explicitly sequenced with validation checkpoints (tool availability decision tree, Unicode detection, output verification via ls/file) and a feedback loop (PDF Option A->B->C->D fallback ordering), satisfying the anchor for clear sequence with explicit validation and error recovery.	5 / 5
Progressive Disclosure	Section structure is clear, but the skill is a monolithic ~400-line file with no bundle files and no references to separate files; content that belongs in references (the sanitization script, troubleshooting catalog, command cheat-sheet) is inlined, fitting the "some structure but content that should be separate is inline" anchor.	3 / 5
	Total	16 / 20 Passed

Description

58%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 names a clear domain and several concrete techniques but omits any "Use when..." trigger guidance and lacks common natural terms and file extensions, leaving completeness and trigger-term quality at mid-level.

Suggestions

Add an explicit "Use when..." clause naming concrete triggers, e.g. "Use when document generation fails or when producing .docx/.pdf/.html with special characters."

Include natural user terms and file extensions (PDF, Word, .docx, .pdf, .html, convert documents) to improve trigger-term coverage.

Reframe the technique list as user-facing actions (e.g. "generate, convert, and sanitize documents") to lift specificity toward comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain ("Multi-path document generation") plus several concrete facets ("tool checks", "Unicode handling", "Python fallbacks"), listing several specific capabilities with only minor coverage gaps; not a 5 because the facets are techniques rather than a comprehensive set of user-facing actions.	4 / 5
Completeness	It gives a clear "what" (multi-path document generation with tool checks, Unicode handling, Python fallbacks) but no "Use when..." clause or equivalent trigger guidance; per the rubric a missing Use-when caps completeness at 3.	3 / 5
Trigger Term Quality	"document generation" and "Unicode" are relevant keywords, but common natural terms and file extensions users actually say (PDF, Word, .docx, .pdf, .html, convert) are missing, so coverage is partial rather than good.	3 / 5
Distinctiveness Conflict Risk	The resilience/fallback framing ("tool checks", "Python fallbacks", "multi-path") carves a mostly distinct niche away from generic document skills, with only minor overlap risk; not a 5 because there are no explicit distinct triggers.	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-enhanced-enhanced-96865f/SKILL.md
Commit: 3827781

Reviewed: 13 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.