resilient-document-pipeline

Unified document generation with tool failure detection, domain knowledge fallback, progressive conversion, and Unicode safety

Quality

56%

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-merged/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, well-validated workflow and real executable code, but it is verbose with redundant restatements and keeps everything inline rather than progressively disclosing detail into its bundle files.

Suggestions

Remove or compress the redundant 'Complete Example', 'Decision Tree', and 'Advantages Over Standard Approaches'/'Best Practices' sections that restate earlier steps, to tighten token use.

Replace the inlined 'Add File' scripts with properly separated files in ./scripts/ and reference them from the body (e.g. 'For conversion: run scripts/convert_with_fallbacks.sh'), so SKILL.md becomes a concise overview.

Either complete the python-docx DOCX fallback with executable code or explicitly justify leaving it as a stub.

Dimension	Reasoning	Score
Conciseness	The ~385-line body is mostly useful but padded: the ASCII diagram, the 'Complete Example', the 'Decision Tree', and the 'Advantages'/'Best Practices' tables largely restate steps already given earlier in the document.	2 / 3
Actionability	It provides concrete, executable guidance throughout — real run_shell/execute_code_sandbox calls, a working sed sanitization command, complete fpdf2/reportlab Python blocks, and a functional convert_with_fallbacks.sh script — with only minor stub exceptions (the python-docx DOCX fallback).	3 / 3
Workflow Clarity	A clear five-step sequence (Detect, Create, Sanitize, Convert, Verify) with an explicit verification step, a validation checklist, and documented progressive-fallback feedback loops for error recovery.	3 / 3
Progressive Disclosure	Two bundle scripts (sanitize_for_pdf.sh, convert_with_fallbacks.sh) exist but are inlined via 'Add File' markers rather than linked/navigated from the body, and the full conversion logic, example, and troubleshooting all sit inline in a monolithic document that should be split out.	2 / 3
	Total	10 / 12 Passed

Description

35%

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 conveys a coherent feature set but lacks any trigger guidance and leans on technical jargon rather than natural keywords. It would not reliably surface when a user actually needs this resilient workflow.

Suggestions

Add an explicit 'Use when...' clause with natural triggers, e.g. 'Use when generating .docx/.pdf/.html documents in environments where pandoc/LaTeX or retrieval tools are failing, or when documents contain Unicode/special characters'.

Replace abstract feature labels with concrete verb-object actions ('generate .docx/.pdf/.html from markdown', 'sanitize Unicode for LaTeX', 'fall back across pandoc, reportlab, fpdf2, wkhtmltopdf').

Surface natural keywords users would say — 'PDF', 'DOCX', 'HTML', 'pandoc failed', 'Unicode', 'conversion' — so the skill triggers reliably.

Dimension	Reasoning	Score
Specificity	Names the document-generation domain plus four capability areas ('tool failure detection, domain knowledge fallback, progressive conversion, and Unicode safety'), but these read as abstract feature labels rather than concrete verb-object actions like 'extract text... fill forms, merge documents'.	2 / 3
Completeness	It states what the skill does but provides no 'when' guidance at all — per the rubric, a missing 'Use when...' clause caps completeness at 2.	2 / 3
Trigger Term Quality	The description uses internal/technical jargon ('progressive conversion', 'domain knowledge fallback') with no natural user-facing keywords a person would actually say, such as 'PDF', 'DOCX', 'report', or 'conversion failed'.	1 / 3
Distinctiveness Conflict Risk	The four qualifiers carve a fallback/resilience niche that separates it somewhat from plain document-gen skills, but the absence of distinct trigger phrases means it could still overlap with similar document generation skills.	2 / 3
	Total	7 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (526 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/document-gen-fallback-enhanced-merged/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.