CtrlK
BlogDocsLog inGet started
Tessl Logo

resilient-document-pipeline

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

53

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 a well-sequenced, highly actionable resilient workflow with explicit validation and recovery loops, but it is padded with redundant framing sections and fails to offload or even reference the two bundled scripts that duplicate its inline logic.

Suggestions

Trim the 'Advantages Over Standard Approaches', 'Best Practices' Do/Don't, and 'When to Return to Standard Methods' sections, and either drop the 'Complete Example' or shorten it to the non-obvious parts, to reduce padding.

Reference the bundle scripts instead of inlining their logic — e.g. 'Run `scripts/sanitize_for_pdf.sh input.md`' and 'Run `scripts/convert_with_fallbacks.sh input.md pdf`' — so progressive disclosure is honored and duplication is removed.

Make the python-docx DOCX fallback concrete (a minimal executable snippet) or explicitly justify deferring it, to close the one actionability gap.

DimensionReasoningScore

Conciseness

The core five-step workflow is efficient and actionable, but the body also carries padding Claude does not need — an ASCII-art overview, an 'Advantages Over Standard Approaches' table, a Do/Don't 'Best Practices' table, a 'When to Return to Standard Methods' section, and a 'Complete Example' that re-walks all five steps — so it is mostly efficient but could be tightened.

3 / 5

Actionability

It provides concrete executable commands and code for the common cases (pandoc invocations, a sed sanitization one-liner, complete fpdf2 and reportlab Python blocks, and `ls`/`file` verification), with only a minor gap where the python-docx fallback is left as pseudocode ('Implementation depends on complexity needs').

4 / 5

Workflow Clarity

The five steps (Detect, Create, Sanitize, Convert, Verify) are clearly sequenced with an explicit validation checkpoint and checklist in Step 5, plus a decision tree and progressive-fallback structure that serve as feedback loops for error recovery, satisfying the anchor for explicit validation and recovery loops.

5 / 5

Progressive Disclosure

Section headers give the body reasonable structure, but content that belongs in the provided bundle scripts (the sanitization logic and the fallback conversion logic) is fully inlined in SKILL.md, and the body never references sanitize_for_pdf.sh or convert_with_fallbacks.sh, so the bundle files are present but not signaled or used.

3 / 5

Total

15

/

20

Passed

Description

50%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 clearly states what the skill does via four capability labels, but it is missing an explicit 'Use when...' trigger clause and leans on internal jargon rather than natural user terms, capping several dimensions at 3.

Suggestions

Add an explicit trigger clause, e.g. 'Use when generating .docx/.pdf/.html documents in environments where pandoc/LaTeX or retrieval tools are failing or when content contains Unicode characters.'

Replace internal jargon ('domain knowledge fallback', 'progressive conversion') with natural user phrases and file extensions users actually say (PDF, docx, html, convert, sanitize).

List concrete actions (e.g. 'generate, sanitize, and convert documents to PDF/DOCX/HTML with fallback engines') to lift specificity above 3.

DimensionReasoningScore

Specificity

The description names the domain ('Unified document generation') and four capabilities ('tool failure detection, domain knowledge fallback, progressive conversion, and Unicode safety'), but these are abstract capability labels rather than concrete user-facing actions like 'convert to PDF' or 'sanitize Unicode', so it stops at naming the domain plus a few actions without being comprehensive.

3 / 5

Completeness

It gives a clear 'what' (unified document generation with the listed capabilities) but provides no 'when' / 'Use when...' trigger clause, so per the cap guidance completeness cannot exceed 3.

3 / 5

Trigger Term Quality

'document generation' and 'Unicode' are relevant keywords a user might say, but the rest ('tool failure detection', 'domain knowledge fallback', 'progressive conversion') is technical jargon users would not naturally utter, and common terms/synonyms like PDF, docx, html, or file extensions are missing.

3 / 5

Distinctiveness Conflict Risk

'Unified document generation' is fairly broad and the skill body itself names two parent skills (document-gen-fallback-enhanced, write-file-fallback-report) covering overlapping subsets, so it is somewhat specific but still risks overlapping with those siblings.

3 / 5

Total

12

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (526 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
HKUDS/OpenSpace
Reviewed

Table of Contents

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.