unified-deliverables-flow

Generate spreadsheets, diagrams, and PDF reports in a phased workflow with explicit iteration budgets and error recovery

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/pdf-checklist-workflow-enhanced/SKILL.md

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.

A well-sequenced, highly actionable workflow with strong validation and feedback loops, but it is a monolithic file with redundant reinforcement sections and large code blocks that would benefit from external reference files.

Suggestions

Move the three full code examples into referenced files (e.g. references/spreadsheet.py, references/diagram.py, references/pdf_report.py) and keep only concise snippets plus a 'See X' pointer inline to raise progressive_disclosure.

Consolidate 'Best Practices', 'Quick Reference: Tool Selection', 'Complete Workflow Checklist', and 'Troubleshooting' into a single section to remove repeated budget/fallback content and tighten conciseness.

Fix the PDF code syntax error (replace 'colors '#2c3e50'' with 'colors.HexColor('#2c3e50')') so all three examples are copy-paste executable, lifting actionability toward 5.

Dimension	Reasoning	Score
Conciseness	The three full code blocks are justified and it avoids explaining library basics Claude already knows, but 'Best Practices', 'Quick Reference: Tool Selection', 'Complete Workflow Checklist', and 'Troubleshooting' substantially rehash the phase/budget/fallback rules already stated, so it could be tightened; the redundancy is noticeable but not severe enough for anchor 2.	3 / 5
Actionability	Provides copy-paste-ready openpyxl, matplotlib, and reportlab code plus concrete verification commands and fallback shell_agent tasks, but the PDF example contains a syntax error ('colors '#2c3e50'' missing the dot/operator) that prevents direct execution of one of three examples — a minor gap that keeps it below 5.	4 / 5
Workflow Clarity	Clear Phase 0→1→2→3 sequence with per-phase iteration budgets, explicit verification checkpoints with ✓/✗ criteria, retry/fallback feedback loops, and a complete checklist; this batch operation includes validation, so the destructive/batch cap does not apply and it matches anchor 5.	5 / 5
Progressive Disclosure	No bundle files exist and the skill is a single ~423-line document with roughly 190 lines of full code examples inlined that would fit better in separate reference files; section headers are well-organized (ruling out 2), but the absence of any one-level-deep references and inlined bulky content matches anchor 3.	3 / 5
	Total	15 / 20 Passed

Description

66%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 across three concrete deliverable types with process framing, but omits any 'Use when...' trigger guidance, capping completeness. Trigger terms are natural but lack synonyms and file extensions.

Suggestions

Append a 'Use when...' clause naming concrete triggers, e.g. 'Use when generating multiple artifact types (Excel, images, PDFs) in one task or when balanced iteration budgeting across deliverables is needed.'

Add file extensions and synonyms to improve trigger-term coverage: 'spreadsheets (.xlsx, Excel), diagrams (.png, charts), and PDF reports (.pdf)'.

Differentiate the verb per deliverable (e.g. 'build spreadsheets, render diagrams, and assemble PDF reports') to lift specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names three concrete deliverable types ('spreadsheets, diagrams, and PDF reports') plus 'phased workflow', 'explicit iteration budgets', and 'error recovery' — several specific actions with only minor coverage gaps, falling short of anchor 5 because 'Generate' is a single repeated verb with no per-deliverable action detail.	4 / 5
Completeness	The 'what' is clear (generate three artifact types in a phased workflow), but there is no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric cap completeness stays at 3 rather than 4.	3 / 5
Trigger Term Quality	'spreadsheets', 'diagrams', and 'PDF reports' are natural terms a user would say, matching anchor 4's 'good keyword coverage'; common synonyms and file extensions (Excel, .xlsx, charts, .png, .pdf) are absent, which is the gap that keeps it below 5.	4 / 5
Distinctiveness Conflict Risk	The multi-deliverable phased-workflow niche with iteration budgeting is mostly distinct with only minor overlap risk against single-purpose spreadsheet/diagram/PDF skills; it lacks the explicit trigger phrases that would push it to anchor 5.	4 / 5
	Total	15 / 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/pdf-checklist-workflow-enhanced/SKILL.md
Commit: 3827781

Reviewed: 7 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.