resilient-research-workflow

Unified workflow that delegates failed web searches to shell_agent for resilient data gathering, then applies anchored spreadsheet proof gates for verified Excel output

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/spreadsheet-proof-gate-merged/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 body is highly actionable and exceptionally well-sequenced with explicit gates and feedback loops, including a complete executable verification script. Its weaknesses are mild redundancy across the rules/contract/gate sections and a monolithic single-file structure with no progressive disclosure into reference files.

Suggestions

Split the large verification script template and the criteria-type catalog into reference files (e.g., references/verify_template.py, references/criteria.md) linked one level deep from the body to improve progressive disclosure.

Deduplicate the rules restated across 'Core rules', 'Outcome contract', and the phase gates; reference a single canonical statement instead of repeating each requirement.

Trim the opening purpose paragraph that restates what the description already covers, keeping only the additional 'Use this skill when' framing.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete scripts and examples, but restates the same rules across 'Core rules', 'Outcome contract', and the phase gates, and re-explains the workflow's purpose already covered by the description; some tightening would reduce tokens without losing clarity.	3 / 5
Actionability	Provides a fully executable openpyxl verification template plus concrete search_web/shell_agent call examples and a precise criterion syntax (required-sheet:, data-populated:) with good/bad examples covering common cases.	5 / 5
Workflow Clarity	Sequenced into phases A/B/C with explicit numbered steps, named gates (Gate A, Gate B, C4 go/no-go, C7 finalization), and validate→fix→re-run feedback loops for the destructive/batch spreadsheet operations, satisfying the feedback-loop requirement.	5 / 5
Progressive Disclosure	Content is well-organized into clear sections but is a monolithic single-file SKILL.md with no bundle references; large blocks (the full verification script, the criteria-type catalog, and the appendix examples) are inlined rather than split into one-level-deep reference files.	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 clearly states what the workflow does with several concrete actions, but lacks an explicit 'Use when...' trigger clause and leans on internal terminology (shell_agent, proof gates) over natural user phrases. Per the rubric's completeness cap, the missing trigger clause limits the score. It is mostly distinct from other skills with only minor overlap risk.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when gathering web data into an Excel workbook, or when search tools are failing and outputs must be verified').

Replace internal/system terms with user-facing synonyms a person would actually say (e.g., 'web research', 'Excel files', 'spreadsheets', '.xlsx') alongside 'shell_agent'.

Enumerate the concrete actions more fully (e.g., 'detect search failures, delegate to a sub-agent, verify results, build criteria checklists, and re-read the saved workbook') to approach comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('delegates failed web searches to shell_agent', 'applies anchored spreadsheet proof gates', 'verified Excel output') across two domains, but the actions are somewhat abstract rather than fully enumerated, so it sits just below the comprehensive 5 anchor.	4 / 5
Completeness	Has a clear 'what' (unified research-to-spreadsheet workflow) but no explicit 'Use when...' trigger clause in the description; per the judging guidelines, a missing trigger clause caps completeness at 3 even though the 'what' is clear.	3 / 5
Trigger Term Quality	Includes relevant terms ('web searches', 'Excel', 'spreadsheet', 'shell_agent') but leans toward internal/system names and omits common user-facing synonyms and natural phrases a user would actually say.	3 / 5
Distinctiveness Conflict Risk	Targets a fairly distinct niche (resilient web research plus anchored spreadsheet proof) with specific triggers; minor overlap risk with generic spreadsheet or research skills keeps it just below 5.	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/spreadsheet-proof-gate-merged/SKILL.md
Commit: 3827781

Reviewed: 5 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.