research-fallback-robust

Handle web research failures with explicit error recognition and domain-specific fallback strategies

Quality

60%

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/research-fallback-enhanced/SKILL.md

Quality

Content

67%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 a well-sequenced, actionable workflow with concrete error triggers and a clear decision flow, weakened mainly by redundant 'Best Practices' restating the steps and lengthy inline examples that add length without proportional value.

Suggestions

Trim the 'Best Practices' section or fold its non-duplicate items back into the relevant workflow steps to remove repetition with Steps 2-4.

Condense the two worked examples to a single compact example, or move full examples to a separate EXAMPLES.md reference and link to it.

Add an explicit output-validation checkpoint in Step 5 (e.g. 'Verify the deliverable meets the stated format and length constraints before finishing') to lift workflow_clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, but the 'Best Practices' section restates earlier workflow points ('recognize error patterns quickly', 'be transparent', 'flag uncertainties') and the two worked examples are lengthy, so it could be tightened rather than earning a 4.	3 / 5
Actionability	Concrete triggers ('unknown error', '1-2 retry' threshold) and specified disclaimers give mostly executable guidance; a few inherently soft steps ('Assess internal knowledge') keep it just below a 5.	4 / 5
Workflow Clarity	Five sequenced steps plus an explicit decision-flow diagram and a retry/pivot checkpoint provide a clear sequence; it stops short of 5 because there is no explicit validation step on the generated deliverable.	4 / 5
Progressive Disclosure	The skill is self-contained with no bundle files and is well-organized into clear sections; because it exceeds 50 lines with two long inline examples, it lands at 4 rather than the 5 reserved for compact single-purpose skills.	4 / 5
	Total	15 / 20 Passed

Description

53%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 and targets a distinct niche, but it lacks an explicit 'Use when...' trigger clause and its actions are somewhat abstract rather than concretely enumerated, capping completeness and specificity at the midpoint.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when search_web or read_webpage fail with unknown error or timeouts and the task still needs to be completed.'

Replace abstract actions ('error recognition', 'fallback strategies') with concrete verbs users would say, such as 'recognize unknown error from search_web, pivot to internal knowledge, and add verification disclaimers.'

Include natural synonyms users might say ('search failing', 'web tools unavailable', 'use internal knowledge') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('web research failures') and 1-2 actions ('error recognition', 'domain-specific fallback strategies'), but the actions are abstract rather than a comprehensive concrete list, matching the 'names domain and 1-2 concrete actions' anchor.	3 / 5
Completeness	The 'what' is clear (handle research failures via error recognition and fallback), but there is no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	'web research failures' is a relevant natural-ish keyword, but common user phrasings ('search isn't working', 'use internal knowledge') and synonyms are missing, fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche (research-failure fallback behavior) with only minor overlap risk against closely related research skills; not a 5 because the trigger phrasing is less concrete than the anchor's PDF-style explicit triggers.	4 / 5
	Total	13 / 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/research-fallback-enhanced/SKILL.md
Commit: 3827781

Reviewed: 10 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.