search-fail-pivot

Heuristic for detecting search tool failures and pivoting to domain knowledge for document generation

Quality

50%

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/search-fail-pivot/SKILL.md

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and gives a usable heuristic, but it is held back by mild verbosity, partially illustrative code, and a missing output-validation step in the generation workflow.

Suggestions

Trim the Benefits section and the reportlab example, or replace the partial snippet with a complete minimal executable script.

Add a verification checkpoint after document generation (e.g. open/validate the produced file before declaring done) to satisfy the destructive/batch feedback-loop expectation.

Tighten the recoverable-vs-non-recoverable definitions into a one-line distinction since Claude already understands these error categories.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete rules, but the Benefits section, the illustrative reportlab snippet, and restated concepts (recoverable vs non-recoverable error definitions) add tokens Claude does not need.	2 / 3
Actionability	The IF/THEN rule and decision flow are concrete, but the code examples are illustrative and incomplete ('... continue with known information') rather than copy-paste executable.	2 / 3
Workflow Clarity	Steps 1-4 are clearly sequenced with a decision flow, but the document-generation step has no validation/verification checkpoint on the output, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	The skill is a single well-organized file with clear sections and no nested references, but at ~120 lines it exceeds the 'under 50 lines' simple-skill case that would earn a 3.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 communicates a clear purpose but is held back by the absence of an explicit 'when to use' trigger and by jargon-heavy phrasing. It is adequate but not exemplary.

Suggestions

Add a 'Use when...' clause with natural trigger terms, e.g. 'Use when search_web or web retrieval repeatedly fails and the task can proceed from existing knowledge.'

Replace jargon like 'pivot to domain knowledge' with user-natural phrasings such as 'fall back to what you already know' or 'stop retrying search'.

Name a couple more concrete actions (e.g. 'count consecutive failures, classify errors as recoverable or not') to raise specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and core actions ('detecting search tool failures and pivoting to domain knowledge for document generation') but does not enumerate multiple concrete capabilities, so it stops short of the level-3 anchor.	2 / 3
Completeness	It states what the skill does but lacks any 'Use when...' or equivalent explicit trigger clause, which the guidelines cap at 2 rather than 3.	2 / 3
Trigger Term Quality	'search' is a natural user term, but 'heuristic', 'pivot to domain knowledge', and 'document generation' are internal/jargon phrasings rather than the varied terms a user would actually say.	2 / 3
Distinctiveness Conflict Risk	The search-failure-pivot niche is somewhat specific, but the description is generic enough that it could overlap with general fallback or document-generation skills.	2 / 3
	Total	8 / 12 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/search-fail-pivot/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.