resilient-context-extraction

Ensures agents extract data from context files with validation and fallback strategies before resorting to assumptions or external searches.

Quality

63%

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/prioritize-context-data-enhanced/SKILL.md

Quality

Content

77%

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

The content is highly actionable with executable commands and a clear, validated workflow. Its main weaknesses are verbosity from repeated guidance and a monolithic structure that inlines a script and reference material instead of splitting them into bundle files.

Suggestions

Move the embedded bash fallback script into ./scripts/extraction_fallback.sh and reference it from SKILL.md to improve progressive disclosure.

Consolidate the duplicated hallucination/assumption guidance across Critical Rule, Warnings, and Recovery Protocol into a single concise section to improve conciseness.

Extract the Tool-Specific Notes table and per-format fallback details into a ./references/ file referenced from the body.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable and avoids explaining basic concepts, but it is long (~150 lines) with notable repetition: the Critical Rule, Warnings, and Recovery Protocol restate the same hallucination/assumption guidance multiple times.	2 / 3
Actionability	It provides copy-paste-ready commands (e.g., 'unzip -p file.docx word/document.xml \| xmllint --format -', 'in2csv file.xlsx', 'pdftotext file.pdf -') plus a complete, executable bash fallback script with real functions.	3 / 3
Workflow Clarity	Six numbered steps form a clear sequence with an explicit validation checkpoint in Step 3 (truncation, expected-vs-extracted comparison) and a feedback loop through fallback strategies (4a-4d) and Recovery Protocol, plus a checklist.	3 / 3
Progressive Disclosure	No bundle directories or external referenced files exist; the body is a single over-50-line document with an inlined bash script (via an 'Add File' marker) and inline Tool-Specific Notes that would be better split into separate files.	2 / 3
	Total	10 / 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 states a clear purpose and implies a trigger condition, but it lacks concrete named actions and an explicit 'Use when...' clause with natural user terms. It is competent but generic, scoring 2 across all dimensions.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g., 'Use when a task provides attached files (PDF, Excel, CSV, .docx) and extraction may be incomplete or truncated.'

Replace abstract phrases ('validation and fallback strategies') with concrete actions like 'inspect, validate, and re-extract using alternative libraries or shell tools'.

Include common user-facing file terms (PDF, Excel, spreadsheet, attached file, truncated) to improve trigger term quality and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain ('extract data from context files') and a couple of actions ('validation and fallback strategies'), but the actions are abstract rather than multiple concrete operations like 'extract text, fill forms, merge documents'.	2 / 3
Completeness	The 'what' is stated and a trigger is implied via 'before resorting to assumptions or external searches', but there is no explicit 'Use when...' clause, capping completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Terms like 'context files', 'validation', 'fallback strategies', 'assumptions', 'external searches' are relevant but miss natural variations a user would say (e.g., 'attached file', 'PDF', 'Excel', 'spreadsheet', 'truncated').	2 / 3
Distinctiveness Conflict Risk	The resilient-extraction framing is fairly specific, but 'context files' is generic enough that it could overlap with general file-reading or document-handling skills.	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/prioritize-context-data-enhanced/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.