resilient-context-extraction

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

Quality

49%

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

56%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 with concrete commands and a real fallback script, and the workflow is clearly sequenced with validation checkpoints. Its main weaknesses are verbosity (restated warnings/recovery) and weak progressive disclosure, since the bundle file is inlined rather than linked and supporting material is not split out.

Suggestions

Trim redundant sections: fold 'Warnings' and 'Recovery Protocol' into the workflow steps and remove the Critical Rule restatement of the Objective to improve conciseness.

Move examples/extraction_fallback.sh into a real ./scripts/ or ./assets/ file and reference it with a markdown link (e.g. 'See [extraction_fallback.sh](scripts/extraction_fallback.sh)') instead of inlining it.

Extract the Tool-Specific Notes table and detailed per-format fallbacks into a separate reference file, keeping SKILL.md as a concise overview.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: 'Critical Rule', 'Warnings', and 'Recovery Protocol' restate the Objective and steps, and the Tool-Specific Notes table duplicates Step 4 fallbacks; padding could be trimmed without losing meaning.	2 / 5
Actionability	Provides concrete executable commands (unzip -p … \| xmllint, in2csv, pdftotext) plus a complete guarded shell script, with only minor gaps (no inline Python sandbox snippet).	4 / 5
Workflow Clarity	Six well-sequenced steps with an explicit validation checkpoint (Step 3) and a checklist; the Recovery Protocol adds a feedback loop, though it is reactive rather than a per-step validate-fix-retry loop.	4 / 5
Progressive Disclosure	No references/scripts/assets directories exist; the only bundle file (examples/extraction_fallback.sh) is inlined via an 'Add File' marker rather than a signaled link, and much inline content (Tool-Specific Notes, Recovery Protocol) could live in separate files.	3 / 5
	Total	13 / 20 Passed

Description

42%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 states a clear purpose but omits any explicit trigger ('Use when...') guidance and uses abstract rather than natural user keywords, leaving it indistinguishable in many contexts. Specificity is adequate but not comprehensive.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when a task includes attached reference files (.xlsx, .csv, .pdf, .docx) that should be extracted before web searching.'

Include natural user phrases and file extensions (e.g. 'attached files', 'spreadsheets', '.xlsx', 'reference files') to improve trigger-term quality.

Tighten the action list to concrete verbs with formats (extract, validate, apply fallback extraction) to raise specificity from 3 toward 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain plus two concrete actions ('extract data from context files with validation and fallback strategies') but lacks file-format specificity and is not comprehensive.	3 / 5
Completeness	Has a clear 'what' (extract/validate/fallback before assumptions or searches) but no explicit 'when'/'Use when' trigger guidance, capping completeness at 3.	3 / 5
Trigger Term Quality	Only generic abstract terms ('context files', 'validation', 'fallback strategies'); no natural user phrases and no 'Use when...' clause or file extensions.	2 / 5
Distinctiveness Conflict Risk	Scope ('context files', 'assumptions', 'external searches') is somewhat specific but broad enough to overlap with general data-handling or research skills.	3 / 5
	Total	11 / 20 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: 3827781

Reviewed: 8 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.