prioritize-context-data

Ensures agents check and use provided context files for data before attempting external searches.

Quality

58%

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/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 body is a clear, actionable, well-sequenced workflow with concrete tool names, a worked example, and a validation checklist, scoring well on actionability and workflow clarity. Its main weakness is conciseness, where rationale and warnings sections add tokens that do not earn their place.

Suggestions

Trim the 'Warnings' section and inline rationale ('Reading a local file is faster...', 'Users attach files expecting them to be used') since Claude already understands these tradeoffs, keeping only the operational rule.

Make the abstract Step 2 ('Determine if any provided file contains the data required') more concrete by specifying how to match, e.g., 'open the file and scan headers/first rows rather than relying on filename alone'.

Consider shortening the Example Usage section to one compact correct example, since the Incorrect Approach largely restates the Critical Rule.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with well-organized steps and a checklist, but the 'Warnings' section and rationale lines like 'Reading a local file is faster and more reliable than web scraping' and 'Users attach files expecting them to be used' add tokens Claude does not need, fitting score 3; it is above 2 because there is no heavy padding or explaining of basic concepts, but below 4 due to these removable justification sections.	3 / 5
Actionability	The guidance names concrete tools ('read_file', 'pandas', 'pdf_reader'), gives a worked incorrect-vs-correct example with sample output, and provides a verifiable checklist, fitting score 4 for an instruction-only skill; it is not a 5 because some steps remain abstract ('Determine if any provided file contains the data required') without a concrete method, and not a 3 because executable tool names and a complete example are present.	4 / 5
Workflow Clarity	A clear five-step sequence is present with an explicit gate ('Do not proceed to web search until you have confirmed the file lacks the necessary information') and a closing checklist as a validation checkpoint, matching score 4; it is not a 5 because there is no error-recovery feedback loop, and not a 3 because the sequence and main checkpoints are explicit rather than implicit.	4 / 5
Progressive Disclosure	The single self-contained file is well-organized with clear section headers (Objective, Critical Rule, Workflow Steps, Checklist, Example Usage, Warnings) and needs no external references, fitting score 4; it is not a 5 because the body exceeds 50 lines and the Example Usage and Warnings sections could be tightened, placing it just above the simple-skill exception threshold.	4 / 5
	Total	15 / 20 Passed

Description

50%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 but lacks an explicit 'Use when...' trigger clause and natural trigger terms users would actually say, capping completeness and trigger quality at 3. It is competent but generic, missing file-extension keywords and synonyms that would improve discoverability and distinctiveness.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should apply this skill (e.g., 'Use when context files are attached to a task or when about to search the web for data that may be in provided files').

Include natural trigger terms and file extensions users actually say, such as 'attached files', 'provided files', 'spreadsheet', 'CSV', '.xlsx', '.pdf'.

Add one or two more specific actions (e.g., 'reads and extracts data from attached files before searching the web') to raise specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names the domain ('provided context files for data') and two concrete actions ('check and use'), but the actions are generic and coverage is not comprehensive, matching the score-3 anchor; it is not a 2 because the domain is clearly named with more than minimal action, and not a 4 because it lists no specific operations like extraction or parsing.	3 / 5
Completeness	The 'what' is clear ('Ensures agents check and use provided context files for data') but the 'when' is only weakly implied via 'before attempting external searches' with no explicit 'Use when...' clause, which per the judging guidelines caps completeness at 3; it is not a 4 because there is no explicit trigger guidance.	3 / 5
Trigger Term Quality	Relevant keywords appear ('context files', 'data', 'external searches') but common natural variations users would actually say ('attached files', 'provided files', 'spreadsheet', 'CSV', file extensions) are missing, fitting score 3; it is above 2 because more than one relevant term is present, but below 4 due to absent synonyms and extensions.	3 / 5
Distinctiveness Conflict Risk	The prioritization niche is somewhat specific but the phrasing ('check and use provided context files for data') is broad and could overlap with file-reading or data-analysis skills, matching score 3; it is not a 4 because the triggers are not distinct enough to minimize overlap with closely related skills.	3 / 5
	Total	12 / 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/SKILL.md
Commit: 3827781

Reviewed: 6 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.