research-lookup
Look up current research information using parallel-cli search (primary, fast web search), the Parallel Chat API (deep research), or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information.
60
71%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/research-lookup/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates its purpose, lists specific tools and capabilities, and provides explicit trigger guidance. It names three distinct backends with their specializations, making it easy for Claude to understand when to select this skill. The description is concise yet comprehensive, covering both the 'what' and 'when' effectively.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Look up current research information', 'finding papers', 'gathering research data', 'verifying scientific information'. Also names three specific backends (parallel-cli search, Parallel Chat API, Perplexity sonar-pro-search) with their specialties. | 3 / 3 |
Completeness | Clearly answers both 'what' (look up research information using three specific backends with automatic routing) and 'when' ('Use for finding papers, gathering research data, and verifying scientific information'). The 'Use for...' clause serves as an explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'research', 'papers', 'academic paper', 'scientific information', 'search', 'deep research', 'verify'. These cover common variations of how users would phrase research-related requests. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly occupies a distinct niche around research/academic information lookup with specific tool names (parallel-cli, Parallel Chat API, Perplexity sonar-pro-search). The focus on scientific papers and research data makes it unlikely to conflict with general web search or document processing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable commands with clear backend routing logic, which is its primary strength. However, it is severely undermined by extreme verbosity and repetition — the same parallel-cli commands appear nearly identically across 5+ sections, and concepts like saving to sources/ are restated excessively. The content would benefit enormously from consolidation and splitting detailed reference material (venue tiers, citation formats, API specs) into separate files.
Suggestions
Consolidate the repeated parallel-cli search command examples into a single 'Command Reference' section or external file, and reference it from other sections instead of duplicating the full command each time.
Move the Paper Quality/Venue Tiers table and Citation Preservation details into separate reference files (e.g., PAPER_QUALITY.md, CITATION_FORMATS.md) and link to them from the main skill.
Remove redundant explanations of the saving requirement — state it once clearly with the rules table, then simply reference it (e.g., 'Always save results per the rules above') instead of repeating the full rationale and examples in multiple sections.
Add explicit validation steps to the workflow: e.g., check that saved JSON is non-empty, verify result count meets expectations, and confirm academic sources were found before proceeding with synthesis.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. The same parallel-cli search commands are shown 5+ times with nearly identical arguments. The saving rules, citation preservation, and backend routing are explained redundantly across multiple sections. The document is ~400 lines when it could convey the same information in ~100-150 lines. Sections like 'Why Save Everything' and 'Integration with Scientific Writing' add little value for Claude. | 1 / 3 |
Actionability | Provides fully executable, copy-paste-ready bash commands with specific flags, domain lists, and output paths. The parallel-cli search examples are concrete and complete. Manual override commands and API specifications are clearly documented with real endpoints and model names. | 3 / 3 |
Workflow Clarity | The routing logic flowchart is clear, and the two-search pattern for academic queries is well-sequenced. However, there are no explicit validation checkpoints — no steps to verify search results quality, check for empty results, or validate that saved files are complete before proceeding. The fallback behavior section mentions error handling but doesn't integrate it into a step-by-step workflow. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files for detailed content. The paper quality tiers, venue rankings, API specifications, citation preservation details, and extensive usage examples are all inline when they could be split into separate reference files. The complementary tools table references other skills but the core content itself is not progressively disclosed. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (551 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
33b69c5
- Reviewed
Table of Contents
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.