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.
72
67%
Does it follow best practices?
Impact
Pending
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
92%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 identifies specific tools and backends, concrete actions, and explicit usage triggers. It effectively communicates both what the skill does and when to use it. The main weakness is a slight overlap risk with other search or information-retrieval skills due to broad terms like 'research information' and 'web search', though the named tools and academic focus help mitigate this.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Look up current research information', 'parallel-cli search', 'Parallel Chat API (deep research)', 'Perplexity sonar-pro-search (academic paper searches)', 'finding papers', 'gathering research data', 'verifying scientific information'. Names specific tools and backends. | 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', 'scientific information', 'search', 'deep research', 'web search'. Covers multiple variations of research-related queries a user might naturally express. | 3 / 3 |
Distinctiveness Conflict Risk | While it specifies research and academic contexts with named tools, the broad terms 'research information' and 'web search' could overlap with general web search or information retrieval skills. The specific tool names (parallel-cli, Perplexity sonar-pro-search) help but the domain could still conflict with other search-oriented skills. | 2 / 3 |
Total | 11 / 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 5-6 times, and the saving instructions are repeated extensively. The content would benefit enormously from splitting reference material (venue tiers, API specs, citation formats) into separate files and eliminating redundant examples.
Suggestions
Eliminate redundant command examples — show the parallel-cli search pattern once with clear variable placeholders, then reference it rather than repeating full commands 5-6 times
Move paper quality tiers, venue rankings, API specifications, and citation format tables into separate reference files (e.g., PAPER_QUALITY.md, API_REFERENCE.md) and link to them from the main skill
Add explicit validation steps: check that saved JSON files are non-empty, verify result count meets minimum threshold, and include a retry/rephrase loop for insufficient results
Remove the 'When to Use This Skill' and 'Summary' sections — the overview already covers routing, and the summary is pure repetition
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines with massive repetition. The same parallel-cli search commands are shown 5-6 times with nearly identical arguments. The 'Save All Results' section repeats saving instructions multiple times. Tables for citation thresholds, venue tiers, and complementary tools add bulk that Claude already knows or doesn't need inline. The summary section restates what was already covered. | 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 with real arguments. API specifications include endpoints, models, and latency expectations. | 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 step to verify search results quality, check for empty results, or validate that saved files are non-empty before proceeding. The fallback behavior section mentions retrying but doesn't integrate it into a clear workflow with feedback loops. | 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 could all be split into separate reference files. Everything is inlined, making the skill extremely long and hard to navigate. | 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
25e1c0f
- 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.