research

Default entry point for any research request — a hybrid router that classifies the question deterministically and either delegates to a specialist research skill (pulse for trends/sentiment, grants for NIH funding, litreview for academic literature, syllabus for course reading, patent for prior-art + IP landscape, dossier for entity research, deepread for evidence-first reading of supplied documents) or runs its own plan-decompose-multi-source-search-synthesize-cite fallback workflow when no specialist matches. Always surfaces the routing decision so users can override. Use when the user makes any research request that doesn't obviously match a more-specific specialist skill (e.g., "research [topic]", "look into [topic]", "what do we know about [topic]", "investigate [topic]", "find me information on [topic]", "do some research on [topic]", "I need to understand [topic]"). Output is a markdown briefing (default) or .docx document (on request) with full citations and an audit log.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

78%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 content is a well-structured, largely executable hybrid-router skill body with strong progressive disclosure and concrete tooling calls. The main gaps are minor verbosity, described-but-not-specified delegated behavior, and batch-workflow checkpoints that are present but somewhat implicit.

Suggestions

Consolidate the repeated 'Never delegates silently' / routing-transparency emphasis into the single Routing Transparency Protocol section to recover tokens.

Frame the fallback batch-search workflow as an explicit validate-checkpoint loop (e.g., after each sub-question: confirm sources received → if <2 sources, widen query → only proceed when adequate) to lift workflow clarity above its current implicit-checkpoint state.

Add a one-line runnable note for the delegation path (e.g., the exact specialist invocation contract) so delegation is as actionable as the fallback path.

Dimension	Reasoning	Score
Conciseness	The body is well-organized and free of PDF-style padding, but at ~250 lines it carries some restatable emphasis (e.g., 'Never delegates silently' recurs several times) and minor expository prose that could be trimmed.	4 / 5
Actionability	Provides concrete executable commands ('scripts/classifier.py --question "..." --output json', 'routing_transparency_logger.py --action record_override') and a real SIGNALS dict, but the delegated specialists' internal behavior is described rather than given as runnable steps.	4 / 5
Workflow Clarity	Phases 1→2→3a/3b are clearly sequenced with a failure-mode table and a retry/stop policy, but the batch fallback-search workflow relies on implicit checkpoints (the 3-consecutive-failure stop is stated but not framed as an explicit validate-then-proceed loop).	4 / 5
Progressive Disclosure	Clear overview with well-signaled, one-level-deep references to three verified reference docs and a scripts section, plus an organized specialist registry table — easy to navigate with no nested references.	5 / 5
	Total	17 / 20 Passed

Description

96%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 is specific, comprehensive, and rich with natural trigger terms while clearly answering both what and when. Its only weakness is mild conflict risk from the generic 'research' label and sibling specialist skills, which the body (but not the description) clarifies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'classifies the question deterministically', delegates to seven named specialists, and 'runs its own plan-decompose-multi-source-search-synthesize-cite fallback workflow' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (hybrid router that classifies deterministically and delegates or runs a fallback workflow) and 'when' ('Use when the user makes any research request that doesn't obviously match a more-specific specialist skill') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Enumerates seven natural phrasings users actually say ('research [topic]', 'look into [topic]', 'what do we know about [topic]', 'investigate [topic]', 'find me information on [topic]', 'do some research on [topic]', 'I need to understand [topic]'), with comprehensive synonym coverage.	5 / 5
Distinctiveness Conflict Risk	Has a clear niche as a research-query router with distinct triggers, but the generic word 'research' and adjacency to engineering/autoresearch-agent and the listed specialists create minor overlap risk that the description does not itself disambiguate.	4 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: research/research/skills/research/SKILL.md
Commit: 19392f7

Reviewed: ~1 hour 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.