K-Dense-AI/scientific-agent-skills / skills/research-lookup
research-lookup
VerifiedCompiles current scholarly evidence for a scientific manuscript or research brief when the user explicitly asks to gather literature, references, background evidence, competing findings, or a manuscript research packet. Uses Parallel Search by default, Parallel Extract for source retrieval, Parallel Research for explicitly deep/exhaustive work, optional explicit Parallel Chat, and optional Perplexity only when requested or allowed as a failure fallback.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 4.1 KB |
| SKILL.md | skill md | 16.8 KB |
| references/api-contracts.md | markdown | 6.5 KB |
| scripts/manuscript_packet.py | script | 27.4 KB |
| scripts/research_lookup.py | script | 47.3 KB |
README.md
View on GitHub# Research Lookup
Parallel-first evidence compilation for scientific manuscripts. Academic retrieval
targets 60 verified, unique references by default and produces a research packet with
structured study evidence, claim provenance, contradictions, gaps, and section briefs.
`SKILL.md` is the authoritative workflow and safety reference.
## Routing
| Request | Backend |
|---|---|
| Manuscript literature or many academic references | Parallel Search + Extract |
| Fast current-information lookup | Parallel Search |
| Explicit deep/exhaustive report | Parallel Research |
| Explicit OpenAI-compatible synthesis | Parallel Chat |
| Optional alternative/failure fallback | Perplexity through OpenRouter |
A bare query uses Parallel Search. Parallel Chat remains available through
`--force-backend chat`, but automatic routing never selects it. The legacy
`--force-backend parallel` flag remains an alias for explicit Parallel Research.
## Setup
```bash
uv tool install "parallel-web-tools[cli]==0.9.3"
parallel-cli login
parallel-cli auth
```
CLI login may be replaced by `PARALLEL_API_KEY`. `OPENROUTER_API_KEY` is needed only
for explicit Perplexity use or an enabled fallback. Explicit Chat requires
`PARALLEL_API_KEY` in the process environment.
Both direct HTTP backends need `requests`; the CLI uses its own isolated tool
environment. Headless login in 0.9.3 is `parallel-cli login --no-browser`.
## Manuscript packet
```bash
python skills/research-lookup/scripts/research_lookup.py \
"Evidence for the manuscript research question" \
--academic \
--target-references 60 \
--context-file manuscript-context.json \
--packet-dir sources/manuscript-research \
--json
```
The academic workflow runs bounded searches for primary studies, reviews and
meta-analyses, seminal publications, methods/mechanisms, and contradictory evidence.
It deduplicates candidates and verifies the strongest sources in batches with
Parallel Extract.
Packet artifacts include:
- complete packet in JSON and Markdown
- normalized references in JSON and BibTeX
- evidence matrix
- claim-to-source map
- synthesis of consensus, conflicts, patterns, and gaps
- Introduction, Methods-rationale, and Discussion briefs
- coverage diagnostics and reproducible search ledger
The target is not padded. If 60 credible references cannot be verified, the packet
reports the shortfall.
`verified_references` means nonempty excerpts were retrieved by Extract, excluding
flagged retractions. DOI/PMID detection alone does not count. Review identity, claim
support, and correction/retraction status yourself before using the bibliography.
## Preserved compatibility
- reusable `ResearchLookup` class
- `--batch`, `--json`, and `-o/--output`
- explicit backend selection
- per-query error isolation
- DOI/URL citation extraction
- human-readable and structured output
- result fields such as `success`, `query`, `response`, `citations`, `sources`,
`timestamp`, `backend`, `model`, and `usage`
## Other modes
```bash
# Fast bounded Search
python skills/research-lookup/scripts/research_lookup.py \
"Latest official guidance" --no-academic
# Explicit Parallel Research
python skills/research-lookup/scripts/research_lookup.py \
"Comprehensive review of topic" \
--force-backend research \
--processor pro
# Explicit Parallel Chat (never automatic)
python skills/research-lookup/scripts/research_lookup.py \
"Synthesize the strongest evidence" \
--force-backend chat \
--chat-model core
# Explicit Perplexity
python skills/research-lookup/scripts/research_lookup.py \
"Find academic evidence" \
--force-backend perplexity
```
## Boundaries
This skill compiles external evidence. It does not generate the user's unpublished
Results or guarantee a PRISMA-complete systematic review. Use `literature-review` for
formal database searching, screening, exclusion tracking, and risk-of-bias procedures;
use `scientific-writing` to turn the packet into manuscript prose.
API contracts were reviewed on 2026-09-30 against official schemas, CLI 0.9.3,
and public OpenRouter model metadata. Service examples are illustrative; regression
tests mock paid calls. See [API contracts](references/api-contracts.md).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |