opencite

Name: opencite
Author: neuromechanist

37stars7forks

How to install opencite?

neuromechanist/research-skills/opencite

$npx -y skills add neuromechanist/research-skills --skill opencite

Installs into the current project.

Summary

Use this skill for "search for papers", "find citations", "look up a DOI", "get BibTeX", "download PDF", "convert PDF to markdown", "find canonical papers", "convert identifiers", "batch download papers", "configure opencite", "literature review", "find related papers", "what pap

Files · 1

View on GitHub

SKILL.md

1	# OpenCite CLI
2
3	OpenCite is a CLI tool for academic literature search and citation management. It aggregates results from Semantic Scholar, OpenAlex, PubMed, arXiv, and bioRxiv/medRxiv, deduplicates them, and outputs formatted results. It also supports PDF retrieval, PDF-to-markdown conversion, and batch operations.
4
5	## Installation
6
7	```bash
8	# Recommended
9	uv pip install opencite
10
11	# Alternative: run without installing
12	uvx opencite --version
13	```
14
15	PDF conversion support (markitdown and markit-mistral) is included by default. When `MISTRAL_API_KEY` is set, markit-mistral handles math, tables, and complex layouts. Otherwise, markitdown (free, local) is the fallback.
16
17	For development:
18	```bash
19	uv sync --extra dev
20	```
21
22	## Research Workflow
23
24	Follow this end-to-end workflow for literature research, paper retrieval, or reading material on a topic.
25
26	### 1. Search for relevant papers
27
28	Choose the search strategy based on the request:
29
30	- Canonical/foundational papers: `uvx opencite canonical "topic" --max 10`
31	- Recent or specific papers: `uvx opencite search "query" --max 20 --sort citations`
32	- Citation graph exploration: `uvx opencite cite "DOI" --direction both`
33	- Combine strategies when appropriate (e.g., canonical for background + search for recent work)
34
35	### 2. Evaluate and select papers
36
37	Review results considering citation count, relevance, recency, and open access availability. Present a summary and confirm which papers to retrieve.
38
39	### 3. Download and convert
40
41	For multiple papers (preferred): Save search results as JSON and use batch-fetch:
42
43	```bash
44	uvx opencite search "topic" --max 10 -f json -o results.json
45	uvx opencite batch-fetch --from-json results.json --convert -o ./papers --summary report.json
46	```
47
48	`batch-fetch --convert` automatically creates this directory structure:
49
50	```
51	papers/
52	├── pdf/ # downloaded PDFs
53	└── markdown/ # converted markdown files
54	└── img/ # per-paper image directories (mistral only)
55	```
56
57	For individual papers:
58
59	```bash
60	uvx opencite pdf "10.1234/example" -o papers/pdf/ --convert
61	```
62
63	Note: `pdf --convert` places the markdown file next to the PDF and does not extract images. For the organized subdirectory layout with image extraction, use `batch-fetch`.
64
65	### 4. Read and synthesize
66
67	Read the converted markdown files for deeper analysis:
68
69	- Summarize key findings across papers
70	- Identify common themes and disagreements
71	- When using `batch-fetch`, markdown is in `papers/markdown/` and extracted images (markit-mistral only) are in per-paper subdirectories under `papers/markdown/img/`
72	- Generate BibTeX for citation: `uvx opencite lookup "DOI" -f bibtex --append-bib refs.bib`
73
74	## Command Summary
75
76	\| Command \| Purpose \|
77	\|---------\|---------\|
78	\| `search` \| Find papers matching a query across multiple APIs \|
79	\| `lookup` \| Look up a specific paper by DOI, PMID, PMCID, or other identifier \|
80	\| `cite` \| Get citing/cited-by papers for a given identifier \|
81	\| `canonical` \| Find the most-cited, foundational papers for a topic \|
82	\| `pdf` \| Download a PDF for a paper by identifier \|
83	\| `convert` \| Convert a local PDF file to markdown \|
84	\| `ids` \| Convert between identifier types (DOI, PMID, PMCID) \|
85	\| `batch-fetch` \| Download PDFs for multiple papers with optional conversion \|
86	\| `config` \| Manage opencite configuration (init, show, path) \|
87
88	For full option listings, see [references/cli-reference.md](references/cli-reference.md).
89
90	## Configuration Essentials
91
92	Initialize configuration and check resolved values:
93
94	```bash
95	uvx opencite config init # create ~/.opencite/config.toml template
96	uvx opencite config show # display resolved config (keys masked)
97	```
98
99	Key environment variables:
100	- `SEMANTIC_SCHOLAR_API_KEY` - Semantic Scholar API
101	- `PUBMED_API_KEY` - NCBI/PubMed API
102	- `OPENALEX_API_KEY` - OpenAlex API (required since Feb 2026)
103	- `MISTRAL_API_KEY` - Enhanced PDF-to-markdown conversion (optional)
104
105	For full configuration details including publisher tokens and loading priority, see [references/api-keys-and-config.md](references/api-keys-and-config.md).
106
107	## Error Handling
108
109	- Rate limits: Semantic Scholar has aggressive rate limiting (1 req/sec). When rate limit errors occur, wait and retry.
110	- Missing API keys: Commands warn about missing keys but still query available sources.
111	- Timeouts: Retry the command or try a different source with `--source`.
112	- PDF not found: opencite reports which sources were tried and why each failed. Papers behind paywalls

People who liked this also viewed

6 picks

Type

opencite

37stars7forks

View on GitHub

How to install opencite?

neuromechanist/research-skills/opencite

$npx -y skills add neuromechanist/research-skills --skill opencite

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# OpenCite CLI
2
3	OpenCite is a CLI tool for academic literature search and citation management. It aggregates results from Semantic Scholar, OpenAlex, PubMed, arXiv, and bioRxiv/medRxiv, deduplicates them, and outputs formatted results. It also supports PDF retrieval, PDF-to-markdown conversion, and batch operations.
4
5	## Installation
6
7	```bash
8	# Recommended
9	uv pip install opencite
10
11	# Alternative: run without installing
12	uvx opencite --version
13	```
14
15	PDF conversion support (markitdown and markit-mistral) is included by default. When `MISTRAL_API_KEY` is set, markit-mistral handles math, tables, and complex layouts. Otherwise, markitdown (free, local) is the fallback.
16
17	For development:
18	```bash
19	uv sync --extra dev
20	```
21
22	## Research Workflow
23
24	Follow this end-to-end workflow for literature research, paper retrieval, or reading material on a topic.
25
26	### 1. Search for relevant papers
27
28	Choose the search strategy based on the request:
29
30	- Canonical/foundational papers: `uvx opencite canonical "topic" --max 10`
31	- Recent or specific papers: `uvx opencite search "query" --max 20 --sort citations`
32	- Citation graph exploration: `uvx opencite cite "DOI" --direction both`
33	- Combine strategies when appropriate (e.g., canonical for background + search for recent work)
34
35	### 2. Evaluate and select papers
36
37	Review results considering citation count, relevance, recency, and open access availability. Present a summary and confirm which papers to retrieve.
38
39	### 3. Download and convert
40
41	For multiple papers (preferred): Save search results as JSON and use batch-fetch:
42
43	```bash
44	uvx opencite search "topic" --max 10 -f json -o results.json
45	uvx opencite batch-fetch --from-json results.json --convert -o ./papers --summary report.json
46	```
47
48	`batch-fetch --convert` automatically creates this directory structure:
49
50	```
51	papers/
52	├── pdf/ # downloaded PDFs
53	└── markdown/ # converted markdown files
54	└── img/ # per-paper image directories (mistral only)
55	```
56
57	For individual papers:
58
59	```bash
60	uvx opencite pdf "10.1234/example" -o papers/pdf/ --convert
61	```
62
63	Note: `pdf --convert` places the markdown file next to the PDF and does not extract images. For the organized subdirectory layout with image extraction, use `batch-fetch`.
64
65	### 4. Read and synthesize
66
67	Read the converted markdown files for deeper analysis:
68
69	- Summarize key findings across papers
70	- Identify common themes and disagreements
71	- When using `batch-fetch`, markdown is in `papers/markdown/` and extracted images (markit-mistral only) are in per-paper subdirectories under `papers/markdown/img/`
72	- Generate BibTeX for citation: `uvx opencite lookup "DOI" -f bibtex --append-bib refs.bib`
73
74	## Command Summary
75
76	\| Command \| Purpose \|
77	\|---------\|---------\|
78	\| `search` \| Find papers matching a query across multiple APIs \|
79	\| `lookup` \| Look up a specific paper by DOI, PMID, PMCID, or other identifier \|
80	\| `cite` \| Get citing/cited-by papers for a given identifier \|
81	\| `canonical` \| Find the most-cited, foundational papers for a topic \|
82	\| `pdf` \| Download a PDF for a paper by identifier \|
83	\| `convert` \| Convert a local PDF file to markdown \|
84	\| `ids` \| Convert between identifier types (DOI, PMID, PMCID) \|
85	\| `batch-fetch` \| Download PDFs for multiple papers with optional conversion \|
86	\| `config` \| Manage opencite configuration (init, show, path) \|
87
88	For full option listings, see [references/cli-reference.md](references/cli-reference.md).
89
90	## Configuration Essentials
91
92	Initialize configuration and check resolved values:
93
94	```bash
95	uvx opencite config init # create ~/.opencite/config.toml template
96	uvx opencite config show # display resolved config (keys masked)
97	```
98
99	Key environment variables:
100	- `SEMANTIC_SCHOLAR_API_KEY` - Semantic Scholar API
101	- `PUBMED_API_KEY` - NCBI/PubMed API
102	- `OPENALEX_API_KEY` - OpenAlex API (required since Feb 2026)
103	- `MISTRAL_API_KEY` - Enhanced PDF-to-markdown conversion (optional)
104
105	For full configuration details including publisher tokens and loading priority, see [references/api-keys-and-config.md](references/api-keys-and-config.md).
106
107	## Error Handling
108
109	- Rate limits: Semantic Scholar has aggressive rate limiting (1 req/sec). When rate limit errors occur, wait and retry.
110	- Missing API keys: Commands warn about missing keys but still query available sources.
111	- Timeouts: Retry the command or try a different source with `--source`.
112	- PDF not found: opencite reports which sources were tried and why each failed. Papers behind paywalls

People who liked this also viewed

6 picks

Type