gracefullight/pkgs / .agents/skills/oma-scholar
oma-scholar
UnverifiedSearch academic literature and generate, validate, or compare Knows paper sidecars. Use for claim/evidence analysis and literature synthesis.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 14.2 KB |
| config/scholar-config.yaml | config | 2.7 KB |
| resources/api-endpoints.md | markdown | 4.7 KB |
| resources/checklist.md | markdown | 3.8 KB |
| resources/execution-protocol.md | markdown | 9.0 KB |
| resources/fallback-providers.md | markdown | 6.0 KB |
| resources/setup-openalex.md | markdown | 2.5 KB |
| resources/sidecar-spec.md | markdown | 10.8 KB |
| resources/upstream-spec-cache.md | markdown | 43.7 KB |
config/scholar-config.yaml
View on GitHub# oma-scholar configuration
# Knows sidecar generation and remote access settings
# Remote API
# `base_url` is the one user-tunable key here (self-hosted knows instances).
# Set it as `scholar.base_url` in .agents/oma-config.yaml, which wins and which
# `oma update` preserves — this file is overwritten and supplies only the
# shipped default. Everything else below is protocol shape.
api:
base_url: https://knows.academy
endpoints:
search: /api/proxy/search
sidecar: /api/proxy/sidecars/{record_id}
partial: /api/proxy/partial
stats: /api/proxy/jobs/stats
# No auth required for proxy endpoints
timeout_seconds: 30
# Partial-fetch defaults: fields you can request individually
# (must match `oma scholar get --section` enum; methods/provenance are NOT
# available via partial fetch — fetch the full sidecar for those)
partial_fields:
available:
- statements
- evidence
- relations
- artifacts
- citation
default_for_summary:
- statements
- citation
# Semantic Scholar fallback (optional key)
# Tier-3 search fallback + `get arXiv:<id>` / `CorpusId:<n>` direct fetch.
# Anonymous use shares a global pool (429s under load; CLI retries once).
semanticscholar:
env_var: S2_API_KEY # sent as x-api-key header
key_request_url: https://www.semanticscholar.org/product/api
# OpenAlex metadata enrichment (optional)
# Used during Generate mode to backfill DOI/venue/year when missing
openalex:
enabled_when_key_present: true
env_var: OPENALEX_API_KEY
# Polite-pool email also accepted for higher anonymous rate limits
polite_pool_env_var: OPENALEX_EMAIL
signup_url: https://openalex.org/
settings_url: https://openalex.org/settings/api
# Free daily allowance (no key): $1 value, ~10K list calls, ~1K search calls
# Sidecar generation defaults
generation:
# Minimum number of statements before warning user about under-extraction
min_statements_complex_paper: 15
# Average relations per statement (relation wiring quality threshold)
min_relations_per_statement: 1.5
# ID format
# Methods are statements (statement_type: method) and use "stmt:"; actors have no ids
id_prefixes:
statement: "stmt:"
evidence: "ev:"
relation: "rel:"
artifact: "art:"
representation: "rep:"
# Output behavior
output:
# When no output path is specified:
# "same_dir" = output next to the input source file
# "cwd" = output in current working directory
default_location: same_dir
filename_pattern: "{base}.knows.yaml"
review_filename_pattern: "{base}.review.knows.yaml"
overwrite: false # Prompt before overwriting existing files
# Lint behavior
lint:
command: "oma scholar lint"
fail_on_warning: false
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 |