Skill
scholar-deep-research/SKILL
Use when the user asks for a literature review, academic deep dive, research report, state-of-the-art survey, topic scoping, comparative analysis of methods/papers, grant background, or any request that needs multi-source scholarly evidence with citations. Also trigger proactively when a user question clearly requires academic grounding (e.g. "what's known about X", "compare approach A vs B in the literature", "summarize the field of Y"). Runs an 8-phase (Phase 0..7), script-driven research workflow across OpenAlex, arXiv, Crossref, and PubMed, with deduplication, transparent ranking, citation chasing, self-critique, and structured report output with verifiable citations.
○ declared by the publisher, as-isSafety
Safety · gateassessed 3mo ago
B8 severity-bearing · 44 informational
Graded from 8 severity-bearing findings on this release.
A gate; it passes or fails, never weighed against price or quality.
Reliability & Quality
n/a
Reliability & Qualityassessed 3mo ago
n/anot assessed
Not assessed; no producer has emitted into this category. An absence, not a zero.
Findings with severity, graded on the same letter scale as safety.
not assessed
Cost
n/a
Costassessed 3mo ago
n/anot assessed
Not assessed; no producer has emitted into this category. An absence, not a zero.
Declared external service dependencies. Never a monetary figure.
not assessed
Popularity
n/a
Popularity · not a figureassessed 3mo ago
n/anot assessed
Not assessed; no producer has emitted into this category. An absence, not a zero.
Context read off the linked repository. It enters no ranking and no grade.
not assessed
Performance tested for◌ not assessed
no controlled task evaluation on this release
Repo◌ not assessed
Vettd Note
No Vettd note yet for this asset.
Best for
Not for
Re-assessed 3mo ago · 1 of 7 categories assessed
Record lookup
◌ Vettd does not install assets; this record describes a copy you obtain yourself.
Custody chain○ no source link recorded
Unknown author ◐repo △ not assessedversion = △ no commit pinnedsha256:cmro…vz2d ◐ signature △ not assessedlicense △ none declaredrecord 67db385a-6a3f-4fae-b23e-7bf3d7e7766a · live
Evidence · 1 of 7 categories · 52 signals
Safety● gradedBmost recent 3mo ago52 signals
how it was established52 signals · vettd · scan
show
References external URL — review for indirect prompt injection riskflaggedExternal URL(s) detected in SKILL.md — referenced content can change after auditvettd · scan · 3moMedium
Safety bypass flag detectedflaggedDetected in scripts/tests/test_agent_native.py:6 — `- init --force / --dangerous gating (confirmation_required)`vettd · scan · 3moLow
Unpinned dependency versionsflaggedscripts/_gates.py: Pin dependency versions for reproducibility (e.g., >=4.12,<5 instead of >=4.12)vettd · scan · 3moLow
Unpinned dependency versionsflaggedscripts/export_bibtex.py: Pin dependency versions for reproducibility (e.g., >=4.12,<5 instead of >=4.12)vettd · scan · 3moLow
Description overclaims scopeflaggedBroad trigger words (anything, everything, all files, etc.) widen attack surface — narrow to specific use casesvettd · scan · 3moLow
Unpinned dependency versionsflaggedscripts/search_arxiv.py: Pin dependency versions for reproducibility (e.g., >=4.12,<5 instead of >=4.12)vettd · scan · 3moLow
Safety bypass flag detectedflaggedDetected in scripts/check_update.py:13 — ``--force` to bypass the throttle when they know something upstream`vettd · scan · 3moLow
Safety bypass flag detectedflaggedDetected in scripts/research_state.py:176 — `Used by `cmd_init` (where the file is created fresh under --force`vettd · scan · 3moLow
scripts/ directory presentflaggedBundled executable scripts foundvettd · scan · 3moInfo
CLI help supportedflaggedscripts/check_update.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
Structured output formatflaggedscripts/tests/test_ingest_roundtrip.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
Structured output formatflaggedscripts/tests/test_locking.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
SKILL.md presentflaggedRequired skill definition file foundvettd · scan · 3moInfo
Description includes usage contextflaggedGood: description explains when to activate the skillvettd · scan · 3moInfo
Progressive disclosure usedflaggedSKILL.md body references files in references/, scripts/, or assets/ — agents can load additional context on demand instead of consuming everything upfrontvettd · scan · 3moInfo
CLI help supportedflaggedscripts/extract_pdf.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
Valid name fieldflaggedName "scholar-deep-research" follows spec (lowercase, hyphens, ≤64 chars)vettd · scan · 3moInfo
No repository linkflaggedNo repository field found in SKILL.md frontmatter. Skills without a verifiable source repository cannot be externally audited.vettd · scan · 3moInfo
Examples includedflaggedFound code blocks, input/output samples, or an examples section — concrete samples help agents pattern-match effectivelyvettd · scan · 3moInfo
No --help supportflaggedscripts/_locking.py: Add argument parsing with --help output so agents know the script's interfacevettd · scan · 3moInfo
CLI help supportedflaggedscripts/dedupe_papers.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
CLI help supportedflaggedscripts/search_openalex.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
CLI help supportedflaggedscripts/tests/test_envelope.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
CLI help supportedflaggedscripts/build_citation_graph.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
Structured output formatflaggedscripts/export_bibtex.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
CLI help supportedflaggedscripts/tests/test_gates.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
assets/ directory presentflaggedStatic resources (templates, schemas, etc.) foundvettd · scan · 3moInfo
Structured output formatflaggedscripts/tests/test_gates.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
CLI help supportedflaggedscripts/tests/test_locking.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
CLI help supportedflaggedscripts/tests/test_schema.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
CLI help supportedflaggedscripts/tests/run.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
No prompt injection or jailbreak signals detectedflaggedScanned text content for instruction override, jailbreak framing, credential solicitation, and embedded injection markersvettd · scan · 3moInfo
references/ directory presentflaggedAdditional documentation files available for progressive disclosurevettd · scan · 3moInfo
Description within character limitflagged680/1024 characters usedvettd · scan · 3moInfo
Step-by-step workflow foundflaggedStructured procedures improve reliability for complex tasksvettd · scan · 3moInfo
CLI help supportedflaggedscripts/rank_papers.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
CLI help supportedflaggedscripts/search_arxiv.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
CLI help supportedflaggedscripts/search_crossref.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
SKILL.md body length is reasonableflagged105 lines (recommended: under 500)vettd · scan · 3moInfo
CLI help supportedflaggedscripts/export_bibtex.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
CLI help supportedflaggedscripts/tests/test_export_formats.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
No secrets or unsafe code patterns detectedflaggedScanned all files for credentials, private keys, and code-level risks (eval, shell exec, destructive ops)vettd · scan · 3moInfo
CLI help supportedflaggedscripts/research_state.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
Structured output formatflaggedscripts/research_state.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
Structured output formatflaggedscripts/_common.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
Structured output formatflaggedscripts/_locking.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
CLI help supportedflaggedscripts/search_pubmed.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
CLI help supportedflaggedscripts/_common.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
Structured output formatflaggedscripts/tests/test_export_formats.py: Uses JSON/CSV output which is easily parseable by agentsvettd · scan · 3moInfo
CLI help supportedflaggedscripts/tests/test_ingest_roundtrip.py: Script documents its interface via --help or argument parsingvettd · scan · 3moInfo
No evaluation test casesflaggedAdd an evals/ directory with test prompts and expected outputs to measure skill qualityvettd · scan · 3moInfo
No --help supportflaggedscripts/_gates.py: Add argument parsing with --help output so agents know the script's interfacevettd · scan · 3moInfo
Reliability & Quality◌ not assessednot assessed0 signals
how it was establishednot assessed; no producer has emitted into this category
Not assessed; no producer has emitted into reliability & quality for this asset. That is different from a check that ran and found nothing, which the record would carry as a row of its own.
Performance◌ not assessednot assessed0 signals
how it was establishednot assessed; no producer has emitted into this category
Not assessed; no producer has emitted into performance for this asset. That is different from a check that ran and found nothing, which the record would carry as a row of its own.
Cost◌ not assessednot assessed0 signals
how it was establishednot assessed; no producer has emitted into this category
Not assessed; no producer has emitted into cost for this asset. That is different from a check that ran and found nothing, which the record would carry as a row of its own.
Compatibility◌ not assessednot assessed0 signals
how it was establishednot assessed; no producer has emitted into this category
Not assessed; no producer has emitted into compatibility for this asset. That is different from a check that ran and found nothing, which the record would carry as a row of its own.
Popularity◌ not assessednot assessed0 signals
how it was establishednot assessed; no producer has emitted into this category
Not assessed; no producer has emitted into popularity for this asset. That is different from a check that ran and found nothing, which the record would carry as a row of its own.
Characteristics◌ not assessednot assessed0 signals
how it was establishednot assessed; no producer has emitted into this category
Not assessed; no producer has emitted into characteristics for this asset. That is different from a check that ran and found nothing, which the record would carry as a row of its own.
Coverage1 of 7 categories assessed · shown
Safety
✓ assessed
assessed as findings and a letter grade, not as signals
Reliability & Quality
△ not assessed
no producer has emitted for this category
Performance
△ not assessed
no producer has emitted for this category
Cost
△ not assessed
no producer has emitted for this category
Compatibility
△ not assessed
no producer has emitted for this category
Popularity
△ not assessed
no producer has emitted for this category
Characteristics
△ not assessed
no producer has emitted for this category
Freshness & re-evaluation
assessed3mo ago · Vettd core○ untracked
source stateThis asset is not yet covered by scheduled change detection.
re-check policyno re-check is scheduled for this assetnot scheduled
re-run whena new release ships, the upstream source changes, or the scanner ruleset is revisednot scheduled
Limitations & open conflicts
limitationReliability & Quality, Performance, Cost, Compatibility, Popularity, Characteristics are not assessed: behaviour there is unmeasured, not clean△ gap
conflictno two sources report the same quantity on this record
Verify: does this record describe your copy?
What record 67db385a-6a3f-4fae-b23e-7bf3d7e7766a covers
scannerv1△ superseded by v11
validityassessed 3mo ago · Staleness unknown
this record was taken at digest sha256:cmrockde602d… compare it against the digest your own scan prints
Reproduce: re-run the evidence yourself
runs the same scanners against your own copy; the published record is never overwritten
How this record comparesagainst other published records · full comparison →
Signal kinds
▲ finding: something to act on, carries a severity● measurement: a reproducible quantityƒ estimate: inferred from a sample▪ fact: read directly off the artifact◆ classification: assigned from a taxonomy◌ nothing found: a producer looked and emitted no object◇ context only: described, never graded
Custody marks◐ computed by vettd○ declared by the publisher, as-is△ not assessed: nothing looked