Research & Search
Research agent skills teach AI agents to gather and synthesize information properly: literature reviews, competitive analysis, web research with citations, and structured summaries. Each SKILL.md encodes a method, not just a prompt, so results stay consistent across runs.
-
sboghossian-mini-claude-for-legal Skill Research Jurisdiction ComparisonUse when a user needs to compare how a specific legal issue is handled across multiple jurisdictions — to choose where to incorporate, where to arbitrate, which governing law to select, or to understand cross-border deal risk. Produces a structured comparison table with per-jurisdiction columns covering statute, rule, enforceability, duration limits, and risk; concludes with a recommendation. Covers MENA (LB, KSA, UAE onshore, DIFC, ADGM, EG) and secondary jurisdictions (UK, US-DE, FR, EU). Each cell must cite a real source.
-
sboghossian-mini-claude-for-legal Skill Conversation Professional B2bUse when the user is identified as a lawyer, in-house counsel, paralegal, or legal professional (B2B audience) and Claude should adopt a terse, citation-dense, structured response mode rather than a consumer-friendly explanatory style. This is a core persona skill that modifies all output format defaults. Activates on user identification signals (job title, firm name, bar membership, professional vocabulary) or on explicit platform-level B2B context.
-
sboghossian-mini-claude-for-legal Skill Output Citation Format Civil Law FrUse when formatting legal citations in the French civil-law style (Dalloz / JurisClasseur convention) for case law, statutes, and doctrine. Applies to outputs destined for francophone MENA jurisdictions (Lebanon, Morocco, Tunisia) as well as France — where citation style follows Cass. com./Civ./soc. conventions rather than Bluebook or OSCOLA.
-
sboghossian-mini-claude-for-legal Skill Research Recent Amendments TrackerUse when a user asks whether a statute is current, whether something has recently changed in a jurisdiction, or whether a previously researched answer has been superseded. Checks official gazettes, legislative portals, and regulator notices across MENA (Lebanon Official Gazette, KSA Umm Al-Qura, UAE Federal and emirate gazettes, DIFC Laws portal, ADGM Legislation portal) and secondary jurisdictions (EU Official Journal, FR Légifrance, UK legislation.gov.uk). Returns current version date, last amendment summary, notable interpretive rulings, and pending changes with status.
-
jmagly-ai-writing-guide Bundle Induct MediaInduct acquired audio/video, transcript sidecars, and source metadata from media-curator into research-complete REF artifacts with timestamp citations and storage policy records
-
jmagly-ai-writing-guide Skill Sidecar LintLint and repair citation sidecars in a research corpus — structural integrity (missing Outgoing/Incoming sections, missing frontmatter ref/title/type, doubled-append duplicate table headers), zero-edge orphan detection, (see REF doc) author backfill from the analysis citation block, and affiliation-primary canonicalization to PROF-O slugs. Runs via `aiwg corpus sidecar-lint` / `aiwg corpus sidecar-repair`.
-
jmagly-ai-writing-guide Skill Verify CitationsVerify all citations in a document against the research corpus
-
sboghossian-mini-claude-for-legal Skill Research Deep Research OrchestratorUse when a legal question requires multi-step, multi-source, multi-jurisdiction research equivalent to a senior associate's full memo — not a quick lookup. Triggers on "I need this for a memo," "for a client opinion," multi-jurisdictional questions, or when confidence on a high-stakes question is low. Orchestrates sub-agents for statute lookup, case-law search, regulator guidance, and amendments tracking; synthesizes into a structured legal memo with table of authorities. Slow and credit-intensive — always estimates cost upfront and confirms with user.
-
sboghossian-mini-claude-for-legal Skill Connector Cocounsel Thomson ReutersUse when a lawyer needs to hand off a complex legal research query to Thomson Reuters CoCounsel — the AI-assisted research layer built on TR's Westlaw database — because the query requires case law retrieval, statutory interpretation, or secondary-source research at a depth beyond the in-house skill set. Requires the user's organization to hold an active Thomson Reuters enterprise license. Triggers on requests involving US case law, multi-jurisdictional statutory research, or deep regulatory analysis where TR's curated legal database adds verifiable authority.
-
sboghossian-mini-claude-for-legal Skill Output Inline Citations With PinpointsUse when Claude must embed legal authority inline within analysis, memos, or drafted clauses with precise pin-cites. Applies across MENA (UAE, KSA, Lebanon, Egypt), DIFC/ADGM, and common-law (UK, US) contexts. Triggers on any request for citation format, source referencing, or when another skill must support its legal propositions with verified authority.
-
sboghossian-mini-claude-for-legal Skill Research Beneficial Ownership LookupUse when a lawyer, compliance officer, or KYC analyst needs to identify the ultimate beneficial owners (UBOs) of a company or structure — piercing through nominee shareholders, holding vehicles, and trust arrangements to identify natural persons with ≥ 25% ownership or equivalent control. Covers MENA (UAE, KSA, Lebanon, Egypt, BVI/Cayman offshore structures common in the region), UK, and EU registries. Integrates sanctions screening and known-nominee cross-checks.
-
jmagly-ai-writing-guide Skill Corpus ExportPackage corpus subsets as distribution archives. Filter by cluster, topic, REF range, or custom expression; bundles PDFs, analysis, citations, and BibTeX into tar.gz.
-
sboghossian-mini-claude-for-legal Skill Safety AI Disclosure Required TribunalsUse when a lawyer or user indicates that AI-assisted work product (research, drafts, briefs, or submissions) will be filed with or presented to a court, tribunal, or regulatory body. Triggers the appropriate AI-disclosure reminder and citation-verification warning based on the forum's rules. Covers US courts (post-Mata v. Avianca standing orders), UK Bar Standards Board guidance, DIFC/ADGM courts, KSA/UAE onshore courts, French ordre des avocats, and EU AI Act implications. Hard-blocks any request to conceal AI use from a tribunal.
-
jmagly-ai-writing-guide Skill Research LintRun the research corpus lint ruleset to detect structural and referential integrity issues — orphan notes, missing frontmatter, broken references, missing GRADE assessments.
-
jmagly-ai-writing-guide Bundle Project AwarenessDetect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions
-
jmagly-ai-writing-guide Skill Kb HealthLint and health-check the knowledge base. Finds orphan pages, missing cross-references, stale claims, broken wiki-links, and regenerates the index.
-
jmagly-ai-writing-guide Skill Kb IngestIngest a source (URL, file, or freeform note) into the knowledge base. Creates a source summary and updates or creates relevant entity and concept pages.
-
jmagly-ai-writing-guide Skill Induct ResearchInduct research sources (issue, file, directory, or URI) into a research corpus — reads, annotates, and files structured induction tasks. Like address-issues but for research.
-
jmagly-ai-writing-guide Skill Profile MetricsCompute corpus-local influence/centrality metrics — per-paper CD-index + PageRank, and per-PROF-P h-index / mean-CD / mean-PageRank / betweenness / eigenvector + influence grade. Runs via `aiwg corpus profile-metrics`.
-
jmagly-ai-writing-guide Skill Research StatusShow research corpus health and statistics
-
jmagly-ai-writing-guide Skill Profile GenerateScaffold compact PROF-P entity profiles for unprofiled hub authors — ranks corpus REFs by citation in-degree, takes each top REF's primary author, skips institutional/group names and already-profiled people. Runs via `aiwg corpus profile-generate`.
-
jmagly-ai-writing-guide Skill Profile TemporalCompute an entity's publication trajectory — per-year paper counts, topic drift, hot-streak detection (≥3 consecutive A-grade years), and career phase. Runs via `aiwg corpus profile-temporal`.
-
jmagly-ai-writing-guide Skill Research AcquireDownload research papers and extract metadata
-
jmagly-ai-writing-guide Skill Research ArchivePackage research artifacts for long-term archival
-
jmagly-ai-writing-guide Skill Research QualityAssess source quality using GRADE methodology
-
jmagly-ai-writing-guide Skill Color TrendsResearch current color trends from Pantone, architecture, film, and design. Use when user asks about trending colors, popular palettes, or wants research-backed color inspiration.
-
jmagly-ai-writing-guide Skill Citation BackfillRebuild bidirectional citation edges in a research corpus. Scans outgoing citations, computes the inverse map, rewrites incoming tables. Fixes one-directional graphs.
-
jmagly-ai-writing-guide Skill Research DiscoverSearch for research papers across academic databases
-
sboghossian-mini-claude-for-legal Skill Pa Workflow Litigation Brief Cite CheckerUse when a litigator needs to verify every citation in a court brief before filing. Checks that cases exist, pin-cites are accurate, holdings are correctly stated, and subsequent treatment (overruling, distinguishing, limitation) has not undermined the cited proposition. Applies Bluebook and OSCOLA citation formats. Covers common-law courts (DIFC, ADGM, UK, US) and mixed civil-law jurisdictions (UAE, KSA, LB, EG) where citation practice differs materially.
-
jmagly-ai-writing-guide Skill Research DocumentGenerate summaries and literature notes from research papers
-
jmagly-ai-writing-guide Skill Summarize TranscriptAnalyze and summarize a transcript, meeting notes, or discussion thread into a clear actionable document
-
techwavedev Skill Scientific WritingCore skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD...
-
jmagly-ai-writing-guide Skill Research Gap DetectBuild the mutual citation graph, find connected components, identify isolated clusters, and optionally search for bridge candidates and file gap issues.
-
jmagly-ai-writing-guide Skill Research ProvenanceQuery provenance chains and artifact relationships
-
techwavedev Skill Citation ManagementManage citations systematically throughout the research and writing process.
-
jmagly-ai-writing-guide Skill Public Records PlanResearch, draft, and track a jurisdiction-specific public-records request without legal conclusions or automated submission.
Frequently asked questions
What are Research & Search agent skills?
Research agent skills teach AI agents to gather and synthesize information properly: literature reviews, competitive analysis, web research with citations, and structured summaries. Each SKILL.md encodes a method, not just a prompt, so results stay consistent across runs.
Which Research & Search skills are most installed?
Popular Research & Search skills on SkillMD right now include research-discover, induct-media, sidecar-lint. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Research & Search skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.