Docs & Writing

gptomics Bundle

Builds reproducible Quarto reports, presentations, and websites across R, Python, and Julia, with correct engine selection, cache-vs-freeze semantics, native cross-references, parameters, and environment pinning. Use when creating a Quarto report of an analysis, setting up freeze for CI, or debugging cross-references, caching, or working-directory issues.

sboghossian-mini-claude-for-legal Skill

Use when a user uploads a scanned PDF or image containing Arabic-language text that is not machine-readable. Invoked automatically when Arabic content is detected in a non-selectable scan, or explicitly when the user requests OCR on an Arabic document. Outputs plain text with confidence scores, RTL-ordered, ready for downstream analysis. Critical for processing Arabic legal documents, court judgments, official gazette pages, and corporate filings in MENA jurisdictions.

sboghossian-mini-claude-for-legal Skill

Use when a user uploads a scanned English-language PDF or contract image where the text layer is absent or empty. Converts image-based pages to searchable text, preserving clause numbering, section hierarchy, and page anchors for citation. Also detects signature blocks and handwritten initials. Triggers automatically when PDF text extraction returns empty, or when the user uploads a photo of a contract from WhatsApp or email.

sboghossian-mini-claude-for-legal Skill

Use when drafting a Performance Improvement Plan (PIP) letter — formal documentation of identified performance deficiencies with specific improvement objectives, success metrics, timeline, support commitments, and consequence disclosure. Covers best-practice standards (SMART objectives, specificity over generality, documentation of support), anti-patterns (pretextual PIPs, retaliation risk), and jurisdictional considerations for UAE, KSA, Lebanon, and DIFC. Triggers on "pip", "performance improvement plan", "performance warning letter", or "underperformance documentation" requests.

oimiragieo Bundle

Convert files to Markdown using Microsoft's MarkItDown library

sboghossian-mini-claude-for-legal Skill

Use when the legal-AI product team needs to read, create, or update issues in the Linear project-management system — including automated bug report creation from chat, feature-request capture, sprint status queries, and pull-request linking. An internal engineering and ops connector; not a legal-content tool. Triggers on requests to create a bug or feature request, check sprint status, or link a chat session outcome to a Linear issue.

oimiragieo Bundle

Atlassian ecosystem integration covering Jira project management, Confluence documentation, Bitbucket source control, and cross-product automation workflows

sboghossian-mini-claude-for-legal Skill

Use when a user or IT administrator needs to install, configure, or troubleshoot the Louis Microsoft Word Add-in (Office Add-in, cross-platform). The plugin surfaces Louis's four key in-document capabilities — clause insertion, redlining/track changes, risk scanning, and citation insertion — without leaving the Word interface. Applicable across all jurisdictions and Office 365 / Microsoft 365 deployments.

sboghossian-mini-claude-for-legal Skill

Use when drafting a vesting schedule for founder shares, employee options (ISO/NSO), or RSUs. Covers the standard 4-year monthly with 1-year cliff structure, alternative schedules (quarterly, annual, performance-based, hybrid), acceleration triggers (single vs double trigger), good-leaver/bad-leaver treatment, and the documentation chain (option plan, grant letter, exercise notice). Includes MENA-specific tax considerations (UAE 9% corporate tax, KSA, no income tax), US 83(b) election timing, and UK EMI/non-EMI treatment.

gptomics Bundle

Designs and validates quantitative targeted metabolomics assays (MRM/SRM on triple-quadrupole, PRM on high-resolution instruments) to report absolute concentrations. Covers the internal-standard strategy (external cal -> global IS -> standard addition -> stable-isotope-labeled IS), weighted calibration judged by back-calculated %RE not R-squared, ion-ratio quantifier/qualifier confirmation, matrix-effect/recovery characterization, and ICH M10 method validation. Use when quantifying a closed panel of known metabolites with units, building or validating an LC-MS/MS assay, choosing an IS or calibration weighting, or judging whether a reported concentration is trustworthy. For untargeted feature detection see metabolomics/xcms-preprocessing; for group statistics see metabolomics/statistical-analysis; for flux/MID/tracing see metabolomics/isotope-tracing.

oimiragieo Bundle

API development expert including REST design, OpenAPI, and documentation

sboghossian-mini-claude-for-legal Skill

Use when a user in a legal AI chat session signals that something is broken, behaving unexpectedly, or producing an error. Guides the assistant through detecting bug signals in conversation, gathering structured context from the user, automatically collecting session metadata, and submitting a properly classified Linear issue — all while enforcing PII redaction and tenant isolation.

sboghossian-mini-claude-for-legal Skill

Use when an organization needs a structured GDPR readiness review across the 10 core compliance areas — lawful basis documentation, privacy notice, consent mechanism, Article 30 records of processing, DPIAs, DPO appointment, DSR handling, 72-hour breach notification, international transfer mechanisms, and vendor/processor management. Produces a traffic-light maturity score per area with findings and prioritized recommendations. Relevant for any organization that processes EU personal data, including MENA companies with EU operations or EU customer data flows.

sboghossian-mini-claude-for-legal Skill

Use when searching ADGM Courts case law or checking case status for matters before the Abu Dhabi Global Market Courts — an English common-law court system in Abu Dhabi's financial free zone. Covers Court of First Instance, Court of Appeal, Small Claims Division, Employment Division, and Arbitration Division. Returns case numbers, party names, judgment status, and PDF links. Pair with DIFC courts search when forum-shopping analysis is needed.

sboghossian-mini-claude-for-legal Skill

Use when checking whether a contract PDF has been fully executed — i.e., all signature blocks are signed — or to identify where signature placeholders remain blank. Detects signature lines, executed wet-ink signatures, initials on pages, and official stamps/seals. Critical for execution verification workflows, document closing checklists, and flagging counterparty documents where execution status is unclear.

oimiragieo Bundle

Master on-call shift handoffs with context transfer, escalation procedures, and documentation. Use when transitioning on-call responsibilities, documenting shift summaries, or improving on-call processes.

gptomics Bundle

Detects contamination in sequencing reads - cross-species (FastQ Screen, Kraken2), vector/PhiX/adapter, rRNA, and same-species cross-sample/index-hopping and sample swaps (SNP fingerprints via verifyBamID2/NGSCheckMate/somalier). Use when suspecting cross-contamination, PDX host reads, microbial carry-over, or sample swaps, and to decide whether to report, filter, or align to a combined reference. For deep taxonomic profiling use metagenomics/kraken-classification.

intent-solutions-io Skill

Analyze and explain TimeGPT forecast results in plain English. Generates executive summaries with driver analysis. Use when stakeholders need forecast explanations, board presentations, or compliance documentation. Trigger with "explain forecast", "why is the forecast", "forecast narrative".

intent-solutions-io Bundle

Orchestrate 6-phase changelog generation workflow with AI synthesis, multi-source data fetching (GitHub/Slack/Git), quality validation, and automated PR creation. Use when automating release notes, weekly changelogs, or documentation updates. Trigger with "generate changelog", "weekly changelog", or "automate release notes".

sboghossian-mini-claude-for-legal Skill

Use when a client-side crash (browser console error, mobile app crash) or backend failure (HTTP 500, unhandled exception) occurs during a legal AI session. Formats raw crash data — stack traces, source-map decoded frames, device/OS info, last user actions — into a structured incident ticket with severity classification and owner routing to Linear and Slack.

gptomics Bundle

Predicts community functional POTENTIAL from 16S/ITS amplicon ASVs with PICRUSt2 (or q2-picrust2) by phylogenetic interpolation of reference-genome gene content - EPA-ng placement, gappa, castor hidden-state prediction of KO/EC/Pfam copy number, 16S copy-number normalization, and MinPath MetaCyc/KEGG pathways - gated by the NSTI quality index. Covers why predicted function is taxonomy re-encoded (never measured gene content and never activity), the mandatory NSTI report (--max_nsti 2 silently drops novel ASVs), why accuracy IS reference coverage (gut Spearman ~0.8, soil/marine collapse), the circularity trap, and Tax4Fun2/FAPROTAX/BugBase alternatives. Use when inferring KO/EC/MetaCyc potential from an ASV table, gating on NSTI, or choosing a prediction method. For MEASURED shotgun function see metagenomics/functional-profiling; for enrichment of KO lists see pathway-analysis/go-enrichment; for DA of predicted tables see differential-abundance.

gptomics Bundle

Checks whether a PCR primer PAIR amplifies only the intended target genome-wide, using pair-aware in-silico PCR (MFEprimer-3.0, UCSC isPcr, NCBI Primer-BLAST) plus a primer3-py 3'-end-stability prefilter, against the correct database. Covers why plain BLAST is the wrong tool (it scores per-primer similarity, blind to 3'-terminal anchoring and to whether the two primers form a convergent amplicon in range), why a single 3'-terminal mismatch suppresses amplification while internal mismatches are tolerated, why intron-spanning RT-qPCR is defeated by processed pseudogenes that force a GENOME search not transcriptome-only, how to read a Primer-BLAST report (empty unintended-products means none passed its filter, not none exist), and that in-silico checking reduces but never replaces empirical validation. Use when confirming specificity, screening off-target amplicons, avoiding paralog/pseudogene hits, or checking SNPs under the 3' end. Design is primer-basics; dimers primer-validation; alignment read-alignment.

sboghossian-mini-claude-for-legal Skill

Use when a developer asks how to integrate with the platform API, authenticate requests, call specific endpoints, handle webhooks, or manage rate limits. This is a platform documentation skill covering the REST and streaming API, SDK installation, authentication, versioning, idempotency, and webhook event structure for the developer hub.

sboghossian-mini-claude-for-legal Skill

Use when a user asks how to install, set up, or use the mobile app — iOS or Android. This is a platform documentation skill covering the mobile app installation flow, sign-in, first task, push notification configuration, biometric unlock, WhatsApp document sharing, and the differences between mobile and web feature availability.

sboghossian-mini-claude-for-legal Skill

Use when generating or formatting output as a DOCX file for a legal document. Defines the heading hierarchy (Heading 1 through 3 plus Body Text variants), font and spacing standards (Times New Roman 12pt, 1.5 line spacing), numbering conventions, margin settings, signature block format, and schedule/annex structure — with rules for what to avoid (manual numbering, inconsistent fonts, hand-drawn signature lines).

intent-solutions-io Skill

This skill analyzes code coverage metrics to identify untested code and generate comprehensive coverage reports. It is triggered when the user requests analysis of code coverage, identification of coverage gaps, or generation of coverage reports. The skill is best used to improve code quality by ensuring adequate test coverage and identifying areas for improvement. Use trigger terms like "analyze coverage", "code coverage report", "untested code", or the shortcut "cov".

gptomics Bundle

Turns shotgun classifier output into a defensible abundance table with Bracken Bayesian re-estimation, then compositional treatment (CLR, zero handling), library-size normalization, reference-frame differential abundance, and optional absolute quantification. Covers why a relative-abundance change is not a change, why Bracken read fractions and MetaPhlAn percentages are different physical quantities, the silent -r read-length bias, the genome-size confound no library-size method fixes, and the rarefaction debate. Use when estimating species abundance from a Kraken2 report, normalizing a community count table, choosing a compositional transform, or converting relative to absolute load. For classification see kraken-classification; for diversity/ordination/DA mechanics see metagenome-visualization.

sboghossian-mini-claude-for-legal Skill

Use when searching for trademarks registered under the Madrid System (international registrations) or in the national databases that feed into WIPO's Global Brand Database. Covers word marks, device marks, sound marks across Nice classes 1–45 with designation-territory filtering. Always the first step in trademark clearance; must be paired with national MENA register searches for a complete clearance opinion, as the WIPO database does not capture purely domestic filings.

sboghossian-mini-claude-for-legal Skill

Use when Claude must format a legal document — contract, NDA, policy, opinion, or procedural submission — in clean Markdown that renders correctly and survives conversion to DOCX or PDF. Applies to all jurisdictions and document types. Triggers on any drafting request where the output is a standalone legal document rather than a conversational answer.

sboghossian-mini-claude-for-legal Skill

Use when a law firm needs a ready-to-adopt AI use policy governing how associates, paralegals, and staff may use Louis or other AI tools. Covers permitted uses, prohibited uses, mandatory safeguards (citation verification, matter-file documentation, bar-rule compliance), and links to relevant professional responsibility rules. Adaptable for MENA and common-law jurisdictions.

sboghossian-mini-claude-for-legal Skill

Use when given a specific Louis feature name and asked to produce a clear one-paragraph explanation plus a concrete use case and (optionally) a screenshot reference. This is a generic explainer generator — not a product overview — and fires when users or in-product help systems need on-demand feature documentation for a named capability. Distinct from the AI feature explainer (product overview) and the use-case explainer (user-goal-first).

sboghossian-mini-claude-for-legal Skill

Use when evaluating whether a Louis AI response matches the expected persona voice, tone register, and output style for a given user segment, practice area, or conversational context. Runs as part of the automated CI eval suite to measure tone-fit quality, jurisdiction appropriateness, and persona trajectory consistency. Surfaces failures as structured scores in the weekly AI quality trend report.

intent-solutions-io Skill

This skill enables cross-browser compatibility testing for web applications using BrowserStack, Selenium Grid, or Playwright. It tests across Chrome, Firefox, Safari, and Edge, identifying browser-specific bugs and ensuring consistent functionality. It is used when a user requests to "test browser compatibility", "run cross-browser tests", or uses the `/browser-test` or `/bt` command to assess web application behavior across different browsers and devices. The skill generates a report detailing compatibility issues and screenshots for visual verification.

gptomics Bundle

Annotates VCF variants with functional consequences, population frequencies, and pathogenicity scores using bcftools annotate/csq, Ensembl VEP, SnpEff, and ANNOVAR. Use when deciding which annotation engine and version to pin, which transcript set to report on (RefSeq vs Ensembl vs MANE Select/Plus Clinical, and why VEP --pick is dangerous clinically), how to reconcile HGVS 3'-shifting with VCF left-alignment, which consequence plus NMD status governs PVS1 eligibility, which single calibrated predictor to use for PP3/BP4 (REVEL, AlphaMissense, CADD, SpliceAI deltas), or how to read gnomAD v2/v3/v4 grpmax filtering allele frequency instead of one global AF cutoff. Not for ACMG combining rules or final classification (see variant-calling/clinical-interpretation).

sboghossian-mini-claude-for-legal Skill

Use when a user needs guidance on how to use the full legal AI workspace — the chat interface, document drafting, matter management, citations, risk analysis, and automated workflow features. This is the primary end-user guide documentation skill, covering all major workspace capabilities with topical sections designed for both new and experienced users.

sboghossian-mini-claude-for-legal Skill

Use when formatting a legal document, contract, or analysis that must appear in both Arabic and English — either as a two-column layout (for DOCX/PDF export) or as stacked bilingual sections (for chat/markdown). Covers RTL/LTR handling, Arabic punctuation rules, currency and numeral conventions, and the required controlling-language statement. Essential for MENA-jurisdiction drafting in the UAE, KSA, Lebanon, and Egypt.