Coding & Dev Tools

intent-solutions-io Skill

This skill uses the database-deadlock-detector plugin to detect, analyze, and prevent database deadlocks. It monitors database lock contention, analyzes transaction patterns, and suggests resolution strategies. Use this skill when the user asks to "detect database deadlocks", "analyze deadlock causes", "monitor database locks", or any requests related to database deadlock prevention and resolution. This skill is particularly useful for production database systems experiencing recurring deadlock issues. The plugin's command `/deadlock` is triggered by these requests.

autohandai-community-skills Bundle

After solving a non-trivial problem, detect generalizable learnings and propose skill updates so future interactions benefit automatically. Always active — applies to every interaction.

autohandai-community-skills Bundle

Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.

autohandai-community-skills Bundle

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

autohandai-community-skills Bundle

Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when to prefer NemoClaw versus integrating OpenShell and OpenClaw directly. Use when users ask about the relationship between OpenClaw, OpenShell, and NemoClaw, or when to use NemoClaw versus OpenShell. Trigger keywords - nemoclaw ecosystem, openclaw openshell, nemoclaw vs openshell, sandboxed openclaw, how nemoclaw works, nemoclaw sandbox lifecycle blueprint, nemoclaw overview, openclaw always-on assistants, nvidia openshell, nvidia nemotron, nemoclaw release notes, nemoclaw changelog.

sboghossian-mini-claude-for-legal Skill

Use when a matter involves healthcare facility licensing, practitioner regulation, drug and device approvals, health insurance obligations, telemedicine, medical liability, or health-data privacy across MENA jurisdictions (Saudi Arabia, UAE, Lebanon, Egypt). Covers national regulatory bodies (SFDA, MOH KSA, DHA, DOH Abu Dhabi, MOHAP, MOPH Lebanon, EDA Egypt), mandatory health insurance frameworks, Vision 2030 privatization, and the overlap with PDPL for health data. Triggers on healthcare licensing MENA, medical device approval KSA/UAE, health insurance UAE, telemedicine regulation, or medical malpractice MENA.

sboghossian-mini-claude-for-legal Skill

Use when Claude must produce a formal legal memorandum for internal law firm distribution, senior counsel review, or partner-level sign-off. Applies to triage memos, full legal opinions, regulatory advice notes, and M&A deal memos across all jurisdictions. Triggers when the audience is a senior lawyer, when the output is a formal written deliverable, or when the request explicitly calls for a memo, opinion, or advice note.

sboghossian-mini-claude-for-legal Skill

Use when assessing a contract, data-processing agreement, DPIA, or organizational practice for compliance readiness against Saudi Arabia's Personal Data Protection Law (PDPL). Covers lawful-basis mapping, data subject rights obligations, cross-border transfer rules, DPO appointment thresholds, breach notification timing, ROPA requirements, and sensitive data handling — all with reference to the SDAIA regulatory framework effective September 2024.

sboghossian-mini-claude-for-legal Skill

Use when performing KYC, counterparty verification, or corporate due diligence on a Lebanese entity. Queries the Lebanon Commercial Register (Sijil al-Tijari) held at the Mohafaza commercial courts to retrieve company form, capital, partners, board composition, statutory auditor, and encumbrances. Essential before signing commercial contracts with Lebanese parties; important caveat on data freshness given court-system delays.

sboghossian-mini-claude-for-legal Skill

Use when asked to draft a construction contract for small to medium projects where the full FIDIC suite is disproportionate. Covers scope of works, bill of quantities, payment and milestone schedule, programme, extensions of time, liquidated damages for delay (with Sharia-compliant framing for KSA), performance bond, retention, variations, insurance (CAR, TPL, workers' comp), defects liability, and dispute resolution. Applicable across MENA and multi-jurisdictional construction projects.

sboghossian-mini-claude-for-legal Skill

Use when drafting a notice of arbitration or request for arbitration to commence institutional or ad-hoc arbitral proceedings. Covers the required content under LCIA, DIAC, ICC, SCCA, UNCITRAL, and DIFC-LCIA (now DIAC) rules, with tactical guidance on claim preservation, parallel court relief, time-bar verification, and filing checklists. Triggers on "notice of arbitration", "request for arbitration", "commence arbitration", or "initiate arbitral proceedings" requests.

sboghossian-mini-claude-for-legal Skill

Use when drafting a trademark application — preparing the applicant details, mark representation, Nice Classification specification, and priority claim for filing with a national registry or via the WIPO Madrid System. Covers specification-drafting discipline (precise vs too vague vs too broad), the GCC unified application, WIPO Madrid, EUIPO, UAE MOEC, KSA SAIP, and Lebanon IP office procedures. Flags the critical rule that overly vague or broad specifications slow examination and weaken enforceability.

sboghossian-mini-claude-for-legal Skill

Use when scoring AI legal output on formatting and structural quality — whether the output is organized appropriately for its type, uses correct heading hierarchy, presents tables and lists where they add value, and meets the formatting conventions expected in MENA legal practice. A 0–5 rubric focused on presentation quality independent of legal accuracy.

sboghossian-mini-claude-for-legal Skill

Use when the platform needs to monitor and surface Louis platform status events — incidents, degradations, scheduled maintenance, and recovery confirmations — to users in a non-intrusive but timely way. Integrates with the status page and incident management system to convert operational events into user-facing feed items, push alerts, and in-app banners calibrated to incident severity and user activity state.

intent-solutions-io Skill

This skill enables Claude to manage database schema changes through version-controlled migrations. It is activated when the user requests to create, apply, or rollback database migrations. The skill supports generating timestamped migration files with both up and down migrations for PostgreSQL, MySQL, SQLite, and MongoDB. It helps in tracking schema evolution and ensuring safe database modifications. Use this skill when the user mentions "database migration", "schema change", "add column", "rollback migration", or "create migration".

intent-solutions-io Skill

This skill enables Claude to design, implement, and manage table partitioning strategies for large databases. It is triggered when the user needs to optimize query performance, manage time-series data, or reduce maintenance windows for tables exceeding 100GB. Use this skill when asked to "create database partitions", "optimize database queries with partitioning", "manage large database tables", or when the user mentions "partitioning strategy", "data archival", or uses the command `/partition`. The skill helps automate partition maintenance and data lifecycle management. It focuses on database best practices and production-ready implementations.

intent-solutions-io Skill

This skill configures load balancers, including ALB, NLB, Nginx, and HAProxy. It generates production-ready configurations based on specified requirements and infrastructure. Use this skill when the user asks to "configure load balancer", "create load balancer config", "generate nginx config", "setup HAProxy", or mentions specific load balancer types like "ALB" or "NLB". It's ideal for DevOps tasks, infrastructure automation, and generating load balancer configurations for different environments.

intent-solutions-io Skill

This skill enables Claude to analyze and optimize database query performance. It activates when the user discusses query performance issues, provides an EXPLAIN plan, or asks for optimization recommendations. The skill leverages the query-performance-analyzer plugin to interpret EXPLAIN plans, identify performance bottlenecks (e.g., slow queries, missing indexes), and suggest specific optimization strategies. It is useful for improving database query execution speed and resource utilization.

intent-solutions-io Skill

This skill enables Claude to monitor database transactions for performance and lock issues using the database-transaction-monitor plugin. It is triggered when the user requests transaction monitoring, lock detection, or rollback rate analysis for databases. Use this skill when the user mentions "monitor database transactions," "detect long-running transactions," "identify lock contention," "track rollback rates," or asks about "transaction anomalies." The skill leverages the `/txn-monitor` command to provide real-time alerts and insights into database health.

intent-solutions-io Bundle

This skill enables Claude to analyze the sentiment of text data. It identifies the emotional tone expressed in text, classifying it as positive, negative, or neutral. Use this skill when a user requests sentiment analysis, opinion mining, or emotion detection on any text, such as customer reviews, social media posts, or survey responses. Trigger words include "sentiment analysis", "analyze sentiment", "opinion mining", "emotion detection", and "polarity".

autohandai-community-skills Skill

Universal principles for agentic development when collaborating with AI agents. Defines divide-and-conquer, context management, abstraction level selection, and an automation philosophy. Applicable to all AI coding tools.

autohandai-community-skills Bundle

Detect NTLM relay attacks by analyzing Windows Event 4624 logon type 3 with NTLMSSP authentication, identifying IP-to-hostname mismatches, Responder traffic signatures, SMB signing status, and suspicious authentication patterns across the domain.

autohandai-community-skills Bundle

Testing reference for Megatron Bridge — unit and functional test layout, tier semantics (L0/L1/L2/flaky), script conventions, running tests locally, adding/moving/disabling tests, and pytest conventions.

autohandai-community-skills Bundle

Describes the NemoClaw plugin and blueprint architecture and how they orchestrate the OpenClaw sandbox. Use when looking up architecture, plugin structure, or blueprint design. Trigger keywords - nemoclaw architecture, nemoclaw plugin blueprint structure, nemoclaw vs openshell, which cli, nemoclaw cli, openshell cli, sandbox commands, nemoclaw cli commands, nemoclaw command reference, nemoclaw network policy, sandbox egress control operator approval, nemoclaw troubleshooting, nemoclaw debug sandbox issues.

gptomics Bundle

Extracts, filters, annotates, and exports differential expression results from DESeq2 or edgeR with proper handling of padj=NA (independent filtering, Cook's outliers, all-zero), multiple-testing correction choice (BH vs Storey q-value vs IHW vs lfsr), TREAT vs post-hoc fold-change filtering, p-value histogram diagnostics, gene annotation via org.db/biomaRt/mygene, GSEA preranked input, ORA background construction, replication reality (Schurch 2016 small-n result), and SABV/sex-stratified reporting. Use when extracting and interpreting DE results, troubleshooting padj=NA, choosing FDR method, preparing ranked lists for pathway analysis, annotating gene IDs, or comparing DESeq2 vs edgeR outputs.

gptomics Bundle

Calculates statistical power for high-dimensional genomics experiments (bulk RNA-seq, scRNA-seq, ATAC-seq, ChIP-seq, methylation, proteomics) under negative-binomial count models using RNASeqPower, PROPER, and simulation via powsimR, distinguishing per-gene from marginal (transcriptome-wide) power, the role of mean expression and dispersion, and the sequencing-depth-versus-replicate tradeoff. Covers simulation as the honest default for overdispersed counts, FDR-aware average power versus single-test power, observed/post-hoc power as an anti-pattern, and the winner's-curse / Type-S / Type-M consequences of underpowering. Use when planning replicate number for a sequencing experiment, deciding whether to add depth or samples, choosing closed-form versus simulation power, estimating power from pilot dispersions, or justifying replication in a grant. For clinical-trial power see clinical-biostatistics/power-and-sample-size; for the inverse sample-size question see experimental-design/sample-size.

gptomics Bundle

Assembles genomes de novo from noisy long reads (Oxford Nanopore R9/R10/Dorado, PacBio CLR) with Flye (repeat graph), Canu (correct-trim-assemble OLC), NextDenovo, Shasta, Raven, wtdbg2, or miniasm, and reconciles bacterial assemblies into a consensus with Trycycler/Autocycler. Covers matching the input flag to the basecaller era (--nano-hq vs --nano-raw), why a raw long-read assembly is contiguous but low-QV and not finished until polished, haplotig false-duplication and purge_dups, coverage and read-N50 as non-substitutable inputs, and mid-read adapter de-chimerization. Use when assembling a bacterial or eukaryotic genome from ONT or PacBio noisy reads, choosing a long-read assembler, or diagnosing an over-collapsed or duplicated assembly. For PacBio HiFi use hifi-assembly instead.

gptomics Bundle

Generates, normalizes, and converts bedGraph signal tracks (4-column chrom/start/end/value, 0-based half-open) with bedtools genomecov, deepTools bamCoverage/bamCompare/bigwigCompare, bedtools unionbedg, and UCSC bedGraphToBigWig. Covers why a raw coverage bedGraph is not comparable across samples until normalized, the CPM/RPKM/BPM/RPGC normalization menu and the conserved-total assumption that makes them wrong under a global perturbation, the strict sorted-non-overlapping-chrom.sizes bedGraphToBigWig contract that silently corrupts a bigWig, effective-genome-size selection, and bin-size aliasing. Use when building or normalizing a coverage/signal track from a BAM, comparing tracks across samples or conditions, converting bedGraph to a browser-ready bigWig, or diagnosing a track that looks plausible but reports wrong heights.

gptomics Bundle

Computes and interprets sequencing read depth and coverage over a genome, windows, or target regions with mosdepth (windowed depth, cumulative distribution, --quantize callable BEDs), bedtools genomecov/coverage (bedGraph tracks, per-target stats), samtools depth/coverage (per-base depth, per-contig depth+breadth). Covers the breadth-vs-mean distinction, the cumulative-coverage curve, evenness (CV/Fano/fold-80/Gini), what each tool silently counts (duplicates, secondary/supplementary, MAPQ, read span vs fragment, mate-overlap), the samtools-depth 8000-cap version trap, and the bedtools coverage -a/-b orientation flip. Use when assessing sequencing adequacy, building coverage tracks, computing breadth at a depth threshold, defining callable regions, or QCing target-capture uniformity.

gptomics Bundle

Detects A/B chromatin compartments from balanced Hi-C contact matrices via eigenvector decomposition of the distance-normalized, Pearson-correlated cis matrix with cooltools (eigs_cis), then orients (phases) the compartment eigenvector against a GC or gene-density track so the active (A) sign is not arbitrary. Covers the eigenvector-is-a-choice problem (per-arm view_df to remove the centromere gradient; picking the eigenvector by max correlation with activity, not by eigenvalue), GC phasing with bioframe.frac_gc, resolution choice (100kb-1Mb), saddle plots and saddle_strength for compartmentalization strength, the cohesin-loss-strengthens-compartments result, subcompartments (SNIPER/Calder/dcHiC), and cross-condition compartment switching. Use when calling A/B compartments, computing E1/eigenvectors, phasing the eigenvector, building saddle plots, choosing a compartment resolution, quantifying compartment strength, or comparing compartmentalization across conditions.

gptomics Bundle

Turns untargeted LC-MS/MS features (m/z, RT, MS/MS) into confidence-stratified metabolite annotations using spectral-library matching (matchms), in-silico tools (SIRIUS/CSI:FingerID, MetFrag) and molecular networking, and assigns a defensible MSI/Schymanski confidence level to each. Use when naming detected features, scoring MS/MS against a reference library, running SIRIUS, or deciding what confidence level an evidence set actually supports. For upstream feature extraction see metabolomics/xcms-preprocessing and metabolomics/msdial-preprocessing; for downstream enrichment that must respect these levels see metabolomics/pathway-mapping; for lipid-specific structural annotation see metabolomics/lipidomics.

gptomics Bundle

Classifies shotgun metagenomic reads to taxa with Kraken2's minimizer/LCA matching against a chosen reference database, then hands off to Bracken for abundance re-estimation. Covers why the database (not the algorithm) decides what can be detected, the --confidence and --minimum-hit-groups precision levers, unique-minimizer false-positive control, host-read removal, and why raw Kraken2 read counts are not abundances. Use when profiling who-is-there from shotgun reads, choosing a Kraken2 database, setting a confidence threshold, controlling false positives, or feeding reports to Bracken. For marker-gene profiling see metaphlan-profiling; for abundance mechanics see abundance-estimation; for assembly/MAG recovery see genome-assembly/metagenome-assembly.

gptomics Bundle

Tests a gene list or ranked gene vector for over-representation or coordinated shifts in Reactome's curated, peer-reviewed, reaction-level pathways using ReactomePA's enrichPathway (ORA) and gsePathway (GSEA), reading the local reactome.db so a run is reproducible given the Bioconductor release. Covers why Reactome's atomic unit is the REACTION and pathways are nested containers so a parent and child enrich on the same genes and double-count one signal, why only human is curated and every other species is orthology-inferred, why enrichPathway has NO keyType argument and returns nothing unless genes are ENTREZ (bitr first), and why viewPathway draws a LOCAL reaction network from a pathway NAME. Use when reaction-level granularity, peer-reviewed curation, or an offline-reproducible database is wanted; for comparative multi-sample or multi-omics analysis use ReactomeGSA. The DE list comes from differential-expression; plots from enrichment-visualization.

sboghossian-mini-claude-for-legal Skill

Use when discussing why AI productivity gains in legal work have not reduced billable hours or client costs, the tension between AI efficiency and hourly billing models, pricing reform pressure, and how the productivity paradox affects law firm economics and legal AI ROI arguments. Relevant for pitches, competitive analysis, legal ops conversations, and anyone questioning whether AI actually saves clients money.

sboghossian-mini-claude-for-legal Skill

Use when formatting a legal AI output as a formal client letter — covering the structure (letterhead, greeting, analysis, recommendation, sign-off), the voice rules (professional peers, calibrated confidence, plain English), and the mandatory cautions (privilege markings, reservation of rights, scope references, avoiding outcome promises). Applies to law firm client communications in all jurisdictions covered by the platform.

sboghossian-mini-claude-for-legal Skill

Use when the legal AI product team needs a curated list of MENA legal, business, and legal-tech publications for press outreach, media placements, and backlink campaigns. Covers UAE, KSA, Lebanon, Egypt, and pan-GCC outlets relevant to a legal AI product focused on MENA practice. Triggers when building or refreshing the MENA media outreach list.