Coding & Dev Tools

sboghossian-mini-claude-for-legal Skill

Use when Claude must structure legal analysis as a formal Issue/Rule/Application/Conclusion memo, opinion, or briefing note. Applies across all jurisdictions including MENA (UAE, KSA, Lebanon, Egypt), DIFC/ADGM, UK, US, and EU. Triggers on requests for legal analysis, memo of law, legal opinion, advice note, or any analytical output requiring reasoned legal argument.

sboghossian-mini-claude-for-legal Skill

Use when the legal AI product team needs to triage and respond to inbound outreach — journalist inquiries, partnership requests, user support escalations, investor notes, and press coverage alerts. Scans and categorises inbox items, drafts responses at appropriate priority, and surfaces high-value opportunities that require immediate action. Triggers when asked to process or prioritise inbound communications for a legal AI product.

sboghossian-mini-claude-for-legal Skill

Use when the user is an experienced lawyer (partner, senior associate, counsel) who needs terse, BLUF-structured legal analysis with citations and no pedagogical scaffolding. This P0 persona sets the default output style for professional legal users — bottom line first, 1-line conclusion, 3-5 line analysis, citations, open issues. Applies across all jurisdictions and practice areas.

sboghossian-mini-claude-for-legal Skill

Use when a site visitor navigates to or searches for the platform's marketplace — a planned phase-2 feature for browsing third-party legal templates, lawyer services, or skill add-ons. Routes to the marketplace landing page or a filtered category view. Currently a placeholder for a phase-2 surface; the skill defines the intended routing architecture for when the marketplace launches.

roadsidedev Skill

Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments

gptomics Bundle

Infers directed, time-delayed gene regulatory edges from BULK time-series expression using Granger causality (statsmodels VAR F-test), dynGENIE3 (tree ensembles regressing ODE-derived derivatives; Random Forests by default, Extra-Trees optional), and dynamic Bayesian networks (bnlearn). Use when the output is a RANKED HYPOTHESIS list for perturbation validation, not validated causal edges; deciding Granger vs dynGENIE3 vs DBN by timepoint count and linearity; sizing maxlag against the n>3*maxlag+1 degrees-of-freedom floor; handling stationarity/differencing before Granger; restricting regulators to known TFs; and comparing network rewiring across conditions at matched edge density. Not for single-cell pseudotime GRNs (see gene-regulatory-networks/scenic-regulons) or static co-expression (see gene-regulatory-networks/coexpression-networks).

gptomics Bundle

Performs retrosynthetic planning using AiZynthFinder (template-based MCTS), maintained or version-pinned template-free models, ASKCOS, and emerging RetroSynFormer with explicit handling of route scoring, configurable MCTS rewards, building-block availability, and forward-prediction checks. Use when assessing synthetic feasibility of generated or selected molecules, planning multi-step syntheses, building synthesis-aware design pipelines, or screening libraries for retro-route feasibility.

gptomics Bundle

Normalizes ChIP-seq data using exogenous spike-in (ChIP-Rx with Drosophila chromatin per Orlando 2014 / Egan 2016; E. coli carryover for CUT&RUN/CUT&Tag). Distinguishes RRPM from Rx-Input scaling, integrates with DiffBind / DESeq2 / edgeR / csaw via sizeFactors and DiffBind library-size vectors, applies the Patel et al 2024 *Nat Biotechnol* failure-mode framework, and validates that normalization is applied at the read level (not peak counts). Use when global signal shifts are expected (HDACi, BETi, EZH2i, dosage, target knockdown), when ChIPseqSpikeInFree detects post-hoc shifts, or when validating internal-control regions before publication.

gptomics Bundle

Identify direct miRNA-target interactions from AGO HITS-CLIP, AGO-CLEAR-CLIP (chimeric reads), HEAP (Halo-Ago2 mouse), chimeric eCLIP / miR-eCLIP (deep miRNA-target profiling), or CLASH using chimeric-read processing pipelines, seed-pairing analysis, and 3' auxiliary pairing rules. Use when distinguishing direct miRNA targets from indirect, integrating CLIP-derived target maps with TargetScan / miRDB / DIANA predictions, applying canonical 7mer-8mer seed matching with 3' UTR context, or recovering miRNA-mRNA chimeras at scale.

gptomics Bundle

Detect distant homologs using profile and structure-aware methods that go beyond standard BLAST. Use when sequence identity falls into the twilight zone (<35% pairwise), when BLAST fails to find homologs that should exist, when working at metagenomic scale (DIAMOND, MMseqs2), or when structure beats sequence (Foldseek). Covers PSI-BLAST (iterative PSSM), jackhmmer (iterative HMM), HHblits/HHsearch (profile-profile), DIAMOND, MMseqs2, and Foldseek (3Di structural alphabet, van Kempen 2024).

gptomics Bundle

Normalizes and transforms RNA-seq count matrices for DE, visualization, clustering, and ML. Covers between-sample (TMM, TMMwsp, RLE/median-of-ratios, upper quartile), within-sample (TPM, FPKM/RPKM), variance-stabilizing (VST, rlog, log-CPM), GC-content correction (cqn, EDASeq), and single-cell (scran deconvolution, scanpy normalize_total). Encodes the composition-bias rationale, the "most genes not DE" assumption and its catastrophic failure modes (MYC amplification, apoptosis, viral host shutoff, prokaryotic stress), the "lengthScaledTPM is not TPM" naming trap, the "TPM is not for DE" rule, the blind=TRUE vs FALSE decision, ERCC spike-in normalization (SBN), and the single-cell zero-inflation breakdown of TMM/RLE. Use when choosing or applying normalization, debugging shifted-MA-plot diagnostics, handling zero-heavy single-cell data, or correcting GC bias.

oimiragieo Skill

Builds mission engine modules, orchestration wiring, plugin system, headless execution, and code review infrastructure

oimiragieo Bundle

Validate planned changes against local framework rules and policy guardrails before implementation or creation.

oimiragieo Bundle

Feature flag lifecycle management -- safe feature toggling, gradual rollouts, A/B testing patterns, flag cleanup strategies, and technical debt prevention. Covers LaunchDarkly, Unleash, OpenFeature, and custom implementations.

oimiragieo Bundle

State management expert including MobX, Redux, Zustand, and reactive patterns

oimiragieo Bundle

Master binary analysis patterns including disassembly, decompilation, control flow analysis, and code pattern recognition. Use when analyzing executables, understanding compiled code, or performing static analysis on binaries.

oimiragieo Bundle

Enforces the use of Zod for form validation throughout the project.

sboghossian-mini-claude-for-legal Skill

Use when converting between currencies for damages calculations, contract valuations, or cross-border legal matters. Covers spot and historical rates for USD, EUR, GBP, AED, SAR, LBP, KWD, QAR, BHD, OMR, EGP, and major global currencies. Includes a critical Lebanese Pound caveat on the multi-rate environment (official BDL vs Sayrafa vs parallel) and guidance on pinning a specific FX rate for litigation use.

sboghossian-mini-claude-for-legal Skill

Use when searching DIFC Courts case law or checking case status for matters before the Dubai International Financial Centre Courts — an English common-law court in Dubai's financial free zone. Covers Court of First Instance, Court of Appeal, Small Claims Tribunal, and Wills & Probate Registry. Returns party names, case numbers, judge, judgment PDFs. Note the DIFC-LCIA arbitration centre was replaced by DIAC in 2021. Pair with ADGM courts search for forum-shopping analysis.

sboghossian-mini-claude-for-legal Skill

Use when a user wants to import, reference, or compare contract templates from Genie AI — an open-source legal template platform. Triggers when a user mentions "Genie AI", "Genie template", or asks to pull in an external template for drafting reference or comparison. Works across all jurisdictions and practice areas where Genie AI has coverage (primarily English-language common-law templates).

sboghossian-mini-claude-for-legal Skill

Use when drafting a child custody and parenting arrangement agreement following divorce or separation. Jurisdiction-sensitive across MENA (hadanah/wilayah split in KSA, UAE, Egypt), Lebanon's 18 confessional courts, and civil-law jurisdictions. Covers physical custody, visitation, decision-making authority, child support, travel consent, and relocation. Always paired with court-ratification advice — most MENA jurisdictions require ratification to give the agreement enforcement weight.

sboghossian-mini-claude-for-legal Skill

Use when drafting an employee handbook (staff manual) that codifies workplace policies and procedures. Covers the full 11-section structure, MENA-specific requirements (bilingual Arabic/English, Saudization/Emiratization sections, end-of-service benefits), DIFC/ADGM free-zone override of federal rules, the critical non-binding disclaimer to prevent the handbook from becoming an employment contract, and common anti-patterns. Applicable across LB, KSA, UAE, DIFC, ADGM, EU, and UK jurisdictions.

sboghossian-mini-claude-for-legal Skill

Use when drafting a law firm engagement letter (retainer agreement) establishing the terms of legal representation. Covers scope, fee structures (hourly/fixed/contingency/hybrid), trust account requirements, conflict-of-interest acknowledgment, file retention, and termination rights. Includes bar-rule compliance notes for LB, KSA, UAE/DIFC/ADGM, and US (NY, CA) jurisdictions, plus anti-patterns including vague scope and missing estimates.

sboghossian-mini-claude-for-legal Skill

Use when drafting a witness statement — a first-person factual narrative used as evidence in court, arbitration, or regulatory proceedings. Covers the standard English-law common-law format (DIFC, ADGM, UK) with paragraph-by-paragraph chronological narrative and a statement of truth, contrasted with the civil-law approach (UAE onshore, KSA, Lebanon, France) where oral testimony at hearings predominates. Addresses international arbitration (IBA Rules) hybrid practice. Flags the cardinal rule that a witness statement must be in the witness's own voice, not lawyer-authored advocacy.

sboghossian-mini-claude-for-legal Skill

Use when a law firm partner or business development team needs to construct a formal fee proposal for a prospective or existing client. Covers all major fee structures (hourly, fixed, contingency, capped, collared, milestone, subscription, hybrid), produces a complete quote with scope, assumptions, tax treatment, and validity, and flags MENA-specific restrictions on contingency and retainer arrangements. Output flows directly into the engagement letter.

roadsidedev Skill

Manage Linear issues, projects, and teams

intent-solutions-io Bundle

Detect arbitrage opportunities between Polymarket and Kalshi using forecast analysis. Use when finding price discrepancies across platforms. Trigger with 'find arbitrage' or 'compare market prices'.

intent-solutions-io Bundle

Analyze and forecast Polymarket contracts using TimeGPT with confidence intervals. Use when predicting contract prices. Trigger with 'Polymarket analysis' or 'forecast prediction market'.

intent-solutions-io Bundle

Analyze causal impact of events on time series forecasts using TimeGPT. Use when quantifying promotion or disaster effects. Trigger with 'event impact analysis' or 'causal analysis'.

oimiragieo Bundle

Gate for HIGH/EPIC tasks that validates plan completeness and architecture compliance before implementation begins

oimiragieo Bundle

Helper skill that deduplicates token-saver memory records before persistence.

oimiragieo Bundle

Detect when agents are stuck in repetitive action loops using a rolling 20-action window with escalating nudges — replan after 3 similar actions, explore after 5, force-done after 8.

sboghossian-mini-claude-for-legal Skill

Use when scoring AI legal output on whether it addresses the question fully. A 0–5 rubric that checks for all material aspects, relevant edge cases, and structural completeness appropriate to the output type — IRAC for analysis, full document structure for drafts, all relevant axes for comparisons.

sboghossian-mini-claude-for-legal Skill

Use when the platform needs to surface official Louis / HAQQ Legal AI press releases, product announcements, partnership news, and institutional communications as a curated feed for users. This feed maintains brand trust by giving users a single authoritative source for platform-level news, as opposed to third-party coverage or rumor. Relevant to in-house teams, enterprise accounts, and users who need to cite the platform's institutional standing.

sboghossian-mini-claude-for-legal Skill

Use when Louis determines that a user's legal matter exceeds AI-only assistance and requires human professional intervention — a lawyer, specialist advisor, emergency service, or regulated professional. Covers the full set of handoff triggers (criminal risk, emergency, high penalty exposure, multi-jurisdictional litigation, user distress, explicit request, low confidence), the handoff process (acknowledge, identify domain, provide resource, schedule), and the constraint that Louis must never pretend to be a human, lawyer, or therapist. P0 safety-critical behavior.

sboghossian-mini-claude-for-legal Skill

Use when advising on construction contracts using FIDIC forms in MENA, including contract book selection (Red/Yellow/Silver/Gold), MENA-specific clause adaptations (currency, force majeure, time-bar enforceability, liquidated damages, performance bonds), Dispute Adjudication Boards (DABs), and arbitration of FIDIC disputes. Covers Saudi Arabia (NEOM/Vision 2030 projects), UAE, Lebanon, and Egypt with jurisdiction-specific civil-law traps.