DevOps & Infra

ariffazil Skill

Operational binding for the MiniMax voice cloning pipeline (mimo-v2.5-tts-voiceclone + speech-2.8-hd). Four-phase protocol: Ingestion → Calibration → Execution → Deployment. F13 SOVEREIGN-gated identity creation. i-ARIF voice profile lives here.

gptomics Bundle

End-to-end Hi-C analysis workflow from FASTQ to compartments, TADs, and loops, with the decision of WHICH features the sequencing depth can support. Covers pairtools read-pair processing and library QC, cooler matrices, ICE balancing and distance-decay expected, A/B compartments, TAD boundaries, loop calling, and the routing of HiChIP/PLAC-seq/Capture Hi-C to protein-directed loop callers. Use when processing Hi-C data end to end, deciding a resolution for a given depth, or choosing between bulk-Hi-C and protein-directed loop calling.

gptomics Bundle

Orchestrates an end-to-end immune-repertoire pipeline from FASTQ to clonotypes, diversity, overlap, somatic hypermutation and lineages, routing on two forks. Use when deciding bulk vs single-cell (bulk amplicon/RNA-seq -> MiXCR analyze preset -> VDJtools/immunarch depth-normalized diversity and overlap -> figures; 10x paired VDJ -> MiXCR 10x preset or Cell Ranger -> scirpy gene-expression integration, chain QC, clonotype clusters); and TCR vs BCR (TCR -> exact CDR3-nt+V/J clonotypes, VDJtools diversity is fine; BCR -> somatic hypermutation makes exact clonotypes wrong -> Immcantation distToNearest/findThreshold clonal clustering, germline reconstruction, SHM, Dowser lineages); selecting the MiXCR 4.x preset by chemistry and activating its license; downsampling to equal depth before comparing diversity or overlap; and optionally annotating antigen specificity.

oimiragieo Bundle

Automated health checks for framework artifacts modified during a pipeline. Validates hook syntax, security patterns (SE-01/SE-02), skill wiring, agent consistency, and routing correctness. Invoked as the final pipeline step when framework artifacts were created, modified, or deleted.

oimiragieo Bundle

Terraform infrastructure operations with safety controls

ariffazil Bundle

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), feature flags (Flagship), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

oimiragieo Bundle

Container orchestration expert including Docker, Kubernetes, Helm, and service mesh

ariffazil Bundle

Runbook for VPS Docker operations — pinned versions, restart discipline, health checks, compose governance. Lower machine entropy.

ariffazil Bundle

Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

ariffazil Bundle

Concrete Docker Compose and container commands for the af-forge VPS stack

gptomics Bundle

End-to-end CLIP-seq pipeline from FASTQ to ENCODE-compliant binding sites, single-nucleotide crosslink maps, annotation, motifs, and (optionally) differential binding. Use when running the full Yeo lab eCLIP / iCLIP / iCLIP2 / iCLIP3 / irCLIP / PAR-CLIP analysis with SMInput control, protocol-specific UMI extraction, ENCODE STAR parameters, CLIPper or Skipper peak calling with stringent log2 FC and -log10 p thresholds, IDR rescue and self-consistency QC, and downstream motif registration with mCross or PEKA.

gptomics Bundle

End-to-end eDNA metabarcoding from raw amplicons to community ecology. Covers QC, primer removal (mandatory before DADA2 filterAndTrim), denoising with OBITools3 v3 (obi stats plural; DMS-based) or DADA2 ASVs (Callahan 2017), decontam combined method as screening-not-classifier (Davis 2018), tag-jumping (Schnell 2015) with a platform-dependent baseline (NovaSeq patterned flow cells ~10x MiSeq), Hill-number effective species counts with coverage-based rarefaction (Jost 2006; Chao & Jost 2012; doubling rule), beta-diversity decomposition with MANDATORY PERMANOVA + PERMDISP pair (Anderson & Walsh 2013), constrained ordination, and the read-counts-not-abundance critique (Lamb 2019). Use when processing eDNA samples for biodiversity assessment, deciding ASV vs OTU, configuring OBITools3 v3, interpreting decontam screening, or reporting community comparisons with the dispersion confound check.

ariffazil Skill

VPS health and diagnostics runbook. Load when checking system resources, Docker state, disk pressure, service ports, logs, SSL/Caddy, databases, or memory pressure on af-forge.

ariffazil Bundle

Thermodynamic reasoning lens for container fleet health, resource pressure, and safe/dangerous intervention boundaries.

oimiragieo Bundle

Automated security scanning pipeline covering SAST (Semgrep), SCA (OWASP dependency-check), SBOM generation (Syft), vulnerability scanning (Grype), and secrets detection (detect-secrets). Invoked by security-architect for pre-commit gates, CI integration, and finding triage.

gptomics Bundle

Orchestrates an end-to-end MeRIP-seq / m6A-seq analysis from raw FASTQ to differential m6A peak calls and metagene plots, chaining fastp adapter trimming, STAR splice-aware alignment (NO deduplication for non-UMI MeRIP), deepTools replicate-concordance + IP-enrichment QC, PreSeq saturation curves, exomePeak2 (transcript-aware, GC-bias-aware negative-binomial GLM) peak calling, optional MACS3 broad-peak cross-check, DRACH motif confirmation as a sanity check (NOT a per-peak filter), exomePeak2 differential calling via the four-BAM-vector interface (bam_ip + bam_input control; bam_treated_ip + bam_treated_input treatment), ChIPseeker annotation, and the canonical Guitar metagene with stop-codon enrichment as the biological QC anchor. Use when running a complete MeRIP analysis from raw reads, when chaining the constituent epitranscriptomics skills (merip-preprocessing -> m6a-peak-calling -> m6a-differential -> modification-visualization), or when wrapping the pipeline in Snakemake / Nextflow.

ariffazil Skill

OpenClaw-native /propose-seal — proposes a sealed candidate to 888-APEX. NEVER self-seals. Pipeline: agent proposes → 888 judges → F13 authorizes → 999 executes (append to VAULT999).

ariffazil Skill

OpenCode-native /propose-seal — proposes a sealed candidate to 888-APEX after a code mutation. NEVER self-seals. Pipeline: OpenCode compiles evidence → 888 judges → F13 authorizes → 999 appends to VAULT999.

ariffazil Bundle

Build GitHub Actions CI/CD pipelines, Docker multi-stage builds, and deploy-verify patterns for VPS af-forge.

ariffazil Skill

Real-time Caddy HTTP error spike monitor, Docker container log stream analyzer, and automated container health recovery watchdog.

gptomics Bundle

Operates the QIIME2 framework as the glue for an amplicon analysis - the .qza/.qzv artifact model, semantic types (FeatureTable[Frequency], SampleData[PairedEndSequencesWithQuality], Phylogeny[Rooted], FeatureData[Taxonomy]), embedded provenance plus provenance replay, import (Casava/manifest/EMP/BIOM), export, the Metadata object, and the q2cli vs Artifact API interfaces. Covers why a .qza is data-plus-executable-history not a file, why export drops provenance, why a .qzv is terminal, why classifier .qza are version-pinned, and the 2026 distribution/rachis rename. Use when importing reads, choosing a manifest/Casava/EMP/BIOM path, reading or replaying provenance, exporting to BIOM/phyloseq, fixing semantic-type or Phred or sklearn-version errors, or orchestrating the pipeline. Denoising -> amplicon-processing; classifier/DB -> taxonomy-assignment; diversity metric/depth -> diversity-analysis; DA tool -> differential-abundance; PICRUSt2 -> functional-prediction; shotgun moshpit -> metagenomics.

oimiragieo Bundle

Evaluates completed agent pipelines across 5 scoring dimensions and produces a composite verdict with actionable recommendations

ariffazil Skill

Full VPS Docker status — all containers, resource usage, arifOS health. Use when Arif asks about container status, VPS health, what's running, memory/CPU usage, or wants to restart/rebuild services.

gptomics Bundle

End-to-end Ribo-seq analysis from FASTQ through periodicity QC, P-site calibration, ORF detection, translation efficiency, and stalling. Use when orchestrating a full ribosome profiling pipeline and deciding harvest/dedup/alignment options and which downstream analyses the library can support.

oimiragieo Bundle

6-phase multi-agent pipeline with approval gates. Orchestrates Plan→Design→Implement→Review→Test→Deploy phases with explicit entry/exit criteria, phase-level agent assignment, and human-in-the-loop approval checkpoints.

oimiragieo Bundle

Cloud and DevOps expert including AWS, GCP, Azure, and Terraform

ariffazil Bundle

Monitor and manage the arifOS federation: docker compose ps, restart dead services, MCP health probes (Observed Port Map), container drift detection, restart count monitoring. USE WHEN: "federation status", "restart dead container", "container health", "docker drift", "service down", "probe MCP", "health check federation". Runs on af-forge (VPS) — native docker and curl required.

ariffazil Skill

Invoke arifOS constitutional MCP tools (000-999 pipeline, F1-F13 enforced). Use to call arif_* tools on the arifos_remote MCP server.

gptomics Bundle

Calls germline SNPs and indels with Google DeepVariant, which reframes variant calling as CNN image classification over multi-channel pileup tensors. Covers platform-specific model selection (WGS, WES, PACBIO, ONT_R104, HYBRID_PACBIO_ILLUMINA), one-shot run_deepvariant vs the three-stage make_examples/call_variants/postprocess_variants pipeline, GPU acceleration of call_variants, DeepTrio for family/trio and de-novo calling, and joint genotyping of gVCFs with GLnexus (not GenotypeGVCFs). Use when deciding DeepVariant vs GATK vs DRAGEN, picking the right --model_type for a sequencing platform, avoiding post-hoc GATK hard filters or BQSR that degrade CNN calls, calling de-novo variants in a trio, merging a DeepVariant cohort, or weighing GIAB-trained benchmark accuracy before clinical deployment.

sboghossian-mini-claude-for-legal Skill

Use when an enterprise customer's IT administrator needs to configure Single Sign-On (SSO) for Louis using SAML 2.0 with their identity provider (Okta, Azure AD / Entra ID, Google Workspace, or Auth0). Covers the end-to-end setup flow, attribute mapping, tenant and group provisioning, testing, and rollout. Applicable across all jurisdictions for any Enterprise-tier deployment.

sboghossian-mini-claude-for-legal Skill

Use when an error occurs anywhere in the legal AI request pipeline and a structured response decision is needed. Classifies errors into six categories (transient, provider, client-input, auth/quota, backend-bug, schema/data-integrity) and outputs the correct action (retry, failover, user guidance, upgrade flow, ticket, escalation) along with a user-facing message and an optional internal ticket reference.

sboghossian-mini-claude-for-legal Skill

Use when a matter involves oil and gas contracts, energy sector licensing, upstream/downstream regulatory obligations, production sharing agreements, or energy-project law in MENA jurisdictions (Saudi Arabia, UAE, Kuwait, Qatar, Oman, Iraq, Egypt, Libya). Covers national oil company frameworks, concession and PSA structures, joint-venture arrangements, environmental and decommissioning obligations, LNG and pipeline regulation, and dispute-resolution in the energy sector. Triggers on oil and gas contracts MENA, PSA, energy licensing KSA/UAE, upstream/downstream regulation, Saudi Aramco, ADNOC, or energy project disputes.

oimiragieo Bundle

Check voice message pipeline config — verify Whisper, ElevenLabs/OpenAI TTS keys and dependencies.

sboghossian-mini-claude-for-legal Skill

Use when running the automated daily evaluation suite that measures the legal AI system's output quality across all benchmark datasets. Orchestrates the full eval pipeline — loading datasets, calling the production model, scoring with LLM-as-judge rubrics, detecting regressions, and publishing results to the leaderboard and observability dashboards.

gptomics Bundle

End-to-end 16S/ITS amplicon workflow from demultiplexed FASTQ to a consensus differential-abundance result, orchestrating cutadapt primer removal, per-run DADA2 ASV inference (learnErrors/mergeSequenceTables/removeBimeraDenovo), region-matched taxonomy assignment, a SEPP/Greengenes2 tree, alpha/beta diversity at a declared sampling depth (phyloseq/vegan, adonis2 paired with betadisper), compositional DA as a consensus of >=2 tools (ALDEx2/ANCOM-BC2) on unrarefied counts, and optional PICRUSt2 functional prediction gated on NSTI. Covers the stage-ordering decisions (primers before truncation, per-run error model, rarefy for diversity not DA, predicted potential not activity) and defers each per-step choice to the six microbiome skills. Use when staging an amplicon study end to end or chaining ASV inference, taxonomy, diversity, and differential abundance. For shotgun reads see workflows/metagenomics-pipeline.

sboghossian-mini-claude-for-legal Skill

Use to select the minimal toolset required to fulfill a request. Defaults to no tools and adds tools only when there is a clear, specific reason — preventing unnecessary RAG retrieval, web search, or paid API calls that add latency and cost without improving response quality. Consumes the output of the skip-RAG gate, tier-awareness gate, and complexity grader to produce a final tools array for the response pipeline.