Skill rating

[omh] Outdated or wrong Hermes memory entries: English-canonical Hermes memory-review guidance: inspect USER.md and MEMORY.md claims and prepare a native write diff without invoking, applying, or obse

[omh] Evaluating a plugin, connector, or API for adoption: external connector readiness - assess whether a named plugin, connector, API, data provider, or multimodal route is safe, affordable, fresh,

[omh] Unvalidated early product idea: test whether a customer problem, segment, and business hypothesis deserve product investment, ending in kill, pivot, persevere, or inconclusive before any PRD. Us

[omh] Business contract, NDA, or policy with legal risk: surface contract and compliance risks, questions, and escalation points before a legal decision or action. Use when the user says: contract rev

[omh] Security event on the code already shipped -- a CVE in a dependency, a secret committed to the repo, a license question, an advisory: triage reachability and severity, contain in order, and neve

[omh] Production is down or an incident is open: command an incident that is still open -- severity as declared live state, commander and roles, an append-only timeline, a recorded temporary mitigatio

[omh] Agent or automation safety risks: review prompt, tool, secret, dependency, destructive-action, and explicit local plugin risks before agent or code execution. Use when the user says: security-sa

[omh] Evaluating a plugin, connector, or API for adoption: external connector readiness - assess whether a named plugin, connector, API, data provider, or multimodal route is safe, affordable, fresh,

[omh] Context window or token budget at risk: plan compact context, token/cost budgets, summarization checkpoints, and overflow recovery before long agent work. Use when the user says: context-budget-

[omh] CRM pipeline or sales forecast to review: turn a supplied CRM export or pipeline snapshot into an evidence-bound pipeline health, forecast, and follow-up review. Aliases: pipeline-review, foreca

[omh] Screen-reader or keyboard accessibility gaps: prepare WCAG, keyboard, focus, screen-reader, target-size, and reflow evidence gates for UI surfaces. Use when the user says: accessibility-audit, a

[omh] Public variant claims to cross-check: retrieve and reconcile source-labelled biomedical evidence with identity, conflict and freshness checks. Use when the user says: biomedical-evidence, biomed

[omh] Commit message or pull-request body to write for a change: draft it in the repository's own convention, with `Tested:` listing only commands observed to run and everything prepared but not run u

[omh] Deliverable demands premium polish: enforce superior content, design, layout, publishing, and visual QA gates. Use when the user says: design-quality-gate, design quality gate, ui ux pro max, de

[omh] Spatial layers to intersect: execute CRS-safe polygon overlay with measured areas, validated geometry and reproducible GeoJSON outputs. Use when the user says: geospatial-analysis, geospatial ov

[omh] Agent instruction file for a repo -- AGENTS.md, CLAUDE.md, a Cursor rule: write or update what an agent cannot derive from the code, inside a marked region, with every command verified or marked

[omh] Uncertain technical choice for a spike: bounded decision prototype workflow: resolve one uncertain interaction, API, performance, or integration choice with a disposable, isolated experiment who

[omh] Team training or course that needs a syllabus: turn a learning goal into a teachable curriculum, assessment plan, and learner-ready sequence. Use when the user says: curriculum design, learning

[omh] Before data leaves the team -- a dataset, log, ticket export or transcript excerpt bound for a vendor, a public issue, a model provider or a training corpus: classify every field, minimize first

[omh] Oversized or tangled UI component: behavior-preserving refactor of UI code - preview the full change plan first, apply as a second explicit step, and work impact-ordered from state architecture

[omh] Self-hosted LLM serving on GPUs: choose the serving engine and quantization from decision tables, prepare deployment as an idempotent runbook with observed-only verification, and measure the end

[omh] Prepared PDBQT inputs: run bounded standalone Vina docking with real poses, scores and replay provenance; never infer efficacy or safety. Use when the user says: molecular-docking, rigid-recepto

[omh] Prospect or account worth pursuing: turn an account or market opportunity into a focused discovery, qualification, and next-step brief. Use when the user says: sales discovery, account plan, out

[omh] AI agent progress for managers: help managers inspect AI-agent progress, blockers, quality gates, and throughput levers. Use when the user says: agent-ops-review, agent ops review, agent product

[omh] Company budget overrun, cash risk, or close issue: turn finance and accounting inputs into a decision-ready variance, cash, and close-risk brief. Use when the user says: finance analysis, budget

[omh] Churn or weak activation among users: turn an observed onboarding, activation, retention, re-engagement, referral, or monetization problem into one consent-safe in-app journey or growth experime

[omh] Fine-tuning a model on your own data -- SFT, DPO, RLVR or a LoRA adapter: decide first whether prompting or retrieval already closes the gap, choose the method from the data you have, and promot

[omh] Native program crashes or corrupts memory: prepare hypothesis-driven debugging of native binaries and instruct the executor to drive a DAP debugger instead of printf. Use when the user says: nat

[omh] Messy or AI-generated code to clean up: delete AI-generated slop, dead code, and duplication while observable behavior stays identical. Use when the user says: ai-slop-cleaner, cleanup, deslop,

[omh] Aiming for design-award quality: score a web surface against published design-award judging axes and name the binding constraint. Use when the user says: award-bar-score, award bar score, award

[omh] Market sizing or customer/competitive analysis: investigate a scoped market with TAM/SAM/SOM sensitivity, attributed customer evidence, and comparable competitor/pricing profiles before a decisi

[omh] Accumulated tech debt to rank: build the severity-by-effort debt ledger from observed repo evidence - orient, audit the named dimensions with file:line citations, rank fixes and quick wins - and

[omh] Huge PDF or document to read in full: read a very large PDF, contract, manual, or report through Hermes in page-anchored ranges with a coverage ledger. Use when the user says: long-document-read

[omh] Data pipeline work -- an ETL or streaming job, a backfill or replay, duplicate events, a schema change downstream, a lineage question, a data-quality regression: make every rerun idempotent, bou

[omh] App idea headed for launch: shape an app idea into decisions, delivery handoff, verification, release, and monitoring status. Use when the user says: idea-to-deploy, idea to deploy, from idea to

[omh] Testing an internal control -- SOX, ICFR or ITGC: define the population and the sample, name the evidence that proves each item, re-perform the control, and grade any deficiency from stated like

[omh] Releasing an iOS or Android app through the stores -- signing, the privacy manifest, a TestFlight or Play beta, a staged rollout, a hotfix: prepare each gate the store enforces, and plan the hal

[omh] Recurring Hermes job on a schedule (cron, digests): design recurring Hermes operations with schedule, delivery, silence policy, context chain, and prepared-vs-observed status. Use when the user

[omh] Application code misbehaves -- a wrong value, a flaky test, a lost update: reproduce it first, form competing hypotheses, discriminate them with the cheapest observation, and only then fix the d

[omh] Decided cross-module refactor to phase: refactor planning - turn a decided boundary-changing refactor into a phased plan - reconnaissance, contracts-first phase order, per-phase verification and

[omh] Database work on a relational store -- a slow query, an index to size, a migration on a big table, a lock taken during deploy, N+1 queries: plan it with the checks that prove it safe, and never

[omh] Gathering candidate papers, datasets, or repos: source candidate inventory - prepare typed source candidates and acquisition status before downstream work; use ulw-research to fetch and cite the

[omh] Designing or reviewing an iOS, macOS, or Apple-style UI: prepare native Apple UI or Apple marketing product-visual direction, review, and improvement briefs with evidence-backed remediation hand

[omh] Git branch in trouble -- a merge conflict, a commit that broke something, history to repair: plan the resolution, the bisect, or the rewrite, name what is already pushed first, and force-push on

[omh] Character art to animate in a game: turn image-model sprite sheets into aligned, QC-gated frames with a fail-closed Pillow helper. Use when the user says: sprite-forge, sprite sheet, pixel sprit

[omh] Current technical or business fact to cite from web: web lookup lane - settle a current-facts question in one cited retrieval round with retrieval dates and source-quality notes; for pre-spec gr

[omh] Pull request or changes to vet: bug-first review with evidence. Use when the user says: code-review, review, audit, find bugs, release gate, claim audit, evidence audit, README claim.

[omh] LLM-powered feature to build: LLM app development: prepare a build handoff for an LLM-powered feature with a pinned provider boundary, schema-first outputs, versioned prompt files, grounded retr

[omh] Shipping a versioned release -- tag it, stage it behind a canary, or roll back the last deploy: decide what goes in, the version, the rollout stages, and a rollback with its trigger and exact co

[omh] Evaluation logs versus reported paper conditions: audit supplied HellaSwag results with exact scores and review-gated evidence; never run a model. Use when the user says: repro-audit, hellaswag