hope

[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 command before it is needed. Use when the user says: release-cut, release cut, cut a release, cut the release, cut a new release, tag a release, tag the release, release candidate.

The English summary is being prepared. Showing the original description.

Turn a customer support case into a reply draft, an assessment of severity and impact, and a recommended escalation path. The skill also identifies missing evidence and prepares next steps with ownership for an internal handover.

• Drafting a reply to a customer affected by a login outage
• Assessing whether a case needs engineering escalation
• Clarifying ownership and missing evidence for a support handover

Clarify inconsistent project terms using repository evidence and reviewed definitions. Answer straightforward questions, organize unresolved terminology decisions by their dependencies, and prepare a shared understanding before implementation planning or handoff.

• Aligning project terms before feature planning
• Checking the meaning and source of a project term
• Resolving conflicting names across code and documentation

Answer focused questions about current technical or business facts through web research. Get citations, retrieval dates, and source-quality notes, with conflicting evidence and inaccessible sources clearly identified instead of filling gaps from memory.

• Check current API pricing on official pages
• Find current guidance in official documentation
• Compare conflicting sources with retrieval dates

[omh] Periodic report for executives: weekly/monthly reports, executive briefs, PPT-ready outlines, and upload packages. Use when the user says: report-package, report package, weekly report, monthly report, executive report, exec brief, leadership deck, status package.

The English summary is being prepared. Showing the original description.

Investigate software slowness, memory leaks, and rising costs through measurement. Identify expensive processing paths, coordinate small reversible fixes, and compare results against a baseline with an explicit limit on acceptable performance regression.

• Investigating slow responses with an unknown cause
• Tracing steadily increasing worker memory usage
• Finding token cost hotspots

Coordinate an active production incident by recording severity, assigning roles, and maintaining a timestamped timeline. Track temporary mitigations, verify recovery against an agreed health signal, and prepare customer notices with delivery status kept explicit.

• Establish severity and roles during a production outage
• Keep a timestamped incident response timeline
• Track temporary mitigations and their removal conditions

[omh] Completion claim tested by Jev: Jev done check: does the gathered evidence support the completion claim? It can only object. Use when the user says: jev-done-check, jev done check, ask jev if this is done, jev evidence check.

The English summary is being prepared. Showing the original description.

Assess release readiness before a production launch. Review evidence for testing, security, performance, monitoring, rollback, documentation, and support, then produce a readiness matrix, a release verdict, and a list of missing evidence.

• Checking operational readiness before a production launch
• Organizing missing test, CI, and security evidence
• Reviewing rollback and monitoring plans

[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 deploy, plan to deploy, idea to launch, ship this idea, ship this feature, launch this feature.

The English summary is being prepared. Showing the original description.

Read lengthy PDFs, contracts, manuals, and reports in page-based sections. Track covered and missing pages, retain progress across resumed sessions, and merge notes into summaries or obligation lists with page references.

• Summarizing a lengthy PDF with page references
• Listing obligations and deadlines in a contract
• Resuming document reading after an interruption

Ask Jev to assess a failed run using its command, error excerpt, and retry history. Get a suggested next step—retry, fix dependencies, request access, or change approach—alongside the rule behind that decision.

• Assess whether a failed run is worth retrying
• Consider fixing dependencies after a failure
• Determine whether to request access

Prepare an implementation handoff for an LLM feature, covering model calls, validated output formats, versioned prompts, document retrieval, and evaluation datasets so future prompt or model changes can be compared against a recorded baseline.

• Planning an invoice field extraction feature
• Designing document retrieval for an LLM application
• Preparing evaluations for prompt or model changes

[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 promote a checkpoint only when it beats the untuned baseline on a held-out eval. Use when the user says: model-finetuning, model finetuning, model fine-tuning, fine-tune a model, fine-tune the model, fine tune a model, fine tune the model, fine-tune.

The English summary is being prepared. Showing the original description.

Prepare an operations board covering token use, cost, latency, run history, queues, and failures. Combine supplied metrics with Hermes records, distinguish measured values from estimates, and identify missing evidence and the next measurement needed.

• Reviewing token use, cost, and latency together
• Organizing run history, queues, and failure modes
• Summarizing supplied Prometheus or Grafana metrics

[omh] Paper or paper PDF to understand: explain a supplied paper or paper/PDF at a selected level while preserving full section coverage and source evidence boundaries. Use when the user says: paper-learning, paper learning, paper-explainer, paper explainer, paper explanation, explain this paper, explain this arxiv paper, paper walkthrough.

The English summary is being prepared. Showing the original description.

Organize agent sessions, MCP connection settings, and Git worktrees into a shared inventory. Compare metadata across tools, distinguish observed information from missing or stale entries, and identify configuration differences before assigning more work.

• Reviewing sessions across multiple coding agents
• Checking differences between MCP configurations
• Listing worktrees before assigning agent tasks

Prepare image card prompts from meeting notes, reports, pull requests, research, and releases. The skill organizes readable text and visual direction around the source and subject, while keeping prompt preparation separate from image generation, review, and delivery.

• Prepare a vertical summary card from meeting notes
• Plan a pull request summary card for reviewers
• Prepare a release announcement image prompt

[omh] Team minutes, retros, and decision history to keep: meeting minutes, scrum/sprint records, retros, decisions, and follow-up history. Use when the user says: operating-rhythm, operating rhythm, meeting minutes, meeting history, scrum record, sprint planning, sprint review, sprint retrospective.

The English summary is being prepared. Showing the original description.

Turn observed problems with onboarding, continued use, or churn into a focused in-app journey or growth experiment plan. Define the audience, consent requirements, budget, owner, and evaluation scope so the plan leads to an explicit decision.

• Plan an onboarding journey for new users
• Design an experiment to improve continued use
• Plan messages that encourage inactive users to return

Set up mail and calendar connections in Hermes for an on-demand morning summary. The workflow checks existing settings, guides authentication, and requires approval before applying changes, keeping access limited to reading and drafting.

• Connect email for morning summaries
• Connect a calendar for morning summaries
• Review connection permissions before setup

Guide the adoption of a new model generation or changed service specifications. Check model recognition, research official documentation, draft behavior-specific instructions, plan routing and pricing updates, and define baseline comparisons to measure the adjustments.

• Checking recognition of newly released model IDs
• Reviewing changed reasoning and tool-use specifications
• Drafting instructions for model-specific behavior

Review external agent prompt files before adapting them for Hermes. The skill inventories sources, checks file formats and argument placeholders, identifies command name conflicts, and records trust concerns so conversion candidates and unresolved issues are clear before implementation.

• Review Claude Code prompt files before moving them to Hermes
• Check Codex prompt formats for compatibility
• Plan mappings for arguments such as $ARGUMENTS

[omh] Model and provider configuration changes: diagnose role-slot model configuration, guide provider connection, and apply changes only after diff approval. Use when the user says: model-setup, hermes model setup, set up my models, set up my model, configure my models, configure model provider, connect my model provider, set up model role slots.

The English summary is being prepared. Showing the original description.