Skill rating
160 skills. The A–F grade combines safety (60%) and quality (40%); tests add a bonus. The rating refreshes automatically from open catalogs.
ManufacturingLogistics and warehouseProcurementQuality controlContact centreField serviceFinanceCustomer supportindustry shortcuts
| # | Grade | Skill | Score ▾ | Safety | Quality | Process | Tests | Popularity | Updated |
|---|---|---|---|---|---|---|---|---|---|
| 101 | B | [omh] Tailoring enabled OMH families: turning one OMH capability family on or off so an install can be tailored instead of taken whole. Use when the user says: capability-toggle, capability policy, di | 100 | 79 | C | — | — | 15 h ago | |
| 102 | B | [omh] Missed route or run lessons to record: classify and review self-improvement store routes as an auxiliary review lane before durable writes, then record workflow attempts as metadata-only traces, | 100 | 79 | B | — | — | 15 h ago | |
| 103 | B | [omh] Recurring operating status and blockers: status, risks, blockers, priorities, and follow-ups. Use when the user says: ops-review, ops review, weekly ops review, status review, operating review, | 100 | 79 | B | — | — | 15 h ago | |
| 104 | B | [omh] Company hiring or HR process to structure: turn hiring and people context into a fair, structured recruiting or people-operations brief. Use when the user says: recruiting plan, hiring scorecard | 100 | 79 | B | — | — | 15 h ago | |
| 105 | B | [omh] Risky command screened by Jev: Jev action check before a risky command: secrets, outbound sends, blast radius; can only add a hold. Use when the user says: jev-action-check, jev action check, as | 100 | 79 | C | — | — | 15 h ago | |
| 106 | B | [omh] Blocked on a project by a knowledge gap: just-in-time learning workflow: select and confirm an immediate learning target, research credible sources, and prepare an application-first brief withou | 100 | 79 | C | — | — | 15 h ago | |
| 107 | B | [omh] Wants Jev risk flags on a diff under review: Jev review flags for a diff: auth, tests, migration risk, severity; flags only, never approves a merge. Use when the user says: jev-review-gate, jev | 100 | 79 | C | — | — | 15 h ago | |
| 108 | B | [omh] Expensive or unconfigured web search: diagnose which search and extract providers, provider tiers, and keyless free tier Hermes reads, guide provider account setup, and apply each change as its | 100 | 79 | C | — | — | 15 h ago | |
| 109 | B | [omh] Engineering leadership over roadmap and risk: roadmap, PM, technical tradeoffs, risk, delivery, release, and follow-up operating cadence. Use when the user says: cto-loop, cto loop, cto, cto pm, | 100 | 79 | B | — | — | 15 h ago | |
| 110 | B | [omh] Shell command or test-suite execution: policy overlay for terminal commands - add cwd, environment, safety, and result-evidence gates after preferring native shell tools for ordinary CLI, packag | 100 | 79 | B | — | — | 15 h ago | |
| 111 | B | [omh] Deep dive before a decision: deep research engine - grounding for specs and decisions: study open-source reference implementations with pinned refs, gather live web evidence with citation discip | 100 | 81 | B | — | — | 15 h ago | |
| 112 | B | [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 th | 100 | 79 | C | — | — | 15 h ago | |
| 113 | B | [omh] Parallel tool-call capability in doubt: report the version and whether MCP parallel tool calls are enabled, then apply the diff for parallel tool calls only after approval; an update only on req | 100 | 79 | B | — | — | 15 h ago | |
| 114 | B | [omh] Business question on market, competitors, pricing: business research brief - turns a market, competitor, pricing, or customer question into a structured evidence-vs-inference brief; for raw link | 100 | 79 | C | — | — | 15 h ago | |
| 115 | B | [omh] Mail and calendar brief configuration: morning brief SETUP (one-time) - connects mail and calendar MCP with read-and-draft-only scope and diff approval; produces the configuration, not the daily | 100 | 79 | B | — | — | 15 h ago | |
| 116 | B | [omh] Aborting an active workflow: ending active workflow state cleanly. Use when the user says: cancel, stop the workflow, abort the run, cancel the loop. | 100 | 79 | C | — | — | 15 h ago | |
| 117 | B | [omh] Folder cleanup, renames, or deletions: policy overlay for local file tasks - add path scoping and destructive-action gates after preferring native file tools for ordinary list, search, organize, | 100 | 79 | B | — | — | 15 h ago | |
| 118 | B | [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, herm | 100 | 79 | C | — | — | 15 h ago | |
| 119 | B | [omh] Email, Slack, or Jira action to perform: external app actions - email, Slack, Discord, Notion, Linear, Jira, CRM, and similar providers, scoped with auth, payload, confirmation, and result-evide | 100 | 79 | C | — | — | 15 h ago | |
| 120 | B | [omh] Explaining OMH itself: current-source-first documentation for OMH itself: product identity, public capability catalog, model routing, local state, and long-term memory. Use when the user says: p | 100 | 79 | B | — | — | 15 h ago | |
| 121 | B | [omh] Undecided OMH route handed to Jev: Jev route pick: answer an OMH route question about which workflow fits, recorded without re-routing. Use when the user says: jev-route, ask jev which workflow, | 100 | 79 | C | — | — | 15 h ago | |
| 122 | B | [omh] Browser login, click, or form task: policy overlay for browser tasks - add auth, confirmation, and observed-trace gates after preferring the native browser for ordinary URL, click, login, and fo | 100 | 79 | B | — | — | 15 h ago | |
| 123 | B | [omh] User named Jev for yes/no or pick-one probabilities: Jev ask: typed yes/no, pick-one, or scored questions to Jev with your own key; returns probabilities, never prose. Use when the user says: je | 100 | 79 | C | — | — | 15 h ago | |
| 124 | B | [omh] OMH install misbehaving: diagnosing oh-my-hermes installation health. Use when the user says: doctor, diagnose omh, installation health. | 100 | 79 | B | — | — | 15 h ago | |
| 125 | B | [omh] Installing, removing, or editing skills: managing local skills. Use when the user says: skill, skills, manage skills. | 100 | 79 | C | — | — | 15 h ago | |
| 126 | B | [omh] Lost track of agent sessions and worktrees: normalize Codex, Claude Code, Hermes, OpenCode, Cursor, MCP host, worktree, and wrapper session metadata into one drift-aware inventory. Use when the | 99 | 79 | B | — | — | 15 h ago | |
| 127 | B | [omh] Attack paths into an operated system: turn a system's components and data flows into assets, trust boundaries, attack scenarios, controls, and the security test that proves each control holds. U | 97 | 83 | B | — | — | 15 h ago | |
| 128 | B | [omh] Provider credentials without exposure: prepare provider-profile metadata without reading secrets or calling providers. Use when the user says: provider-profile-posture, provider profile posture, | 99 | 79 | B | — | — | 15 h ago | |
| 129 | B | [omh] Hidden or swallowed errors suspected: find swallowed errors, unsafe fallbacks, hidden UI/runtime failures, and missing propagation before they become false green status. Use when the user says: | 99 | 79 | A | — | — | 15 h ago | |
| 130 | B | [omh] Unsure whether Codex or Claude Code is ready: executor runtime readiness - compare Codex, Claude Code, Hermes coding, and oh-my runtimes by tools and handoff mode; use external-connector-readine | 99 | 79 | B | — | — | 15 h ago | |
| 131 | B | [omh] Proof a change is done before merge: define and record build, lint, typecheck, test, security, docs, generated-output, and CI evidence before completion or merge. Use when the user says: verific | 100 | 78 | B | — | — | 15 h ago | |
| 132 | B | [omh] Product or company copy to publish or rewrite: scope publish-ready writing, rewriting, summarization, translation, release-note, newsletter, customer-copy, social-copy, README-copy, and email-dr | 99 | 79 | B | — | — | 15 h ago | |
| 133 | B | [omh] Previously rejected options to revisit: recall scoped reviewed rejected decisions without elevating them to approved memory. Use when the user says: decision-recall, rejected decision recall, re | 99 | 79 | B | — | — | 15 h ago | |
| 134 | B | [omh] Career search to interview: find verified opportunities, tailor evidence-grounded applications and track confirmed outcomes. Use when the user says: ai-job-search, job search, evaluate this job | 100 | 78 | C | — | — | 15 h ago | |
| 135 | B | [omh] Dataset or table to analyze: scope supplied data with provenance, causal-claim, and hallucination guards. Use when the user says: data-analysis, data analysis, dataset analysis, csv analysis, js | 99 | 79 | B | — | — | 15 h ago | |
| 136 | B | [omh] Bot replies via Discord, Slack, or Telegram: normalize Discord, Slack, Telegram, and other gateway sessions into origin, thread, delivery, silent, attachment, and status-update policy. Use when | 99 | 79 | B | — | — | 15 h ago | |
| 137 | B | [omh] Audio, video, or screenshot to process: user-sent media - audio, video, YouTube links, screenshots, receipts, OCR, meeting recordings, transcripts, timestamps, and clip summaries, gated for sour | 99 | 79 | B | — | — | 15 h ago | |
| 138 | B | [omh] Dictated voice note about project work or status: terse voice and mobile-style requests - turn short spoken-style asks into clarify, plan, status, handoff, or confirmation actions. Use when the | 99 | 79 | B | — | — | 15 h ago | |
| 139 | B | [omh] Project fact to remember across future sessions: capture one bounded durable project or product memory candidate through explicit remember, refuse, or defer review; for a past decision use decis | 99 | 79 | B | — | — | 15 h ago | |
| 140 | B | [omh] Live rate, score, or local time a work task needs: policy overlay for live lookups - add provider, freshness, units, and source-quality gates after preferring native live-data tools for ordinary | 99 | 79 | B | — | — | 15 h ago | |
| 141 | B | [omh] Resume or finish the work we agreed on: continue or finish the accepted work from conversation context, preserve rejected ideas, and report evidence-bounded completion. Also declare and advance | 100 | 78 | B | — | — | 15 h ago | |
| 142 | B | [omh] Repository vocabulary unclear or inconsistent: project terminology alignment workflow: look up, capture, correct, and align the words a repository uses before planning or handoff. Use when the u | 100 | 78 | C | — | — | 15 h ago | |
| 143 | B | [omh] Hermes badges unlocked and achievement progress: achievements observation: summarize hermes-achievements badges, tiers, recent unlocks, and progress from local plugin artifacts. Use when the use | 99 | 79 | B | — | — | 15 h ago | |
| 144 | B | [omh] Coordinating several agents or profiles: coordinate multiple Hermes profiles or agents with task, handoff, heartbeat, blocker, and completion states. Use when the user says: agent-board, agent b | 99 | 79 | B | — | — | 15 h ago | |
| 145 | B | [omh] Software feature or bugfix not yet planned: structured planning before execution. Use when the user says: plan, implementation plan, make a plan, write a plan, write the plan, task breakdown, sa | 100 | 78 | B | — | — | 15 h ago | |
| 146 | B | [omh] Ambitious project goal needing many build cycles: agentic interviewer -> planner -> researcher -> builder -> reviewer cycles until a real gate. Use when the user says: loop, goal loop, long hori | 100 | 78 | B | — | — | 15 h ago | |
| 147 | B | [omh] Project fact to remember across future sessions: capture one bounded durable project or product memory candidate through explicit remember, refuse, or defer review; for existing Hermes memory us | 99 | 79 | B | — | — | 15 h ago | |
| 148 | B | [omh] Scattered knowledge needing a wiki: wiki construction blueprints and retained knowledge capture with destination-aware external knowledge connection guidance. Use when the user says: wiki, proje | 100 | 78 | B | — | — | 15 h ago | |
| 149 | B | [omh] Large multi-part job to run on its own: plan it as a graph of small nodes, run the ready ones in parallel through Hermes' delegate_task, verify the goal with a separate node, and repair failed n | 100 | 78 | B | — | — | 15 h ago | |
| 150 | B | [omh] Hostile scenario testing: adversarial QA and fix loops. Use when the user says: ultraqa, adversarial qa, hostile scenarios, e2e qa, real-world qa, qa scenario, release qa, 敵対的QA. | 100 | 78 | B | — | — | 15 h ago |