Skip to content

rlaope/oh-my-hermes / skills/omh-research-department

omh-research-department

Verified

[omh] Recurring market or topic research: research operations department - coordinate Scout, Analyst, and Briefer work with source-inbox and status boundaries; for one decision brief use `omh-research-brief`, and for typed candidates before research starts use `omh-source-finder`. Use when the user says: research-department, research department, research ops department, research operations department, scout analyst briefer, scout analyst brief, daily research department, competitor research department.

Research Department

This is a Hermes-native research-department workflow skill.

Why This Exists

research-department exists so Hermes users can start complex research-ops patterns without manually designing profiles, cron, knowledge storage, synthesis tooling, and delivery glue, while OMH keeps every runtime claim observed-only.

Do Not Use When

  • The user only needs a one-off current-source lookup; use omh-web-research for one cited round, or ulw-research for a reference-implementation study with a depth budget.
  • The user only needs a one-off business synthesis; use omh-research-brief.
  • The request is pure scheduling with no source collection or synthesis; use omh-automation-blueprint.
  • The user asks for coding implementation; prepare a selected executor/runtime handoff after the research plan is accepted.
  • The request is one news watch over named companies, or a scheduled run of a watch that already exists, with no knowledge store, synthesis tool, or briefing lanes to set up, and Hermes' bundled competitor-news-monitor skill is available; load that skill.
  • The user wants a one-off paper search by topic, author, category, or paper id rather than a recurring paper review, and Hermes' bundled arxiv skill is available; load that skill.

Examples

Good example:

  • Prompt: Set up a Scout, Analyst, and Briefer research flow for daily competitor and market changes.
  • Expected behavior: Prepare research_department_plan/v1 with Scout/Analyst/Briefer lanes, source inbox buckets, briefing status, knowledge-store and synthesis-tool readiness, and observed-only evidence requirements.
  • Why: The request is recurring, source-backed, and operational; a single research brief would miss the ongoing workflow/status boundary.

Bad example:

  • Prompt: research-department prove the synthesis tool queried the knowledge base and posted the Slack brief.
  • Expected behavior: Ask for observed synthesis-tool and gateway delivery evidence or mark those states as not_observed.
  • Why: The workflow pack can prepare the operating pattern, but it cannot prove external tool execution or delivery.

Completion Checklist

  • research_department_plan/v1 names topic, cadence, delivery target, knowledge store and synthesis-tool readiness, each as supplied or missing.
  • Scout, Analyst and Briefer each map to a loadable skill; source_inbox/v1 has separate raw, processed, brief, conflict and verification buckets.
  • The watchlist, the materiality threshold and one cutoff per source are written down before the first run.
  • Any schedule is not_observed unless a cronjob_manage result or a cron listing was read.

Recovery Notes

  • If one watch source cannot be read, retain covered sources' findings and the failed source's previous cutoff, mark its coverage unresolved, and hand back that source and uncovered window rather than reporting a quiet period.
  • If the synthesis tool cannot process collected findings, retain raw findings in source_inbox/v1, mark synthesis not_observed, and hand back research_department_plan/v1 with the synthesis-tool readiness gap.
  • If schedule creation has no cronjob_manage result or cron listing, retain the cadence and Scout, Analyst, and Briefer plan, mark job creation not_observed, and hand back the prepared job description for separately approved scheduling.

Workflow Lane

  • Current lane: Research and company ops - research, signals, ops, and briefings.
  • If intent belongs to another lane, hand back to omh-routing or name the adjacent workflow.
  • Shared product, routing, compatibility, and evidence rules: skill_view(name='omh-routing', file_path='references/skill-common-rail.md').

When to Use

Use when Hermes should turn an ongoing or recurring research request into a prepared Scout -> Analyst -> Briefer workflow with source inbox, knowledge-store and synthesis-tool readiness, and briefing status without claiming research execution.

Strong routing signals: `research-department`, `research department`, `research ops department`, `research operations department`, `scout analyst briefer`, `scout analyst brief`, `daily research department`, `competitor research department`, `market research department`, `paper review`, `weekly paper review`, `research paper review`, `paper research`, `notebooklm research`, `obsidian research vault`, `knowledge store`, `knowledge storage`, `synthesis tool`, `knowledge summarizer`, `research inbox`, `source inbox`, `briefing status`, `리서치 부서`, `리서치 조직`, `리서치 운영`, `수집 합성 브리핑`, `지식 저장소`, `요약 도구`, `경쟁사 리서치 부서`

Catalog Metadata

Category: research Phase: research-department Hermes role: researcher Quality tier: research-ops-gated Reasoning demand: standard

Quality bar:

  • Name topic, source boundaries, cadence, delivery target, knowledge-store destination, and synthesis-tool readiness.
  • Map Scout, Analyst, and Briefer lanes to concrete OMH skills and source inbox buckets.
  • Expose collected, synthesized, briefed, conflict, and verification counts as status, not execution proof.
  • List required evidence before claiming retrieval, synthesis, storage, delivery, or verification.
  • Inside the Scout lane, when the watch area is a set of named companies and Hermes' bundled competitor-news-monitor skill is available, run the watch through that skill; when the user names no knowledge store and the bundled llm-wiki skill is available, offer it as the store.
  • A schedule stays a prepared job description in the plan and OMH creates no job. In a Hermes session the job is created with the cronjob_manage tool, and it counts as created only from that tool's observed result or a cron listing.
  • For a recurring watch, write the watchlist and the materiality threshold down once, before the first run, and reuse them unchanged: what is watched and what is worth reporting change only by a recorded edit, so one candidate is accepted or rejected the same way on every run.
  • Report coverage source by source on every run. A source the run could not read is unknown coverage for that period and is named as a gap; it is never reported as a quiet period or as nothing new.
  • Keep one cutoff per source and move it only for a source the run covered. A source that failed keeps its earlier cutoff, so the next run reads the missed window instead of skipping it.
  • Count by the underlying event, not by article or URL: reprints, rewrites, and link variants of one announcement are one finding, and an independent second source stays attached to it as corroboration.
  • For market watches, keep a dated competitor/pricing snapshot per covered entity with source IDs, observation/effective dates, original packaging and normalized comparison units. Reuse a stable period, currency, units, source cutoff, and materiality threshold; record scope changes and distinguish a real change from changed source coverage.
  • Classify market findings as observed, vendor-asserted, or inferred and preserve contrary evidence. When coverage fails, retain the failed source's previous cutoff and name the uncovered window; do not turn a failed read into unchanged pricing or no new activity.
  • When a material event needs sizing, customer/JTBD, or comparable pricing work, hand the bounded analysis to omh-market-research with snapshot IDs, source dates, cutoff, gaps and budget; return findings to omh-research-brief before Briefer delivery. A prepared handoff does not prove any analysis ran.
  • Outreach, paid sources, and schedule creation require separate explicit approval; research-operation setup is not permission to contact customers, buy data, schedule a watch, or approve a product investment.

Handoff policy:

Keep the research operating model in Hermes. Map Scout to ulw-research/omh-web-research, Analyst to omh-research-brief/omh-web-research, and Briefer to omh-report-package or meeting/report workflows. Record retrieval, synthesis-tool output, knowledge-store writes, delivery, and verification only from observed evidence.

Required inputs:

  • topic or watch area
  • source boundaries
  • cadence
  • delivery target
  • knowledge-store preference
  • synthesis-tool preference

Expected outputs:

  • research_department_plan/v1
  • source_inbox/v1
  • briefing_status/v1
  • not-evidence boundary

Artifact expectations:

  • research_department_plan/v1 under .omh/research-department/plans when a wrapper or CLI records it

Safety rules:

  • Do not claim web retrieval, synthesis-tool query, knowledge-store write, cron creation, gateway delivery, or verification from a prepared plan.
  • Keep raw findings, processed notes, briefs, conflicts, and verification needs in separate source inbox buckets.
  • Treat vendor-specific tool names as optional aliases for synthesis-tool and knowledge-store readiness unless observed evidence exists.

Runtime Evidence

Preferred harness for this skill: research-department.

omh runtime record --skill research-department --harness research-department --status started

Record observed delegation results; otherwise return not_available or not_observed. Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.

  • Treat wrapper memory/context summaries as advisory local context, not proof of opaque Hermes memory reads or changes. Preserve workflow intent and stop conditions; verify before claiming completion. Reply in the user's own words and the host's own voice: its SOUL.md persona owns reply language, tone, speech level, and sentence endings, progress updates included (where it sets no language, use the one the user wrote in), and OMH shapes structure and content only. When the requested output is delivered, put any open points inside the result and end with no question or offer; only when the person asked to choose or decide and that choice is still theirs, end with one specific question about it, not a list, a generic offer, or a footer; the shared rail's Reply Language And Host Voice and Turn Ending sections hold the full rule.

Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.

Shared product, compatibility, topology, memory, harness, and execution rules: skill_view(name='omh-routing', file_path='references/skill-common-rail.md'). Load it when applicable; otherwise name an unavailable capability.

add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall