Best Practice Research

Best Practice Research

This is a Hermes-native best-practice-research workflow skill.

Why This Exists

best-practice-research exists to keep research work explicit, evidence-backed, and inside the Hermes/executor boundary instead of relying on ad hoc chat narration.

Do Not Use When

• The request is casual chat, a status-only acknowledgement, or another workflow has stronger routing evidence.
• The user needs implementation, review, CI, merge, or external publishing evidence that has not been delegated or observed.

Examples

Good example:

• Prompt: best-practice-research: check official docs and upstream examples before we choose the plugin packaging pattern.
• Expected behavior: Gather primary-source guidance, compare options, and separate evidence from recommendation.
• Why: The request needs citation-backed best-practice research before implementation.

Bad example:

• Prompt: best-practice-research: treat casual chat or unaccepted work as if this workflow already produced verified results.
• Expected behavior: Ask a clarification question or route to a narrower workflow instead of forcing best-practice-research.
• Why: The request lacks the required inputs or would overclaim work that Hermes did not observe.

Completion Checklist

• The research question, source boundaries, recency assumptions, and confidence level are named.
• Observed sources, inference, synthesis, and unresolved retrieval gaps are separated.
• Follow-up planning or handoff uses the research summary without calling it execution evidence.

Recovery Notes

• If sources cannot be accessed, state the retrieval gap and use only observed local context.
• If evidence is thin or one-sided, lower confidence and ask for a narrower source boundary.

OMH Context Rail

• This skill is part of OMH's Hermes workflow layer, not a standalone executor.
• Product context: OMH is a Hermes-native workflow pack: choose skills, shape work, prepare artifacts, show status, and hand off with evidence boundaries.
• Current lane: Research and company ops (source-finder, web-research, best-practice-research, autoresearch-goal, research-brief, strategy-brief, feedback-triage, research-department, +6 more) - research, signals, ops, and briefings.
• If the user intent belongs to another OMH lane, hand back to oh-my-hermes or name the adjacent workflow instead of force-fitting this skill.
• Cross-skill context: every OMH skill: match lane; generic tool can render or execute.
• Generic-tool checkpoint: image->img-summary; frontend->frontend/a11y/visual-qa; paper->paper-learning; content->content-operator; media->media-input-operator; file->materials-package; search->web-research; live->live-info-operator; audit->workspace/production/security; failures->build-failure; verify->verification-gate; code->codegraph/onboarding/ultraprocess.
• Coverage: Every generated workflow skill carries this rail.
• Normal users talk to Hermes; OMH CLI is infra.
• Boundary: Prepared OMH routing, cards, handoffs, or artifacts are not observed execution, image generation, delivery, review, CI, merge-readiness, or merge evidence.

Use When

Use when correctness depends on current official or upstream guidance.

Strong routing signals: best-practice-research, best practice, official docs, upstream guidance

Catalog Metadata

Category: research Phase: evidence Hermes role: researcher Quality tier: source-gated

Quality bar:

• Use official or upstream sources first and name the version/environment assumptions.
• Map applicability to the user's local context before recommending action.
• Preserve residual uncertainty instead of overstating best practice.

Handoff policy:

Run as Hermes-side evidence gathering; hand coding to the selected executor/runtime only after source-backed guidance is summarized.

Required inputs:

• chosen technology
• question
• version or environment constraints

Expected outputs:

• source-backed guidance
• applicability notes
• residual uncertainty

Artifact expectations:

• research notes or citations when the wrapper captures them

Safety rules:

• Do not imply hidden Hermes runtime behavior.
• Use the smallest verification that can prove the claim.

Harness Discipline

• Start from the representative harness registry in oh-my-hermes when the workflow needs coding, research, planning, goal execution, architecture, critique, QA, or documentation lanes.
• Prefer richer evidence and clearer stop conditions over adding more workflow names.
• Use specialist lanes only when they change the quality of the answer or verification.

Runtime Evidence

Preferred harness for this skill: research.

When local shell access or a bot wrapper is available, record metadata-only evidence:

omh runtime record --skill best-practice-research --harness research --status started
omh runtime delegate --run  --requested --not-observed --result not_observed

Record observed delegation results when Hermes or the wrapper exposes them. If delegation is unavailable, keep the result explicit as not_available or not_observed.

Hermes Compatibility Contract

• Preserve the workflow intent, stop conditions, and verification discipline.
• Use Hermes-native tools, file operations, and subagent/delegation features when available.
• Do not require runtime tools, role prompts, or overlays that Hermes Agent does not expose.
• Respect omh_target_topology/v1 when a wrapper reports it: bind state to the current target/thread, adapt only the parts of this workflow that benefit from multiple Hermes agents, and fall back to single-target behavior when active_agent_count is one.
• When target topology changes from one to many or many to one, give a concise setup-change comment or use the wrapper's apply action before treating the new topology as persistent.
• Treat wrapper-supplied memory/context summaries as advisory local context, not proof that opaque Hermes memory was read or changed.
• When a runtime-specific mechanism appears in imported instructions, translate it to a Hermes-native artifact:
• goal tools -> .omh/goals/ ledgers, goal_completion_gate/v1, goal_status_card/v1, goal_continuation/v1, or explicit checklists with named next actions,
• question renderers -> one concise question in the current Hermes interface,
• native subagents -> Hermes delegation when available, otherwise sequential lanes,
• shell bridge commands -> optional bridge mode only.

Execution Rules

1. Load supporting context with skills_list / skill_view when needed.
2. State the workflow target, constraints, validation evidence, and stop condition.
3. Keep progress evidence-backed.
4. Verify with the smallest relevant test or inspection before claiming completion.
5. If Hermes cannot provide a required runtime capability, say so and use the fallback above.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: rlaope
• Source: rlaope/oh-my-hermes
• License: MIT
• Homepage: https://rlaope.github.io/oh-my-hermes/

Install and usage instructions live in the source repository linked above.