Hermes Skills and OpenClaw Superpowers: Reusable AI Workflows

Hermes skills are reusable procedures that tell a private AI assistant how to perform repeated work. OpenClaw users may know the same idea as OpenClaw skills or "OpenClaw superpowers." Hermes is the current runtime. The legacy term remains useful for people searching for the original concept.

The decision rule is simple: if a task repeats, has clear inputs, and should produce the same kind of output every time, it belongs in a skill. A good skill defines its trigger, inputs, allowed tools, blocked actions, approval gates, escalation rules, output format, owner, and execution receipt.

If you want Claw Empire to implement the runtime and its first skills, apply for a private AI worker setup. For the control model behind sensitive actions, read Approval-Gated AI Agents.

OpenClaw superpowers and Hermes skills

"OpenClaw superpowers" is legacy community terminology for reusable agent capabilities and procedures. In the current Claw Empire stack, Hermes skills are the practical implementation: narrow, inspectable procedures that load when a task matches their trigger. Keep the old term for discoverability, but use Hermes when describing the runtime installed and operated today.

What a Hermes skill does

A skill answers one practical question: how should Hermes do this kind of work?

A strong skill includes:

• purpose: the result the workflow should produce;
• trigger: when Hermes should use it;
• inputs: messages, files, systems, or context required;
• allowed tools: what the assistant may read or draft with;
• blocked actions: what it must not do;
• approval gates: when the assistant must stop and ask;
• escalation rules: when Hermes should hand the task to a person;
• output format: what the owner receives for review;
• receipt: what gets logged after the run;
• owner: who updates the skill when the workflow changes.

The skill should be short enough for an owner to inspect. If it reads like a policy binder, split it.

Here is a copyable starting point:

# Lead follow-up draft skill

Purpose: Prepare accurate reply drafts for qualified inbound leads.

Use when:
- A new lead arrives from an approved inbox, form, or CRM queue.

Inputs:
- Source message.
- Current offer notes.
- CRM history when available.

Allowed actions:
- Classify the lead.
- Summarize context.
- Draft a reply and CRM note.

Blocked actions:
- Send email.
- Quote price or promise availability.
- Change CRM stage.

Approval gate:
- Show the source, proposed action, draft, risk, and expected result.

Escalation rules:
- Hand off discounts, legal terms, angry prospects, or unclear ownership.

Output:
- Classification, context, draft, next action, and approval request.

Receipt:
- Log the approved action, reviewer, result, and unresolved question.

Owner:
- Sales workflow owner.

Skills vs prompts vs automation

These three get confused.

A prompt is a one-off instruction. It is useful for experimenting, but fragile when the same task repeats.

A skill is a reusable workflow. It standardizes the steps, output, tools, and stop conditions.

Automation is when that workflow runs from a trigger or schedule. Automation should come after the skill has been tested, not before.

A safe progression is: prompt to explore, skill to standardize, scheduled or triggered workflow to scale. Do not skip the middle step.

Good skill candidates

Create a skill when the task repeats and mistakes are easy to define.

Good first candidates:

• lead follow-up draft from a form or email;
• meeting brief from calendar, CRM, and recent notes;
• support ticket summary and response draft;
• daily owner briefing from open loops;
• weekly project status report;
• content outline review against brand rules;
• invoice follow-up draft;
• research brief with source links.

Weak candidates:

• "handle sales";
• "be strategic";
• "run support";
• one-off research;
• anything where the owner cannot name the stop condition.

The best first skill saves review time without pretending the assistant owns the decision.

Example: lead follow-up skill

A tiny agency might use a lead follow-up skill like this.

Purpose: prepare fast, accurate reply drafts for qualified inbound leads.

Use when: a new lead arrives from an approved inbox, form, referral message, or CRM queue.

Allowed actions: classify the lead, summarize context, draft a reply, suggest a CRM note, and ask for approval.

Blocked actions: send email, quote price, promise availability, mark a deal closed, delete the source message, or change CRM stage without approval.

Approval packet: source message, lead classification, proposed reply, CRM note, risk level, and exact action requested.

A real run: a referral lead emails on Tuesday afternoon. The skill reads the message, pulls recent CRM context, and classifies the lead as "warm referral, ready to book." It drafts a reply that names the referral, proposes two time windows, and stops before quoting price. You receive the source, draft, risk, and requested action in one review packet. After approval, Hermes can send the reply, update the CRM, and log the receipt.

That is specific enough to help and narrow enough to review.

Put approval gates inside the skill

Approval rules should be explicit, not implied. Require owner approval before Hermes:

• sends customer messages;
• changes CRM status;
• posts public content;
• edits production systems;
• deletes or archives source material;
• quotes price, timeline, discounts, or refunds;
• makes legal, financial, medical, hiring, or reputation-sensitive commitments.

For each approval, tell Hermes what evidence to show. The owner should see the source, proposed action, exact output, risk, and where the receipt will be logged.

A bare "approve?" message is too thin. The point of the skill is to make approval fast because the decision packet is complete.

Skills, memory, and runbooks are different

Do not use skills as a dumping ground for every business fact.

Use this split:

• Runbook: the business operating rules for a workflow.
• Skill: the reusable procedure for one task inside that workflow.
• Memory: stable preferences and durable facts that should persist.
• Project file: current state the assistant can reread.
• Chat: the immediate request and output constraints.

Example: "never quote price without owner approval" belongs in the runbook and relevant skills. "The owner prefers short customer replies" can live in memory. "This week is booked" belongs in current status, not permanent memory.

Test before trusting

Run the skill against real but low-risk examples. Use at least three cases:

1. normal case;
2. missing-context case;
3. risky case involving customer trust, money, timeline, or policy.

Check whether Hermes used the right source, followed the right order, stopped at approval, produced the expected format, and flagged uncertainty instead of guessing.

If the same correction appears twice, update the skill. Do not keep retyping the same instruction in chat.

Keep skills narrow

A skill should not be "Sales Assistant." It should be "Lead Reply Draft," "Proposal Follow-Up Checklist," or "CRM Note Preparation."

A useful rule: if a skill needs more than one owner, more than one approval model, or more than one source of truth, split it.

Narrow skills are also easier to retire. Old skills become hidden bugs when offers, tools, credentials, or approval policies change. Give every skill a visible owner. Review it when the workflow or permissions change, then retire it when nobody can vouch for its instructions.

First-week setup

1. Choose one repeated low-risk workflow.
2. Write the current manual process in five to ten bullets.
3. Add allowed tools and blocked actions.
4. Add approval gates and the exact review packet.
5. Define the output format.
6. Test on three examples.
7. Save corrections into the skill.
8. Use it for a week before expanding scope.

The first skill should save review time, not prove autonomy.

Recap

Hermes skills are reusable, reviewable operating procedures for a private AI assistant. Use them for repeated work with clear inputs, outputs, tools, and approval points. Keep them narrow, test them with real examples, separate them from memory and runbooks, and retire stale skills quickly.

Next step

For the broader setup pattern, read What Is a Private AI Executive Assistant? and Approval-Gated AI Agents. If you want a done-for-you implementation path, apply for a private AI worker setup.