Hermes Imports - Setup Guide¶
Source: affaan-m/everything-claude-code (Community)
Skill: hermes-imports · Installs: 2.7K+ · Category: Workflow / DevOps
Platform: Linux, macOS, Windows
Hermes Imports converts repeated Hermes operator workflows into safe, shareable ECC (Everything Claude Code) skills. It strips private workspace state - local paths, credentials, account names, personal data - and produces release-pack artifacts ready for public distribution.
Installation¶
npx skills add affaan-m/everything-claude-code@hermes-imports
Prerequisites¶
| Requirement | Details |
|---|---|
| Hermes Agent | Working local workflow to export |
| Git | For version control of exported skills |
| ECC environment | Target for the exported skill |
When to Use¶
- A Hermes workflow has been repeated enough to become reusable
- A local operator prompt should become a public ECC skill
- A launch, content, research, or engineering workflow needs sanitized handoff docs
- A workflow mentions local paths, credentials, personal datasets, or private account names
Import Rules¶
- Convert local paths → repo-relative paths or placeholders
- Replace live account names → role labels (
operator,default profile,workspace owner) - Describe credential requirements by provider name only
- Keep examples narrow and operational
- Never ship: raw workspace exports, tokens, OAuth files, health data, CRM data, finance data
- If the workflow requires private state to make sense, keep it local
Sanitization Checklist¶
Before committing an imported workflow, scan for:
- [ ] Absolute paths (
/Users/...,/home/...) - [ ]
~/.hermespaths (unless documenting local setup) - [ ] API keys, tokens, cookies, OAuth files, bearer strings
- [ ] Phone numbers, private email addresses, personal contact graphs
- [ ] Client names, family names, non-public account names
- [ ] Revenue, health, or CRM details
- [ ] Raw logs with tool output from private systems
Conversion Pattern¶
- Identify the repeatable operator loop
- Strip private inputs and outputs
- Rewrite local paths as repo-relative examples
- Turn one-off instructions into
When To Use+ process steps - Add concrete output requirements
- Run a secret and local-path scan before committing
Verification¶
After export:
- Grep for absolute paths: grep -r "/Users\|/home/" ./exported-skill/
- Grep for credentials: grep -ri "token\|api.key\|secret\|password" ./exported-skill/
- Verify the skill works in a clean ECC environment
- Open a PR with the sanitized skill
Related Skills¶
Integration with CorpusIQ¶
CorpusIQ is the connector layer that lets AI assistants read the systems a business already runs on - accounting, payments, CRM, email, files and analytics - and answer with the source named. It is read-only by design: it retrieves data and never writes to, or acts in, a connected system, which is what makes it safe to point at live accounts.
This page is part of the CorpusIQ directory, the reference we maintain for the MCP server and agent-skill ecosystem. Run alongside CorpusIQ, a third-party server like this one can be combined with a company's own business data in a single answer.