hermes-imports

$npx mdskill add affaan-m/ECC/hermes-imports

Sanitize Hermes workflows for safe ECC reuse.

  • Transforms local operator tasks into public skills.
  • Removes credentials, paths, and private data.
  • Replaces specific accounts with generic role labels.
  • Outputs release-pack artifacts ready for deployment.

SKILL.md

.github/skills/hermes-importsView on GitHub ↗
---
name: hermes-imports
description: Convert local Hermes operator workflows into sanitized ECC skills and release-pack artifacts. Use when preparing a Hermes workflow for public ECC reuse without leaking private workspace state, credentials, or local-only paths.
origin: ECC
---

# Hermes Imports

Use this skill when turning a repeated Hermes workflow into something safe to ship in ECC.

Hermes is the operator shell. ECC is the reusable workflow layer. Imports should move stable patterns from Hermes into ECC without moving private state.

## When To Use

- A Hermes workflow has repeated enough times 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 that must be removed before publication.

## Import Rules

- Convert local paths to repo-relative paths or placeholders.
- Replace live account names with role labels such as `operator`, `default profile`, or `workspace owner`.
- Describe credential requirements by provider name only.
- Keep examples narrow and operational.
- Do not ship raw workspace exports, tokens, OAuth files, health data, CRM data, or 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 such as `/Users/...`
- `~/.hermes` paths unless the doc is explicitly explaining local setup
- API keys, tokens, cookies, OAuth files, or bearer strings
- phone numbers, private email addresses, and personal contact graphs
- client names, family names, or account names that are not already public
- revenue, health, or CRM details
- raw logs that include tool output from private systems

## Conversion Pattern

1. Identify the repeatable operator loop.
2. Strip private inputs and outputs.
3. Rewrite local paths as repo-relative examples.
4. Turn one-off instructions into a `When To Use` section and a short process.
5. Add concrete output requirements.
6. Run a secret and local-path scan before opening a PR.

## Example: Launch Handoff

Local Hermes prompt:

```text
Read my local workspace files and finalize launch copy.
```

ECC-safe version:

```text
Use the public release pack under docs/releases/<version>/.
Return one X thread, one LinkedIn post, one recording checklist, and the missing assets list.
```

## Example: Quiet-Hours Operator Job

Local Hermes job:

```text
Run my private inbox, finance, and content checks overnight.
```

ECC-safe version:

```text
Describe the scheduler policy, the quiet-hours window, the escalation rules, and the categories of checks. Do not include private data sources or credentials.
```

## Output Contract

Return:

- candidate ECC skill name
- sanitized workflow summary
- required public inputs
- private inputs removed
- remaining risks
- files that should be created or updated

More from affaan-m/ECC

SkillDescription
accessibilityDesign, implement, and audit inclusive digital products using WCAG 2.2 Level AA
agent-architecture-auditFull-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
agent-evalHead-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
agent-harness-constructionDesign and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
agent-introspection-debuggingStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
agent-payment-x402Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol.
agent-sortBuild an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.
agentic-engineeringOperate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
agentic-osBuild persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.
ai-first-engineeringEngineering operating model for teams where AI agents generate a large share of implementation output.