Skip to main content
ClaudeWave
Skill39.4k repo starsupdated 4d ago

hermes-tweet

>

Install in Claude Code
Copy
git clone --depth 1 https://github.com/wshobson/agents /tmp/hermes-tweet && cp -r /tmp/hermes-tweet/plugins/hermes-tweet/skills/hermes-tweet ~/.claude/skills/hermes-tweet
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Hermes Tweet

Hermes Tweet adds an X/Twitter toolset to Hermes Agent. It is useful for social
listening, account research, launch monitoring, support triage, giveaway audits,
and controlled workflows where private or state-changing operations stay
explicit.

## When to Use This Skill

Use this skill when the user wants to:

- Install Hermes Tweet into a Hermes Agent runtime
- Discover available X/Twitter read and action routes
- Read X/Twitter account, tweet, trend, monitor, or search data
- Summarize public signal before drafting responses or campaigns
- Keep private and state-changing operations gated behind explicit operator intent

## Setup

Install and enable the plugin through Hermes:

```bash
hermes plugins install Xquik-dev/hermes-tweet --enable
```

Hermes scans plugins during installation and updates. Review each warning.
A dangerous verdict blocks installation or disables an update.

Set the API key on the Hermes runtime host:

```bash
export XQUIK_API_KEY="<your-key>"
export HERMES_TWEET_ENABLE_ACTIONS="false"
```

Keep `HERMES_TWEET_ENABLE_ACTIONS` false for read-first sessions. Set it to
`true` only for an approved private read, write, monitor, webhook, extraction,
draw, or media operation.

## Inputs

Ask for these inputs before selecting routes:

- Objective: research, monitoring, support triage, giveaway audit, or action prep
- Target: account handle, tweet URL, keyword, list, monitor, or trend
- Time window and freshness needs
- Whether any private or state-changing operation is in scope
- Confirmation that the Hermes runtime has `XQUIK_API_KEY`

## Workflow

1. Search the bundled endpoint catalog with `tweet_explore` to find matching routes.
2. Read public X/Twitter data through `tweet_read` after selecting a catalog route.
3. Use `tweet_action` for private or state-changing routes only after explicit approval.
4. Keep API keys in environment variables or the Hermes runtime env file.
5. Do not paste credentials into prompts, issues, PR comments, or tool inputs.
6. Load [workflow patterns](references/workflows.md) when the user asks for a
   campaign, monitor, support, or giveaway workflow instead of a single read.

## Tool Model

| Tool | Purpose |
| --- | --- |
| `tweet_explore` | Search the bundled endpoint catalog without using the API key. |
| `tweet_read` | Call catalog-listed public read-only endpoints when `XQUIK_API_KEY` is set. |
| `tweet_action` | Call private reads, writes, monitors, webhooks, extractions, draws, and media operations only when action gating is enabled. |

## Output Format

Return concise operational output:

```text
Summary:
- What was checked and why

Read routes:
- Catalog path, input, and result summary

Action plan:
- Proposed private or state-changing operations, each awaiting explicit approval

Next check:
- Follow-up route or monitoring cadence when useful
```

## Usage Examples

Research an account before drafting a reply:

```text
Use Hermes Tweet to inspect recent public context for @example before drafting a reply.
Keep actions disabled.
```

Monitor a launch keyword:

```text
Track X/Twitter mentions for "Example Launch" today.
Summarize themes and notable accounts. Do not post.
```

Prepare a guarded post:

```text
Draft a launch tweet and list the exact tweet_action call you would use.
Wait for approval before any action route.
```

Capture structured route notes:

```json
{
  "objective": "support-triage",
  "route": "/api/v1/x/search",
  "action_gate": "disabled",
  "approval_required": true
}
```

## Troubleshooting

- If only `tweet_explore` appears, configure `XQUIK_API_KEY` on the Hermes runtime
  host and reload or restart the active Hermes session.
- If action routes are unavailable, keep public reads separate. Set
  `HERMES_TWEET_ENABLE_ACTIONS=true` only for an approved private or
  state-changing operation.
- If a route does not match, use `tweet_explore` again and choose a catalog-listed
  path instead of guessing endpoints.

## Best Practices

- Treat Hermes Tweet as the Hermes-native X/Twitter layer, not a generic API wrapper.
- Keep research read-only by default. Require approval before creating or
  changing monitors.
- Use Desktop or gateway operator review before private or state-changing calls.
- Validate the exact catalog path before calling `tweet_read` or `tweet_action`.
- Restart gateway, cron, or long-running Hermes sessions after env changes.

## See Also

The social-publishing plugin complements Hermes Tweet for broad multi-platform
publishing. Hermes Tweet is focused on the Hermes Agent X/Twitter toolset and its
read-first, approval-gated operating model.

See [the endpoint and approval contract](references/endpoint-contract.md) when a
route boundary is unclear. See the official guide at
https://github.com/Xquik-dev/hermes-tweet#readme.
screen-reader-testingSkill

Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.

wcag-audit-patternsSkill

Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance. Use when auditing websites for accessibility, fixing WCAG violations, or implementing accessible design patterns.

multi-reviewer-patternsSkill

Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.

parallel-debuggingSkill

Debug complex issues using competing hypotheses with parallel investigation, evidence collection, and root cause arbitration. Use this skill when debugging bugs with multiple potential causes, performing root cause analysis, or organizing parallel investigation workflows.

parallel-feature-developmentSkill

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system simultaneously, when establishing file ownership to prevent merge conflicts in a shared codebase, when designing interface contracts so parallel implementers can build against each other's APIs before they are ready, or when deciding whether to use vertical slices versus horizontal layers for a full-stack feature.

task-coordination-strategiesSkill

Decompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and workload balancing. Use this skill when breaking down work for agent teams, managing task dependencies, or monitoring team progress.

team-communication-protocolsSkill

Structured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid. Use this skill when establishing communication norms for a newly spawned team, when deciding whether to send a direct message or a broadcast, when a team-lead needs to review and approve an implementer's plan before work begins, when orchestrating a graceful team shutdown after all tasks are complete, or when debugging why teammates are not coordinating correctly at integration points.

team-composition-patternsSkill

Design optimal agent team compositions with sizing heuristics, preset configurations, and agent type selection. Use this skill when deciding how many agents to spawn for a task, when choosing between a review team versus a feature team versus a debug team, when selecting the correct subagent_type for each role to ensure agents have the tools they need, when configuring display modes (tmux, iTerm2, in-process) for a CI or local environment, or when building a custom team composition for a non-standard workflow such as a migration or security audit.