hermes-tweet
Install and operate Hermes Tweet, a Hermes Agent plugin for X/Twitter research, timeline reading, tweet analysis, and approval-gated private or state-changing operations. Use this skill when installing Hermes Tweet, researching X/Twitter accounts, monitoring launch signals, inves
Install
npx skills add https://github.com/wshobson/agents/tree/main/plugins/hermes-tweet/skills/hermes-tweet
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install wshobson-agents@llmmart
git clone https://github.com/wshobson/agents.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole wshobson/agents collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
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:
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:
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
- Search the bundled endpoint catalog with
tweet_exploreto find matching routes. - Read public X/Twitter data through
tweet_readafter selecting a catalog route. - Use
tweet_actionfor private or state-changing routes only after explicit approval. - Keep API keys in environment variables or the Hermes runtime env file.
- Do not paste credentials into prompts, issues, PR comments, or tool inputs.
- Load workflow patterns 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:
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:
Use Hermes Tweet to inspect recent public context for @example before drafting a reply.
Keep actions disabled.
Monitor a launch keyword:
Track X/Twitter mentions for "Example Launch" today.
Summarize themes and notable accounts. Do not post.
Prepare a guarded post:
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:
{
"objective": "support-triage",
"route": "/api/v1/x/search",
"action_gate": "disabled",
"approval_required": true
}
Troubleshooting
- If only
tweet_exploreappears, configureXQUIK_API_KEYon 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=trueonly for an approved private or state-changing operation. - If a route does not match, use
tweet_exploreagain 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_readortweet_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 when a route boundary is unclear. See the official guide at https://github.com/Xquik-dev/hermes-tweet#readme.
Files (agents)
-
references
-
endpoint-contract.md 1.6 KB
# Endpoint and Approval Contract Use this reference when a selected Xquik route or approval boundary is unclear. The rules apply to CLI, Desktop, dashboard, gateway, scheduled, and delegated Hermes Agent sessions. ## Tool Matrix | Tool | API key | Network | Action gate | User approval | | --- | ---: | ---: | ---: | ---: | | `tweet_explore` | No | No | No | No | | `tweet_read` | Yes | Yes | No | No for public read-only routes | | `tweet_action` | Yes | Yes | Yes | Yes for the exact operation | `tweet_explore` reads the bundled catalog. `tweet_read` accepts only catalog-listed public read-only routes. `tweet_action` handles writes, private reads, monitors, webhooks, extraction jobs, giveaway draws, and media operations. ## Approval Checklist Before calling `tweet_action`, state and confirm: 1. The catalog-listed endpoint and method. 2. The target account or workflow. 3. The complete payload without credentials. 4. The expected side effects and reason. 5. The user's explicit approval for this operation. Approval for one operation does not authorize retries, related operations, or future scheduled runs. Stop after policy, authentication, validation, or account-state failures. ## Runtime Checks ```bash hermes plugins list hermes tools list ``` Confirm that `tweet_explore` remains available without `XQUIK_API_KEY`, `tweet_read` appears only with the key, and `tweet_action` remains unavailable unless `HERMES_TWEET_ENABLE_ACTIONS=true` is intentionally configured. After environment changes, reload an active CLI session. For gateway use, run `hermes gateway restart`, then start a new gateway session. -
workflows.md 1.4 KB
# Hermes Tweet Workflow Patterns Use these patterns when the request is broader than one route lookup. ## Social Listening 1. Search for search, trend, radar, and monitor routes with `tweet_explore`. 2. Use `tweet_read` for public read-only routes. 3. Ask for approval before creating or changing a monitor with `tweet_action`. 4. Group results by theme, account, link, and recency. 5. Recommend a follow-up read route when the signal is incomplete. ## Support Triage 1. Read mentions, account context, and relevant tweet threads. 2. Summarize the user problem without exposing credentials or private runtime data. 3. Draft replies separately from action calls. 4. Ask for explicit approval before any private read, reply, DM, follow, or webhook operation. ## Giveaway Audit 1. Read the original tweet, replies, reposts, followers, and public lists. 2. Keep an evidence trail of route paths and result summaries. 3. Ask for approval before private reads, extraction jobs, or giveaway draws. 4. Present candidate next steps after the public read-only evidence is complete. ## Controlled Publishing 1. Confirm that `HERMES_TWEET_ENABLE_ACTIONS=true` is intentional for this session. 2. Draft the content and identify the exact `tweet_action` route. 3. Show media, reply, scheduling, or account-change inputs before execution. 4. Wait for approval, then call only the approved route.
-
-
SKILL.md 5.4 KB
--- name: hermes-tweet description: > Install and operate Hermes Tweet, a Hermes Agent plugin for X/Twitter research, timeline reading, tweet analysis, and approval-gated private or state-changing operations. Use this skill when installing Hermes Tweet, researching X/Twitter accounts, monitoring launch signals, investigating mentions, auditing giveaways, or preparing gated X operations. Use proactively when a Hermes Agent workflow needs current X/Twitter context. Requires XQUIK_API_KEY for read and action tools. license: MIT metadata: version: "0.1.13" source: https://github.com/Xquik-dev/hermes-tweet homepage: https://github.com/Xquik-dev/hermes-tweet#readme --- # 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.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.