jeremylongshore/tons-of-skills-marketplace / plugins/community/hermes-tweet/hermes_tweet/skills/hermes-tweet
hermes-tweet
VerifiedUse Xquik in Hermes Agent for public X research, monitoring, thread summaries, creator discovery & approved actions. Not affiliated with X Corp. Use when the user requests X data or a named action. Trigger with "search X", "monitor X", "post tweet", or "X trends".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.0 KB |
| references/endpoint-contract.md | markdown | 2.6 KB |
| skill-card.md | markdown | 3.6 KB |
skill-card.md
View on GitHub# Hermes Tweet Skill card
This is a public self-assessment, not NVIDIA verification.
Do not present Hermes Tweet as NVIDIA-verified unless the release also includes
a clean SkillSpector scan report, Tier-3 eval data, `BENCHMARK.md`,
`skill.oms.sig`, and signature verification instructions for the exact reviewed
skill directory.
## Owner
- Published by Xquik.
- **Repository.** https://github.com/Xquik-dev/hermes-tweet
- Licensed under MIT.
- **Version.** 0.1.13
- **Primary Skill.** `SKILL.md`
## Use case
Hermes Tweet helps Hermes Agent users find X/Twitter endpoints, perform
authenticated X/Twitter reads, and run explicitly approved X/Twitter workflow
actions through the bundled Hermes Tweet tools.
Use it for:
- Searching tweets, reading tweet details, replies, and user profiles.
- Preparing action previews for posts, replies, follows, direct messages,
monitors, webhooks, extraction jobs, media workflows, and giveaway draws.
- Keeping X/Twitter automation inside catalog-listed Xquik API routes.
Do not use it for account connection, re-authentication, billing, credit top-up,
support tickets, or direct HTTP fallback routes.
## Inputs and configuration
- **Required configuration.** Set `XQUIK_API_KEY` in the runtime
environment. Never request, echo, log, or store the value.
- **Action gate.** Set `HERMES_TWEET_ENABLE_ACTIONS=true` before
write-capable tool calls.
- **Project plugin gate.** Set `HERMES_ENABLE_PROJECT_PLUGINS=true` for
trusted local Hermes project plugin loading.
- **User input.** Accept natural language, endpoint choices, and explicit action
payload approval.
## Capabilities
- **Tools.** `tweet_explore`, `tweet_read`, and `tweet_action`.
- **Network.** Required only through catalog-listed Xquik API routes reached by
those tools.
- **Shell.** Not required for normal operation. Use Hermes CLI commands only for
installation and registry diagnostics.
- **Files.** Not required for normal operation. Do not write reports, credentials,
logs, screenshots, or cached payloads unless the user asks for an explicit
export workflow.
- **MCP.** Not required.
## Outputs
- Endpoint recommendations from `tweet_explore`.
- Concise summaries of authenticated read results from `tweet_read`.
- Action previews, JSON-like payloads, and post-call summaries for
user-approved `tweet_action` calls.
- Troubleshooting guidance for missing configuration or disabled action gates.
## Side effects
- `tweet_explore` has no external side effects.
- `tweet_read` performs authenticated reads.
- `tweet_action` may change account or workflow state only after explicit user
approval and only when the action gate is enabled.
## Known risks and mitigations
- **Broad requests.** Start with `tweet_explore`, prefer `tweet_read`, and require a
user-approved endpoint plus payload before `tweet_action`.
- **Exposed secrets.** Ask only for environment configuration, never key values, and
never put credentials in tool arguments.
- **Guessed endpoints.** Accept only catalog-listed `/api/v1/...` paths. Reject direct
HTTP fallbacks.
- **Account changes.** Keep `HERMES_TWEET_ENABLE_ACTIONS=false` by default. Summarize
side effects before any account-changing call.
## Release trust gate
Before broad enterprise release or any NVIDIA-verified claim:
1. Run SkillSpector against the complete skill directory.
2. Resolve critical or high findings.
3. Add Tier-3 eval data and `BENCHMARK.md` for the reviewed release.
4. Sign the exact reviewed skill directory and publish `skill.oms.sig`.
5. Verify the published directory with the expected certificate chain.
## References
- `SKILL.md`
- `README.md`
- `after-install.md`
- `SECURITY.md`
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |